Downloads 2026
Number of events: 9215
- $\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
- $\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
- $\chi$-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
- $\delta$-Mem: : Efficient Online Memory For Large Language Models
- $\epsilon$-Good Action Identification in Fixed-Budget Monte Carlo Tree Search
- $f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
- $\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
- $h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
- $\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
- $\mathbf{\mathtt{MAD\text{-}Bench}}$: How Do Multimodal Agents Deceive You?
- $\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
- $\mathrm{Bounded\mbox{-}RS}$: A Bounded Evaluation Protocol and Testbed for Representational Systematicity
- \$OneMillion-Bench: How Far are Language Agents from Human Experts?
- $PAS^2$: Physics-Anchored Spectral Reasoning for Air Quality Forecasting
- $\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
- $\pi^2$: A Simple Framework for 2D-to-3D Registration
- $R^2E$: A Role-driven Reward Evolutionary Framework for Automated Reward Function Design
- $R^3$: 3D Reconstruction via Relative Regression
- $SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
- $\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
- $\textbf{EchMo}$: End-to-End Radar Echo Segmentation
- $\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
- $\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
- $\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics
- $\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
- 2D Spatial Reasoning with Adaptive Neural Cellular Automata
- 2nd Embodied Spatial Reasoning (ESR) Workshop
- 2nd Workshop on Advances in Representation Learning for Earth Observation (REO-2)
- 2nd Workshop on Principles of Generative Modeling (PriGM)
- 2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
- 3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds
- 3DABSeg: Adaptive 3D Ankle Bone Segmentation with Multiscale Feature Fusion Mixture-of-Experts
- 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
- 3D Consistency Tokens
- 3D Fresnel Volumizing for Efficient Implicit Velocity Field Reconstruction
- 3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
- 3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows
- 3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
- 3D Point Splatting for mmWave Radar Novel View Synthesis
- 3D Skew Normal Splatting
- 3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism
- 3D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identification
- 3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
- 8th Robot Learning Workshop: Is Physical AI Going Zero-Shot?
- A$^2$IQL: Adaptive Asymmetric Implicit Q Learning for Automated Warehouse Consolidation
- A$^3$Bench: A Benchmark for Compositional Reasoning over Aggressive Interactions in Videos
- A2Eval: Agentic and Automated Evaluation for Embodied Brain
- A2I: Adjacency-to-Image Structural Encodings for Graph Learning
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
- A Batched Hartigan's $k$-Means Clustering
- ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
- ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
- A Benchmark for Omni-Modal Reasoning in Long Videos
- AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
- ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
- A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
- A Bitter Lesson for Data Filtering
- A Black-Box Reduction from Regret to Multi-Level Coverage
- AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark
- Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction
- AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
- AcceleGrad#: Adaptive Geometry-Aware Acceleration
- Accelerated Image Editing via Consistency-Aware Source Token Pruning
- Accelerated last-iterate convergence of Extragradient via power-law stepsizes
- Accelerating Diffusion Language Models via Structured Suffix Modeling
- Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding
- Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
- Accelerating Long-Context LLM Prefill via Layer-wise Progressive Token Pruning in Local Deployment
- Accelerating Neural Network Training with Augmented Koopman Dynamics
- Accelerating Rectified Flow Models via Trajectory-Aware Caching
- Accelerating Safe Reinforcement Learning with Massive Parallelism
- Accelerating the Inference Era with AI-Driven, Globally Optimized HW/SW Co-Design
- Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
- AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration
- Accuracy of Noise Ceiling Estimators for Brain Scores
- Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
- AC/DC on a Budget -- Alternating Sparse Phases
- ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
- ACDP: Architecture-aware Cross-Dataset Performance Predictor for NAS
- ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
- ACER: Towards Generalizable Protein-ligand Co-folding
- A Characterization of Latent Variable Causal Models Consistent with Observational Data
- Achieve Latency-Efficient Temporal-Coding Spiking LLMs via Discretization-Aware Conversion
- Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling
- Achieving Better Local Regret Bound for Online Non-Convex Bilevel Optimization
- Achieving Directional-Stationarity from a Single Random Direction Step
- Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
- A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models
- A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
- A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry
- A Composite Activation Function for Learning Stable Binary Representations
- A Comprehensive View of Fairness through Distributional Stability
- A Computational Perspective to Data Ablation Experiments
- A Constrained Bi-level Optimization Framework for Constrained Preference-Based Reinforcement Learning
- A Control-Theoretic Approximation to Predictive Coding Dynamics
- AcousticBench: Measuring Acoustic Perception in Large Audio Language Models
- ACQueReLlo: Alignment-Aware Constrained Quantization via Reinforcement Learning for Large Language Models
- A Critical $\beta$-Scale for Posterior Collapse in Dirichlet $\beta$-VAEs
- A Cross-Interaction Neural Architecture for Submodular Functions
- Acting without Knowing: Planning, Prediction, and Transfer Dissociate in Interactive Visual Physics
- Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
- Action Chunking Proximal Policy Optimization with Feedback Correction
- Action Images: End-to-End Policy Learning via Multiview Video Generation
- Action-Level Behavior Policy Optimization for Variance-Reduced Policy Gradients
- Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
- ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
- Activation Functions Shape Token Synchronization in Stochastic Transformer Dynamics
- Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control
- Active Context Selection Improves Simple Regret in Contextual Bandits
- Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries
- Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
- Active Learning as Nullspace Regulation: A Spectral Representation Perspective
- Active Learning for Conditional Generative Compressed Sensing
- Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
- Active Learning From Positive and Unlabeled Examples
- Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
- Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval
- Active Memory Feedback Loop for Fast–Slow Dynamics in Liquid Neural Networks
- Active Probabilistic Reasoning in Humans and LLMs
- ActO: Extracting Action Representations from MLLM Embeddings for Video World Models
- Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces
- ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
- Act, Validate, Adapt: Closing the Causal Discovery-Control Loop
- ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
- A Curvature Phase Transition Governs Coherence Penalty Efficiency Against Feature Absorption in SAEs
- AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question Answering
- AdaCal: Adaptive Calibration for Robust Sparse Attention in Long-Context LLMs
- AdaCodec: A Predictive Visual Code for Video MLLMs
- AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning
- AdaKVQ: Adaptive Mixed-Precision KV Cache Quantization For Efficient Reasoning Models
- AdaMAP: Learning Adaptive Multi-Action Prediction with Grounded Dreaming Guidance
- AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation
- Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
- AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks
- AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery
- AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation
- AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
- AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
- AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
- ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
- Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery
- Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
- Adapting to Conflict: Equilibrium Structure and Adaptive Learning in Harmonic Games
- Adapting Vision Transformers to Organoid Imaging
- Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
- Adaptive and Neutral Theory of Evolution Strategies for Large Language Models
- Adaptive Attribute Completion with Representation Space for Incomplete Graph Domain Adaptation
- Adaptive auditing of AI systems with anytime-valid guarantees
- Adaptive Calibration in Non-Stationary Environments
- Adaptive Communication Range for Scalable Cooperative Multi-Agent Reinforcement Learning
- Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection
- Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
- Adaptive Coordinate Transforms for Neural Operators
- Adaptive Covariance and Multi-Layer Alignment for Out-of-Distribution Detection
- Adaptive Delayed-Update Cyclic Algorithm for Variational Inequalities
- Adaptive Entropy-Sparing for Efficient Reasoning
- Adaptive Feature Propagation for Attribute-Missing Graph Clustering
- Adaptive Fine-Tuning Scheduler for Multi-Tenant Edge LLM via Convergence-Aware Bandits
- Adaptive Gated Simplicial Propagation for Node Classification in Multimodal Graphs
- Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
- Adaptive Inference for Functionals of M-Estimands
- Adaptive Internal Readout for Native Multimodal Models
- Adaptive Joint Testing of Policies in Discounted Markov Decision Processes
- Adaptive LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries
- Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
- Adaptive-Margin Masking and Restoration for Balanced Multimodal Learning
- Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
- Adaptive Multi-Frame Learning for Expressive and Stable Atomic Representations
- Adaptive multiscale operator correction via learned spectral subspace and physics-informed optimization.
- Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics
- Adaptive Power Iteration Method for Differentially Private PCA
- Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
- Adaptive Random Forests from Online Learning and Testing by Betting
- Adaptive Realizable Regression from Two Online Learners
- Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
- Adaptive Robust Estimator for Policy Optimization in Reinforcement Learning
- Adaptive Scheduling Pipeline For Multi-Instance Asynchronous Reinforcement Learning
- Adaptive Stepsizes for Eligibility Traces in Deep Reinforcement Learning
- Adaptive Target-Charging with Privacy Filters and Individual Accounting
- Adaptive Test Case Discovery for LLM-Assisted Decision Making in High-Stakes Domains
- AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift
- AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation
- ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
- AdaSRU: Adaptive Source-Free Recommendation Unlearning via Gradient-Constrained Optimization
- AdaST: Adaptive Coupling for Spatial-Temporal Forecasting
- AdaState: Self-Evolving Anchors for Streaming Video Generation
- AdaTree: Serving-Aware Adaptive Tree Construction for Speculative Decoding
- AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes
- AdDirector: Anchored Guidance for Generating Camera-Controllable Advertisement Videos
- Addressable Memory for Video World Models
- Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning
- Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options
- A Deep Learning Framework for Scalar-on-Function Models
- AdERA: Adaptive Exponent Reuse for Lossless Allgather in Sharded MoE Training
- Ad-Hoc Teamwork from Human Demonstrations
- A Diagnostic Benchmark for Layered Layout and Template-Variant Reasoning
- A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
- A Differentiable Interior-Point Method in Single Precision
- ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
- A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning
- AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising
- ADKV: A Low-Overhead Adaptive Delta Quantization for KV Cache in LLM Inference
- ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
- A Doubly Smoothed Decentralized Stochastic Minimax Optimization Algorithm
- AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
- AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
- A Dual-Domain Vision Transformer with Spectral Positional Bias
- Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
- Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models
- Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization
- Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
- Advectra: Asymmetric Latent Transport for Non-Stationary Physics
- Adversarial Attack and Defense for Machine Learning in Statistical Physics
- Adversarial Corpus Selection to Attack Subgraph Matching based Graph Retrieval
- Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair
- Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
- Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball
- Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
- AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
- A dynamical systems theory of reward-modulated learning in linear recurrent networks
- A Dynamic Decomposition Strategy for the MOEA/D With Proven Performance Guarantees
- AEGIS: Adaptive Efficient Generative Inference Scheduling for Structured Latent Models
- AEGIS: Almost Surely Safe Offline Reinforcement Learning
- AegisFlow: Training-free Non-myopic Path-safe Guided Flow Matching
- Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
- AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
- AEON: Unifying Video and 3D World Models
- AERO: Adaptive Ensemble-Disagreement Routing for Oracle Feedback in Sample-Efficient Online RLHF
- AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting
- AeroMosaic:Transport-Aware Multimodal Evidence Fusion for Atmospheric Pollution Risk Inference
- AesGI-Bench: Benchmarking and Evaluating the Aesthetic Quality of AI-Generated Images via Large Multimodal Models
- AET-Bench: Pixel-Accurate Atomic Tomography Is Not Atom-Accurate
- AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL
- A Faster Algorithm for the Half-Trek Criterion in Structural Causal Models
- A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling
- A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition
- Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification
- Affine-invariant Cubic Newton with Weak Learners
- Affine Tracing: A New Paradigm for Probabilistic Linear Solvers
- AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation
- A Foundational Model System for Datacenter Machine Repairs
- A Frank-Wolfe Approach to Goldstein Stationarity
- A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
- A General Concept-based Decomposition for Vision–Language Embeddings
- A General Filter-Enhanced Approach to Smartphone Hyperspectral Imaging
- A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
- A general kernel framework for non-CND distance measures using $|\mathcal{D}|$-dimensional sparse landmark embeddings
- A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing
- Agent$^2$ RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?
- Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
- AgentAbstain: Do LLM Agents Know When Not to Act?
- AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
- AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
- AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs
- AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
- Agent Explorative Policy Optimization for Agentic Multimodal Reasoning
- AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
- AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
- AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
- Agentic Abstention: Do Agents Know When to Stop Instead of Act?
- Agentic AI Benchmark and Application for Enterprise Tasks
- Agentic AI Design Should be Mediated to Promote Social Welfare
- Agentic AI-Empowered Dynamic Survey Framework
- Agentic AI for Biological Discovery: Toward Closed-Loop Life-Science Intelligence
- Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
- Agentic Geometry Problem Solving via Human-like Parallel Bidirectional Reasoning
- Agentic-imodels: Evolving agentic interpretability tools via autoresearch
- Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
- Agentic Multi-Turn Reasoning: A Fairness Approach
- Agentic Neural Architecture Search
- AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
- AgenticOS: Co-designing Systems and ML Foundations of an OS Layer for Agentic AI
- Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
- Agentic Systems for Molecular Sciences
- AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?
- Agentic Video Editing from Underspecified Requests
- AgentKernelArena: Benchmarking Performance and Generalization of AI Coding Agents on GPU Kernels Optimization
- AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
- AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
- Agent MechSuits : Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
- Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
- Agent-Native Research Artifacts
- AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
- AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems
- AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
- Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection
- Agent Security is a Systems Problem
- Agents' Last Exam
- AgentSSL: Can MLE Agents Leverage Unlabeled Data?
- AgentTailor: Dual-Gate LLM-Assisted Re-ranking for Personalized Long-Tail Recommendation
- Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning
- AgentVista: Evaluating Multimodal Agent in Ultra-Challenging Realistic Visual Scenarios
- AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
- Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks
- AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games
- Agnostic Language Identification and Generation
- Agnostic Online Learning with Reliable Abstention
- A Graph Foundation Model for Unified Clustering
- Agreement without Coverage: Conditional Agreement is Non-Identifying in Variable-Support Structured Extraction
- Agree to Disagree: Multimodal Autonomous Negotiation and Calibration for Entity Representation Learning
- A Grid Efficient Transport Optimization Model for the Wasserstein Barycenter Problem
- AgriManager: A Framework and Benchmark for LLM-RL Generalization in Agricultural Management
- AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning
- A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory
- A Hierarchical Tokenization Framework for Voxel-Level fMRI Representation Learning
- A Hierarchical World Model for Driving
- A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
- AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
- AI4Mat-NeurIPS-2026: NeurIPS-2026 Workshop on AI for Accelerated Materials Design
- AI Agents for Biomedical Imaging and Multimodal Clinical Data
- AI Agents May Always Fall for Prompt Injections
- AI Agents Push Humans Out of the Loop
- AI Alignment Can Build Moral Autonomy
- AI and Science: Evolution or Extinction?
- AI and the Self: Human Identity, Authenticity, and Agency in the Age of AI
- AI-Assisted Classification under Correlation Neglect and Trust
- AI at Scale for Clinical Impact (ASCI): Cancer Pathology Foundation Models
- AI Behavioral Evaluation Should Be Grounded in Psychophysics Across Marr’s Levels
- AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation
- AI Control for Sandbagging on Fuzzy Tasks
- AIDaR: AI Data Readiness for Scientific Discovery
- AI Evaluation Should Require Standardized Item-Level Data Releases
- AI for Chip Design
- AI for Drug Discovery: Bridging the Translation Gap
- AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes
- AI for Meta-Science: Scaling and Organizing Science in the Age of AI Scientists
- AI for Peace
- AI for Science: Verification in the Age of AI Scientists
- AI for Stochastic Dynamics: From Theoretical Foundations to Scientific Applications
- AI for Verifiable Coding: Human-Aligned Collaborative Agents for Autoformalization, Proofs, and Heuristics
- AI Foundations for Power Grids: From Models to Deployment at Scale
- AI GAMESTORE: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
- AI-Generated Content Should Be Evaluated by Its Substance, Not Its Source
- AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence
- AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference
- AI-Mediated Communication Can Steer Collective Opinion
- AI Models Can Provably Hide Arbitrary Capabilities
- AIRA 2: Overcoming Bottlenecks in AI Research Agents
- AIRA-Compose: Agentic Discovery of Neural Architectures
- AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection
- AirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting
- AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space
- AI Safety Evaluations Need More Human-AI Experiments
- AIs with Secret Loyalties are a Serious but Addressable Threat
- A Kernel Nonconformity Score for Multivariate Conformal Prediction
- AKTD: FDR Control for LLM Training Data Detection under Approximate Exchangeability
- ALAM: Algebraically Consistent Latent Transitions for Vision-Language-Action Models
- A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability Lifecycle
- A latent control model for realistic rodent motion
- A Latent-Load Framework for Reliability Analysis and Intervention Design in LLM Pipelines
- A Latent World-Action Model with Jointly Aligned Reasoning
- ALETHEIA: A Multi-Frequency Eddy Current Pulsed Thermography Dataset for Neural Operator Learning in Nondestructive Testing
- Algebraic Machine Learning: learning as computing subsets of the subdirect decomposition from Abstract Algebra
- AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance
- Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
- Algorithmic Impact Reveals the Hidden Structure of Alignment
- Algorithms for Linear Equations with Min and Max Operators Under (Absolutely) Halting Condition
- Align $\&$ Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
- Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
- Align and Distill: Unifying and Improving Domain Adaptive Object Detection
- Align as You Couple: Learning Spatial Resolved Inference from H&E Images with Mollified Flow Matching
- Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
- AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
- Aligned Delta-Triplane Transformers as Occupancy World Models
- Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
- Aligning AI Teams
- Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference
- Aligning Flow Map Policies with Optimal $Q$-Guidance
- Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
- Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
- Aligning Language Model Benchmarks with Pairwise Preferences
- Aligning Language Models with Selective Prediction
- Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF
- Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
- Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions
- Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
- Alignment Dynamics in LLM Fine-Tuning
- Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
- Alignment Is Not Enough for Safe Medical LLM Evaluation
- Alignment Needs 'Cognitive Control': On The Role of Regularization in LLM Alignment
- Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
- ALIGN-Rec: Continual Recommendation under Heterogeneous Unlearning Requests
- A Little Robustness Is All You Need: Leveraging Predictions for Contextual Optimization
- All-Addition Spiking Diffusion Models with Attention Enhancement
- Alleviating Hallucination with Training-Free Uncertainty-Guided Steering
- All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
- Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
- AlloGen: Conformation-Selective Binder Design with Differential State Scoring
- AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
- Alloy Agents Can Be More Dangerous Than Either Model Alone
- All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping
- Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
- Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift
- A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds
- A Locality-Aware Surrogate for Natural-Gradient Descent in Quantum Optimization
- A Locally Tokenized Generative Model for Robust Time-Series Watermarking
- A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
- AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
- AlphaPROBE: Alpha Mining via principled retriveval and on-graph biased evolution
- AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
- ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs
- A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
- AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
- A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)
- AMARIS: Merging Generalist and Specialist LLMs via Adaptive Subspace Inheritance
- A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
- A mathematical theory of balancing relational generalization and memorization
- A Matter of Interest: Understanding Interestingness Judgments of Math Problems in Humans and Language Models
- A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
- AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
- AmbientFM: A Foundation Model for Ambient Sensing
- AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
- A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
- A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
- A Mechanistic Analysis of Looped Reasoning Language Models
- A Mechanistic Interpretability Study of an Astronomical Foundation Model
- A Mechanistic Investigation of Theory of Mind in a Large Language Model
- A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems
- A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
- A Method-Class Divide in Sub-4-Bit Quantization:\\Iterative vs.\ Single-Pass Sensitivity to Data Composition
- A method to automatically discover symbolic local learning rules
- AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
- AMGenC: Generating Charge Balanced Amorphous Materials
- A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
- A Model of Diverse Sampling from Language Models
- Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning
- Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
- Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
- Amortized Molecular Optimization via Group Relative Policy Optimization
- Amortized Optimal Transport from Sliced Potentials
- Amortized-Precision Quantization for Early-Exit Vision Transformers
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
- Amortized Vine Copulas for High-Dimensional Density and Information Estimation
- Amortizing Generative Guidance for Model-Based Reinforcement Learning
- Amplitude Decoupling in Gaussian Process Training: Exact Decomposition, Pole Cancellation, and Evaluation-Efficient Optimization
- AMPS: Adaptive Modality Preference Steering via Functional Entropy
- A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation
- A Multimodal Benchmark for Evaluating Cause-of-Death Inference Using Child Health and Mortality Data
- A multi-scale information geometry reveals the structure of mutual information in neural populations
- AMUSE: Anytime Muon with Stable Gradient Evaluation
- AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation
- AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
- Analytical Correction for Subsampling Bias in Drifting Models
- Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
- Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models
- An Analytical Model of Compute-limited Multistage Training Pipelines
- An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
- Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training
- Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation
- Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
- Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring
- An Axiomatic Analysis of DPO and NLHF as Reference-Dependent Probabilistic Voting Rules
- Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
- ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
- Anchored Protein Engineering
- Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
- Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
- Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG Measurement
- Anchoring Reasoning Distillation via Syntactic Constraints
- Anchor PCA
- AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
- AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
- ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
- AndroidReality: How Far Are Mobile Agents from the Real World?
- A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
- An Educated Guess: Deriving Statistically Aligned Gradient Estimates for Zeroth-Order Optimization
- An Efficient Algorithm for Thresholding Monte Carlo Tree Search
- An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection
- An Efficient Geometric Characterization of Robust Fair Learning
- An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
- An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
- An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
- An Equivariance Principle for Optimizer Design: Symmetry-Compatible Updates for Embeddings, LM Heads, and MoE Routers
- A New Framework for Quantum Reinforcement Learning
- A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
- A New Perspective on XAI: Scientific Theory Building for Auditable Artefacts
- An exact information theory of generalization phase transitions in Bayesian diffusion models
- Angular Networks: Low-Bit Learning from Randomized Similarity Estimators
- Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
- An In-Depth Analysis of Hallucination Detection Methods for Vision-Language Models
- An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing
- An Information-theoretic Framework for Auditing Unfairness in Training Data
- Annealing in variational inference mitigates mode collapse: a theoretical study on Gaussian mixtures
- Announced Breaks Separate Conformal Reliability from Frequency Calibration
- An Open-Source Training Dataset for Foundation Models for Black-box Optimization
- An Õptimal Differentially Private PAC Learner for Concept Classes with VC Dimension 1
- A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures
- Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive
- Antibody Generation via Redistributed Latent Diffusion
- Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
- AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
- AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency
- AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation
- AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
- AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
- Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion Editing
- Anytime-Valid Conformal Risk Control
- Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling
- AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
- ApertureAttn: Native 4K Video Generation with Image-Only Supervision
- APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
- APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
- AppCIF-Bench: An Application-Level Complex Instruction Following Benchmark for Large Language Models
- Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
- Approaching Effective Merging in Model Embedding Space
- Approaching I/O-optimality for Approximate Attention
- Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
- Approximate Envy-Free Allocations up to any k Goods
- Approximate Matrix–Vectors Under a Bounded $\ell_1$ Assumption and Applications to Kernel Matrices
- Approximate Memory Suffices for Universal Approximation with State Space Models
- Approximation Algorithms for GPU Pricing under Finite Capacity
- Approximation Guarantees for Robust Aggregation in Federated Learning
- Approximation in Contrastive Representation Learning
- Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
- APPSolver: Adaptive Patch Partitioning for Point-Wise Ship Flow Prediction on Unstructured Meshes
- A Primal-dual Approach for Semi-Infinitely Constrained Reinforcement Learning
- A Principled Optimal Transport Framework for Frame Selection in Long Video Understanding
- A Principled Self-Referenced Early Stopping Approach for Deep Image Prior
- A Private Empirical Defense Against Privacy Audits
- A probabilistic model of visual segmentation explains early visual cortical dynamics
- A Process-Level Evaluation of LLM Discovery Agents
- A Provably Convergent and Practical Algorithm for Gromov–Wasserstein Optimal Transport
- APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
- AptaBench: A Benchmark for Aptamer-Small Molecule Binding
- AQBENCH: Benchmarking Neural Surrogates for Air Quality Forecasting
- A Quantitative Visual Taxonomy of Worldwide Writing Systems
- AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
- Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
- ARCANA: A Benchmark for Abstraction and Analogical Reasoning
- ARC-Encoder: learning compressed text representations for large language models
- Archimedean Copula Inference via Taylor-Mode AD
- Architecture-Embedded Physics Priors for Mitigating Spectral Bias in Physics-Informed Neural Networks
- ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
- Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
- AR-Edit: Training-Free Streaming Video Editing without Inversion
- A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees
- Are Easier or Harder Examples Better? Rethinking Data Selection for Reward Models and Preference Optimization
- A Refined Sample-Complexity Analysis of Robust Policy Optimization under Decaying Actor Stepsizes
- A Regularization-Based Approach to Public Belief State Search for Adversarial Games
- Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test
- Are LLMs Good at Feature Engineering? Evidence from a Controlled Synthetic Benchmark
- Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
- Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Rewards
- A Reproducible Evaluation Protocol for Quantum Non-Linearity in Variational Quantum Models
- Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
- ARES: How Reliable Are LLM User Simulators for Recommender A/B Testing?
- A Retained-Signal Interface for LLM Watermark Robustness under Paraphrase
- Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
- A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks
- Are Well-Trained Surrogates Optimal? Rethinking the Surrogate Role with Instability for Unlearnable Examples
- Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
- Are we really tilting? The mechanics of reward guidance in flow and diffusion models
- Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
- Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
- Argus: A Cross-Regime Benchmark for the Transferability of Uncertainty Quantification in Computer-Use Agents
- ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
- ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
- ARROW: Augmented Replay for RObust World models
- ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation
- ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling
- Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
- Artificial Aphasias in Lesioned Language Models
- ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
- ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
- ASAP: Attention Sink Anchored Pruning
- ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
- ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
- A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
- A Scalable Multi-Task Model for Virtual Sensors
- A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
- A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines
- AsdaKV: Attention-Overlap Driven Semantic KV Retrieval for Long-Context LLMs
- A second order regret bound for NormalHedge
- A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
- A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
- A Separation Principle for Cooperative Multi-Agent Reinforcement Learning
- A Set-Sequence Model for Time Series
- ASH: Agents that Self-Hone via Embodied Learning
- A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training
- A simple model of co-emergence of grid and place fields
- A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data
- A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
- A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
- A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
- Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts
- Ask-E: An Environment for Calibrated Question Generation
- Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
- Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
- Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
- Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs
- ASO Atlas 2.0: Evaluating antisense oligonucleotide prediction across the preclinical pipeline
- A Solvable Model of Chain-of-Thought in In-Context Learning
- A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models
- A Sparse Low-Rank Biclique Decomposition for Graphs
- A Spectral Framework for Closed-Form Relative Density Estimation
- ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
- ASQ: Agent-guided Semantic-aware Quantization for Large Language Models
- AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
- Assessing Per-Sample Membership Inference Vulnerability without Retraining
- Assessing Sample Quality in Conditional Generation under Compositional Shift
- Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
- ASSET: Acquisition-Sensitive Subspace Estimation for Test-Time Adaptation of Medical VLMs
- Assign and Add: A Mechanistic Study of Compositional Arithmetic
- Assistive Dueling Bandits: No-Regret Algorithms for Assisting No-Regret Users
- A Stability Analysis of AdamW: Unstable Equilibria and Non-Convergence
- A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
- A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
- A Steerable Deep Network for Model-Free Diffusion MRI Registration
- As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
- ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
- ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations
- AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
- A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
- A Structure-Aware Higher-Order Message Passing Framework on Walk States for Graph Classification
- A Structured LLM Framework for Inorganic Material Synthesis Planning
- A Subgoal-driven RL Framework for Improving Long-Horizon Web Agents
- A Surrogate Perspective on Convergence of Fixed-Target DQN
- ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?
- AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
- Asymmetric Factorization for Low-Rank PSD Learning: When Is the Relaxation Exact ?
- Asymmetric Flow Models
- Asymmetric Generalization in Deep CTR Models: A Block-wise Diagnosis
- Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization
- Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
- Asymmetric Phase Coding Audio Watermarking
- Asymmetric Scaling Laws from Sparse Features
- AsymPipe: Accelerating Large-scale DiTs Image Editing via Asymmetry-Aware Pipeline Parallelism
- Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
- Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
- Asymptotic Anytime-Valid Inference for U-statistics
- Asynchronous Agentic Poisoning
- AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
- AsyncOPD: How Stale Can On-Policy Distillation Be?
- A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
- A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning
- A systematic evaluation of vision-language models for observational astronomical reasoning tasks
- At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections
- A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
- A Theoretical Analysis of Test-Driven Code Generation
- A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
- A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
- A Theoretical Framework for Self-Play Theorem Proving Algorithms
- A Theory of Adversary-Directed Online Learning
- A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
- A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
- A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
- A Theory of Training Profit-Optimal LLMs
- A Theory on Flow Matching with Neural Networks
- A Tight Hierarchy For Chain of Thought
- ATI-VLA: Action-Centric Predictive Vision–Language–Action Models via Actionable Alignment Then Adaptive Injection
- ATLAS: Adaptive Temporal Learning for Single-Cell Multi-Omics Alignment and Dynamics
- ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
- AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas
- AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
- AtmoZero: Self-Play Post-Training for Caption-Free Weather Time-Series Captioning
- Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics
- Atom-level Protein Representation Learning Improves Protein Structure Prediction
- AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction
- Atoms and Pivot Based Correlation Clustering
- AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
- A Topological Encoder Decoder Framework for Temporal Graph Learning
- A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs
- A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
- A Transformer-Derived Iterative Preconditioner
- A Trust Region Approach for Learning Schrödinger Bridges
- AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
- Attack-Inference Aligned Universal Adversarial Attacks on Video Object Segmentation
- Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety
- Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
- Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
- Attention Alignment Between Humans and Vision-Language Models
- Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
- Attention-based PCA
- Attention-Based Pretraining for Unsupervised Amortized Causal Discovery
- Attention-based Routing for Interpretable Multimodal Brain Encoding
- Attention-Based Sampler for Diffusion Language Models
- Attention-Based Soft Answer Sets
- Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
- Attention Drift: What Auto-Regressive Speculative Decoding Models Learn
- Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
- Attention Is More Than You Need: Spectral Redundancy in Multi-Head Routing
- Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
- Attention Sinks and Outliers in Attention Residuals
- Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention
- Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
- Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning
- Attention Transfer Is Not Universally Effective for Vision Transformers
- AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
- Attribute-Efficient Learning of Sparse Halfspaces with Constant Malicious Noise Rate
- Attribution-Guided Exit Policy for Reliable Early-Exit Inference
- Attribution-Guided Shared-Private Decoupling for Noise-Reduced Audio-Visual Representation Learning
- Attributions All the Way Down? The Metagame of Interpretability
- ATTRIB: Workshop on Data Attribution and Provenance
- A typed tensor language for federated learning
- Auction-Based Online Policy Adaptation for Evolving Objectives
- Audible World Models: Spatially Aware Sound Generation for 3D Worlds
- AudioAgentBench: Evaluating Multi-Turn Voice Agents on Real-World Tasks
- AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
- AudioGS: High-Fidelity Neural Audio Compression via Continuous Gaussian Splatting
- AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
- Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
- Auditing AI peer reviewers: a dose-response and false-positive benchmark on real scientific papers
- Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
- Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
- Auditing Conformal Prediction for Language Models Under Inference-Time Model Shift
- Auditing Correlated Failures in Frozen-Feature Pretrained-Encoder Pools for Medical Segmentation
- Auditing Cross-Lingual Fairness in Language Model Watermarking
- Auditing Evidence Framing at NeurIPS: A Decade-Scale Study of Accepted Papers
- Auditing Instruction Robustness in Vision-Language-Action Models via Diversity-Aware Red Teaming
- Auditing is not Evaluating: LLM Audit Requires Dynamic, Contextual, Budget-aware and Reliable Evidence
- Auditing Privacy Leakage in Tabular Foundation Model Embeddings
- Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
- Auditing Single-Query Recoverability in Self-Supervised Representations
- Auditing the Judge: Human-Grounded Bias Discovery, Quantification, and Mitigation in LLM Judges
- Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
- AuGhostmentation: The Eyes Never Stand Still—$\textit{Why Should CNNs?}$
- Augmented Equivariant Mesh Networks for Anatomical Segmentation
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
- Augmented Lagrangian Predictive Coding
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures
- A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
- A Unified Framework for Adversary-Aware Differential Privacy Bounds
- A Unified Framework for Image-to-3D Part Generation via Variable Granularity
- A Unified Framework for Uniform-Price Resource Allocation Mechanisms
- A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
- A Unified Image and Video Encoder for Multimodal LLMs
- A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs
- A Unified Neural Architecture for Variable-Wise Shape Constraints
- A unified pairwise distribution matching framework for graph domain adaptation under structure shift
- A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation
- A Unified Semismooth Newton Approach to Multitask and Multivariate Square-Root Lasso Problems
- A Unified Spectral Theory of Multimodal Losses
- A Unified Theoretical Framework for Task Recognition and Task Learning in In-Context Learning
- A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
- A Unifying Perspective on Language Model Interpretability
- A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
- AURA: An Autonomous Retouching Agent with Photographic Visual Thinking
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
- Auto-Annotation with Expert-Crafted Guidelines: A Study through 3D LiDAR Detection Benchmark
- AutoDataBench: How Far Are LLM Agents from Autonomously Engineering Post-Training Data Pipelines?
- Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
- Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
- AutoformBot: Formalizing Mathematics at Scale
- AutoHoney: Automating, Deploying, and Evaluating Scheming Honeypots Across Production Codebases
- AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding
- Automata from Agent Traces: Failure and Next-Step Prediction
- Automated Causal Effect Estimation through Self-Evolving AI
- Automated Hypothesis Discovery for Characterizing Annotation Disagreement
- Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
- Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
- Automatically Refining Coding Rules for AI Coding Agents
- Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning
- Automatic Textbook Formalization
- Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
- AUTOMEM: Automated Learning of Memory as a Cognitive Skill
- Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments
- Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
- Autonomous Driving Research Requires a Community-Driven Data Paradigm
- Autonomous Scientific Discovery via Iterative Meta-Reflection
- Autoregressive Appearance Prediction for 3D Gaussian Avatars
- Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
- Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
- Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria
- AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
- AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
- AuxGeoAgent: Synthesizing Challenging Geometry Proving Data via Planning and Symbolic Deduction
- Auxiliary Clues Aware’s Geometry Problem Solving
- AVENUE: Audio-Video Editing Understanding and Evaluation
- AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding
- AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
- AVIS: Adaptive Test-Time Scaling for Vision–Language Models
- AVO: Agentic Variation Operators for Autonomous Evolutionary Search
- AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
- Avoiding Feature Collapse in Graph ODEs via Hysteretic Topology Evolution
- Avoiding Obfuscation with Prover-Estimator Debate
- AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
- A World Model of Radiologist Reading for Medical Image Representation Learning
- AWP: Activation-based Window Pruning for Gigapixel Object Detection
- Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley Axioms
- Axiomatic World Modeling for Physics Reasoning
- AXIOM: Foundations of Efficient Deep Learning
- B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints
- B2P-Corr: Batch-to-Population Gradient Estimators for Non-Decomposable Correlation Losses
- Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
- BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone
- BACE: Behavior-Adaptive Connectivity Estimation from Multi-Region Neural Recordings
- Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
- Backdoor Attacks Rerouted: BatchNorm as a Sink for Adversarial Signals
- Backdoor Attacks under Lossy Compression: From Failure to Reactivation and Adaptation
- Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
- Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
- Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
- Backtracking with Linear-in-Depth Search-Space Growth: Width-Limited Tree Search for Large Language Models
- Balanced Multi-Task Learning from an Optimality-Gap Perspective
- Balancing Frequencies and Pixels in Flow Matching
- Balancing Image Compression and Generation with Bootstrapped Tokenization
- BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations
- BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning
- Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery
- BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
- Bandits via Additive Quantized Representations
- BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
- BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
- BarrierSteer: LLM Safety via Learning Barrier Steering
- Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
- Base Items Overfit, New Items Underfit: Hidden Cost of Joint Training in Incremental Adaptation
- BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition
- BASIL-DCM: Biophysical Amortized Scalable Inference for Latent Dynamic Causal Modeling
- Basis-Mediated Bilinear Attention: A New Method for Greatly Reducing Query--Key Pathway Parameters
- BASTION: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
- BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
- BA-T: An Iterative Transformer for Two-View Bundle Adjustment
- Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
- Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
- Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
- BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial Training
- Bayesian Additive Distribution Regression
- Bayesian Backprop as Belief Propagation: Single-Pass Predictive Uncertainty
- Bayesian Causal Experimental Design for CATE Estimation under Noncompliance
- Bayesian Causal Stress Testing: Posterior Fragility of Treatment-Effect Conclusions
- Bayesian Decision Making around Experts
- Bayesian Low-Rank Posteriors for Scalable Membership Inference
- Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
- Bayesian Preference Learning for Test-Time Steerable Reward Models
- Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
- BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments
- Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators
- Bayes-pFCL:Bayesian Personalized Federated Continual Learning
- BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
- Bayes-Sufficient Compression Is Not Enough: How Communication Helps in Multi-Agent Systems?
- BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
- B-CALM: Bias-Limited Bayesian Borrowing for RCT-Anchored Treatment Effects under Covariate Mismatch
- BDC-Merge: Cross-Architecture Model Merging via Dependency Alignment
- BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation
- BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
- BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
- BeamWitness: Rooted Subgraph Beam Search for Selective Graph Representation Learning
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
- Be CARE-ful with Text-to-SQL Benchmarks
- Beckmann Transport Models: From Autonomous Flows to One-Step Maps
- BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets
- Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
- Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood
- Behaving Better, Thinking Worse: Sycophancy Across Post-Training Stages
- Behavioral Foundation Models for Quality Diversity
- Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
- Behavioral Probes for Information Flow in LLM Swarms
- BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
- Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning
- Behavior Pack Optimization for Video MLLM Post-Training
- Behaviour4All: A Dependency-Aware Toolkit for in-the-wild Facial Behaviour Analysis
- Belief Engine: Configurable Stance Dynamics for Multi-Agent LLM Deliberation
- Bellman Contraction under MMD: A Unified Framework
- Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence
- BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
- Below the Reliability Floor: Recovering True Success from Judge-Gated Loops
- Benchmark for Assessing Olfactory Perception of Large Language Models
- Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs
- Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
- Benchmarking and Optimizing Multimodal Structured Generation: The OracleGraph Dataset and PRISM Framework
- Benchmarking Attention for Tabular Foundation Models
- Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
- Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
- Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline
- Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training
- Benchmarking Multi-Modal Graph-based Social Media Popularity Prediction
- Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
- Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
- Benchmarking Optimizers for Large Language Model Pretraining
- Benchmarking Risk Attitudes of LLMs
- Benchmarking Sensor-Fault Robustness in Forecasting
- Benchmarking sequence-to-ensemble predictors on UNICORNEdb, a UniProt-grouped database of PDB-derived conformational ensembles
- Benchmarking Vietnamese Legal Knowledge of Large Language Models
- Benchmark Recovery Does Not Certify a Frozen Tool-Trigger Contract After Quantization
- Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub
- Benchmarks as Measurement Instruments: Quantifying Signal and Noise for More Efficient AI Evaluations Under Distribution Shift
- Benchmarks Design under Data Scarcity: From Coarse Labels to Diagnostic Evaluation of Biosynthetic Gene Cluster Models
- Benchmark Shadows: How Data Regimes Shape Parameter Footprints and Generalization
- Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
- BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics
- Benign Reinforcement Learning Can Amplify Latent Backdoors
- Bentkus-type asymptotic e-values
- Bernini: Latent Semantic Planning for Video Diffusion
- Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
- BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
- Best Arm Identification for Bandits with Shifting Means
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
- Best-of-$N$ Guidance for Test-time Diffusion Alignment
- Bet Imaginatively, not Historically in Independent-Data Sequential Testing
- Better Language Models Require Better Domain-Specific Inductive Biases
- Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
- Beyond 3 Million Tokens: A Multi-Modal Foundation Model for Full-Resolution Heliophysics
- Beyond Accuracy: A Diagnostic Benchmark for Hypothesis-Driven Experiment Planning in LLM Agents
- Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
- Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
- Beyond a Single Score: An Audit of Aesthetic Evaluation in Text-to-Image Pipelines Across Subcultural Visual Languages
- Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
- Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
- Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models
- Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting
- Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
- Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping
- Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization
- Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
- Beyond Contraction: Geometry-Faithful Supervised Dimensionality Reduction for Data Visualization
- Beyond Coordinates: Encoding Graph Structure via Contextual Distribution and Relational Similarity
- Beyond Copy-Paste: How Well Do Subject-Driven Video Models Understand Their Subjects?
- Beyond Correctness: Robustness-Driven Evolutionary Self-Training for Large Language Models
- Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models
- Beyond Decoupled PEFT: Geometry-Aware Low-Rank Adaptation via Riemannian Reparameterization
- Beyond difficulties: Insights for provably efficient design of autocurriculum in RLVR
- Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
- Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
- Beyond Downstream Scores: Controlled Diagnostics for Point-Cloud Self-Supervised Learning Evaluation
- Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
- Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
- Beyond Eigenfunctions: Divergence Principal Functions for Representation Learning
- Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
- Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs
- Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
- Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search
- Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery
- Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
- Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
- Beyond Flat Frames: Hierarchical Graph Reasoning for Long Video Understanding
- Beyond Flat Gossip: Tiered Gossip Learning for Scalable Collaborative AI
- Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
- Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC Ensemble
- Beyond Generation: Unlocking Discriminative Representations from Diffusion Models
- Beyond Global Alignment: Structured Compositional Reasoning for Vision-Language Models
- Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness
- Beyond Hard Negatives: Grounded Positive Supervision for Compositional CLIP
- Beyond High and Low: Evaluating Graded Cognitive Diversity in LLM Persona Simulations
- Beyond ICA: Identifiability by Symmetry Breaking
- Beyond IID: How General Are Tabular Foundation Models, Really?
- Beyond Imputation: Mask-Adaptive Conformal Prediction via Tree Embeddings on General Missing Data Mechanisms
- Beyond Incremental Beam Search for Compositional Explanations of Neurons
- Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
- Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities
- Beyond Isolation: Neighbor-Consistent Data Pruning for Multivariate Time Series Forecasting
- Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
- Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning
- Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms
- Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
- Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting
- Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution
- Beyond Local Neighborhoods: Fractional Diffusion with Levy Flights on Simplicial Complexes for Link Prediction
- Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
- Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons
- Beyond Marginal Coverage: Efficient Localized Conformal Prediction via Residual Rank Calibration
- Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
- Beyond Maximum Likelihood: Variational Inequality Estimation for Generalized Linear Models
- Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
- Beyond MNIST: Limitations of Amplitude Encoding on Quantum Classification
- Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
- Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural Denoising
- Beyond Next Token Prediction: Diffusion and Flow Models for Next-Generation Decoding
- Beyond Node Sequences: Relational Diffusion for Unified Graph Learning
- Beyond Normal References: Discriminative Few-Shot Anomaly Detection
- Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors
- Beyond Outcome Rewards: Process-Aware Optimization for Search Agents
- Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
- Beyond Outcome: Trajectory-Driven Prompt Optimization via Multi-Dimensional Rewards
- Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
- Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
- Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment
- Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
- Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
- Beyond Pessimism: Offline Learning in KL-regularized Games
- Beyond Pixel Space: Frequency-Domain Uncertainty Estimation for Structure-Aware Diffusion Guidance
- Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation
- Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
- Beyond Private Training: The New Landscape of AI Privacy
- Beyond Proxy Metrics: MLLM-Based Human Surrogate Evaluation for Explainable AI
- Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
- Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
- Beyond Raw Observations: Distilling and Storing Invariant Driving Memories for Generalizable Autonomous Driving
- Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment
- Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models
- Beyond Risky Activities: Bridging the Supervision Gap for Situational Risk Reasoning
- Beyond Row Alignment: Virtual-Camera-Aware Online Stereo Rectification
- Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
- Beyond Score: A Dataset for Joint Action and Score Predictions in 2v2 Sports
- Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept
- Beyond Selection: Token Parameterization for Extreme Visual Token Compression
- Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
- Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion
- Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
- Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
- Beyond SFT-to-RL: Pre-alignment via Black-box On-policy Distillation for Multimodal RL
- Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
- Beyond Single-Shot Conditioning: Test-Time Condition Refinement for Diffusion-Based Image Restoration
- Beyond Single-Step Likelihood: Gibbs Variational Last Layers for Long-Horizon Dynamics Learning
- Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology
- Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
- Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion
- Beyond Stabilization: Dual-EMA Teachers for Global–Local Semantic Learning in Semi-Supervised Medical Image Segmentation
- Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
- Beyond Structural Agnosticism: Stable-Rank-Guided LoRA for Structure-Aware Fine-Tuning
- Beyond Success Rates: Trainability and Extractability in Offline GCRL
- Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents
- Beyond Task Success: Probing Cognitive Primitives in Web Agents
- Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation
- Beyond the Full Slate: Evaluating MNL Algorithms on All Slates
- Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
- Beyond the Grid: Continuous Dictionary Pursuit for Interpretable Signal Decomposition
- Beyond the Half Approximation: Fair and Efficient Online Class Matching
- Beyond the Linear Separability Ceiling: Aligning Representations in VLMs
- Beyond the Node Barrier: Zero-Shot Strategy Planning for LLM Training on Super-Nodes
- Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs
- Beyond the Readout: Reservoir State Statistics for Model-Space Learning under Sparse Observations
- Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
- Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training
- Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
- Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation
- Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL
- Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
- Beyond Truthfulness: Evaluating Honesty in Large Language Models
- Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image Enhancement
- Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes
- Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics
- Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
- Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
- Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
- Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
- Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling
- B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
- BFS-PO: Best-First Search for Large Reasoning Models
- Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
- BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors
- Bias, Measurement Error, and Double-Dipping: When Can GNN Convolutions Help Brain Connectome Prediction?
- BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
- Bias-Variance Optimized Preference Optimization for Large Reasoning Models
- Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
- Bidirectional Sparse Attention for Faster Video Diffusion Training
- Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics
- BigCell: Generating Gigapixel Whole-Slide Images
- Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
- Bigger Isn’t Better: Why the Indiscriminate Scaling of Foundation Models Can’t Solve Biology
- BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots
- Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
- BiLi: Bridging the Last Mile in LiDAR Localization
- Bilinear Matching Bandits
- BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode
- BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
- Binary Regression: Universal Ising Model, Binary Expansion and Beyond
- Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences
- Binding Multiple Modalities via Multimodal Wasserstein Barycenter
- Binding Visual Features Point by Point
- BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction
- Biological Graph Priors Enable Representation Learning for Cellular Microscopy
- Biomedical Acquisition-induced Style Shifts as Mixture Shifts: Style-aware Mixture-of-Experts Multimodal Prompt Learning
- BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging
- BioSafetyBench: Agentic Cascade Evaluation for the Bio-AI Ecosystem
- BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
- BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
- Birth-Death Structural Learning for 3D Gaussian Splatting
- BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
- BitDance: Scaling Autoregressive Generative Models with Binary Tokens
- BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
- Bits Beat Tokens: A Regret Rate Distortion Theory for Large Language Model Agents
- BitShift-RoPE: Zero-FLOP Relative Positional Encoding for Spiking Neural Network Transformers
- Black-Box Followers, White-Box Leaders: Partial Zeroth-Order Methods for MPECs
- Black-Box Inference of LLM Architectural Properties with Restrictive API Access
- Black-box model classification under the discriminative factorization
- Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles
- BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training
- BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
- BLARM: Animating 3D Objects from Video via Blending LAtent Rigid Motion Primitives
- BLEND: Balancing Personalization vs. Generalization in Federated Vision–Language Models
- BlendCast: Teaching Vision-Language Model to Anticipate Member Skill in Weather Ensembles
- BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs
- Blind-Window Forecasting: Real-Time Benchmarking and Multimodal Reconstruction for Tropical Cyclones
- Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
- BlockFormer: Transformer-based inference from interaction maps
- Block-OBS-GS: Exact Per-Block Joint Brain Surgery with Gauss–Seidel Refinement for LLM Pruning
- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
- Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
- Block Sparse Flash Attention
- Block Sphere Vector Quantization
- Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge
- Blur Issue Matters for Thermal Novel View Synthesis: A Floating Gaussian Suppression Approach
- BMAttn: Block-Aligned Mixed-Precision Attention Quantization for LLM Inference
- BoardGameArena: A Multi-Dimensional Benchmark for Strategic Reasoning of LLMs in Board Games
- BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation
- BodyBench: Evaluating Adversarial Image Defenses Against AI Nudification Inpainting
- Bonobo: Efficient Library-Scale Generation for De Novo Antibody Design
- BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability
- Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation
- Boosting Graph Contrastive Learning via Manifold-Guided Representation Disentanglement
- Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
- Boosting LLM Reasoning via Human-Inspired Reward Shaping
- Boosting Multiagent Reinforcement Learning at High Replay Ratios with Ensemble Reset
- Boosting Off-Policy RLVR with Data-Centric Replay
- Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
- BOOST: Power-Optimal Strong-FWER Testing for Block-Structured Multiplicity
- Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- BootstrapAgent: Turning Repository Setup into Reusable Agent Knowledge
- Bootstrapped Bipartite Actor-Critic for Diffusion RL
- Borda-Based Fair Multi-User Dueling Bandit in Tabular and Generalized Linear Settings
- Bottleneck Benchmark: Sequence Compression Under Controlled Difficulty and Fixed Latent Size
- Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace
- Boundary-Induced Forgetting in Large Language Model Tool Chains: Measuring Field-Routing Failures
- Boundary Mass in Feature Space as a Label-Budget Diagnostic for Representations
- Bound-Conditioned Latent Inference for Progressive Image Compression
- Bounding Global and Local Compression Error of Signal Parameterizations
- Bounds on Extrapolation across Phase Transitions with Generalized Regression
- BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-Tuning
- BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
- BRACE: Bipolar Reference-Aware Calibration and Estimation for Incomplete Multimodal Learning
- Brain2voice 2.0: High-performance voice synthesis brain-computer interface
- BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
- Brain Economy-Aligned Graph Transformers
- BrainEM: A Large-Scale and Diverse Benchmark for EM Neuron Segmentation in Connectomics
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG
- BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
- BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction
- BrainWhisperer: Leveraging Whisper for Speech Decoding in Neuroprosthetics
- BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics
- Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
- BraveATA: Benchmarking Broad and Verifiable End-to-End Automated Theoretical Analysis of Large Language Models
- BRAVO: Bridge Matching for Autoregressive Video Generation
- Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
- Breakeven complexity: A new perspective on neural partial differential equation solvers
- Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
- Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
- Breaking BAD: Heterogeneous Byzantine-Robust Federated Learning via Gather and Scatter Scores
- Breaking Curse of Dimensionality for Mutual Information Estimation with Vine Copulas
- Breaking feature collapse in self-supervised time series encoder
- Breaking Information Islands in Sparse Tuning via Small-World Connectivity
- Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
- Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View Generation
- Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo
- Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
- Breaking the Exactness Barrier: Interleaved DeepSeek Sparse Attention for Efficient Long Context Reasoning
- Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces
- Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers
- Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning
- Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning
- Breaking the Static: Dynamic Text Conditioning for Diverse Image Generation
- Breaking the Synthesis Barrier for AI-Designed DNA Libraries
- Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
- BReD: Block Replay Dithering for Stable Low-Bit EMA Optimizer States
- Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
- BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
- Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding
- BrickFlow: Connectivity-Guided Brick Reconstruction
- BRIDGE: Brain-Vision Representation Integration through Depth and Granularity Encoding
- Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative Modeling
- BridgeMVS: Bridging Multi-View Stereo and Monodepth via Bidirectional Dynamic Fusion
- BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
- Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling
- Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering
- Bridging CLIP with DINO: Cross-Modal Information Maximization for Online Test-Time Adaptation
- Bridging Compute- and Data-Optimal Pretraining
- Bridging Diffusion and Autoregression for Flexible Time Series Synthesis
- Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances
- Bridging Image Restoration and Recognition via Causal Mediated Unrolling
- Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
- Bridging Optimal Transport, Learning and Structured Data: Toward Geometric Distributional Learning
- Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
- Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement Learning
- Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
- Bridging Sequence and Structure with Unified Domain Adaptation for Drug-Target Interaction Prediction
- Bridging Simulation and Reality: Geometry and Decision Alignment for Autonomous Driving
- Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
- Bridging Textual Profiles and Latent User Embeddings for Personalization
- Bridging the Gap Between Harmfulness Belief and Refusal Behavior for Safety Alignment
- Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
- Bridging the Gap: Position-Independent Cache Reuse for Hybrid SSM-Attention Architectures
- Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining
- Bridging the Simulation-to-Experiment Gap with Adversarial Distribution Alignment
- Brittlebench: Quantifying LLM robustness via prompt sensitivity
- BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
- Brute-Force Jailbreaks and Codon-Aware Watermarking for DNA Foundation Models
- BSO: Safety Alignment Is Density Ratio Matching
- BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation
- BucpTSF: Breaking the Uniform Computation Paradigm in Time-Series Forecasting
- Budget-Conditioned Clipping Policies for Differentially Private Federated Learning
- Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation
- Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion
- Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making
- BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget
- Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes
- Build-and-Find: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases
- Building Transformation Layers for Riemannian Neural Networks
- BuresTomFlow: Bures-Geometric Flow Matching for Posterior Quantum Tomography
- Busemannformer: Horospherical Self-Attention for Hyperbolic Graph Transformers
- BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
- B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
- Bypassing PC1 Makes SAEs More Reproducible
- ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment
- C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-Tuning
- C2G-BENCH: A Cyber-Physical Evaluation Benchmark for Hierarchical Reinforcement Learning in Grid-Interactive Hyperscale Data Centers
- C3H: Compression-to-Consensus Criteria Hijacking in Multimodal LLM Recommender Systems
- C3: Long-Horizon Character Consistency via Causal-Continuous State Dynamics and Memory Rewriting
- C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
- C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance
- CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth
- CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
- CacheMAS: Cache Communication for Single-Pass, Jointly-Optimized Multi-Agent Systems
- Cache the Future: Training-Free Self-Revision for Diffusion Transformer Acceleration
- CADMA: Capacity-Aware Recall Decomposition for Generative Model Assessment
- CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
- CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models
- CA-Judge: Teach Large Models to Judge Anomalies via Comparison for Video Anomaly Detection
- CalArena: A Large Scale Post-Hoc Calibration Benchmark
- Calibeating Prediction-Powered Inference
- Calibrated Safe Policy Improvement for Continuous Offline Reinforcement Learning
- Calibrated Target Noise Recovers Curvature from the Gradients
- Calibrating Agentic LLMs for Clinical Prediction
- Calibrating Generative Models to Feature Distributions with MMD Finetuning
- Calibrating LLMs with Semantic-level Reward
- Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
- Calibration Is Not Control: Intervention Advantage for LLM-Agent Oversight
- Calibration without Ground Truth
- Calibration without labels in multiple testing
- CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
- CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying
- Can 4D Foundation Models Remember?
- Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
- Can AI Agents Synthesize Scientific Conclusions?
- Can an LLM Reason Like a Lawyer? Benchmarking the ability of LLMs to map the facts of a case to the elements of the applicable legal rule
- Can Bits Seal Language?
- Can Circuit Alignment Predict OOD Generalization?
- Can Complementary Signals Bridge Similarity Islands? Manifold-Augmented Graph Embedding for Multimodal Recommendation
- CANDO: Cooperative Agentic Network for Layout Design Optimization
- Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?
- Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset
- Can Hybrid-Parallel Planning Support Alternating Model–Strategy Design? Dependency-Keyed Per-Layer Primitives for Re-Planning
- Can Ideologues Agree on Quality? From Non-identifiable Latent Factors to Collective Outcomes
- Can In-Context Learning Support Intrinsic Curiosity?
- Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
- Can Large Language Models Develop Gambling Addiction?
- Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
- Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
- Can LLMs explain themselves truthfully with code?
- Can LLMs Reliably Grade Olympiad Proofs? A Controlled Study of Mathematical Verification with LLMs
- Can LLMs Take Retrieved Information with a Grain of Salt?
- Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
- Can Model Merging Improve Aggregation in DiLoCo?
- Cannistraci-Hebb Channel-wise Dynamic Sparse Training of Convolutional Neural Networks with Contextual Modulation
- Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications
- Canopy: Tree-Aware Rollout Scheduling for Agent Reinforcement Learning
- Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
- Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
- CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
- CanViT: Toward Active-Vision Foundation Models
- Can VLMs Reason When to Stop for Human Safety?
- Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
- Can We Trust AI Evaluation? Robustness, Causality, and Risk in Modern AI Assessment
- Can We Trust Item Response Theory for AI Evaluation?
- Can We Trust the Judge? Building Reliable Evaluation for Language Models
- Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing
- Capacity-Constrained Online Convex Optimization with Delayed Feedback
- CAPER: Clause-Aligned Process Supervision for Text-to-SQL
- CAPO: A Primal-Dual Framework for Constraint-Aware Prompt Optimization
- Capricorn: Highly Efficient and Secure Mixture of Experts Inference Framework
- CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
- Capturing In-Context Learning Dynamics with Task Operators
- Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
- Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators
- Cardinality-Decomposed Loss for Heterogeneous GNNs
- CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search
- CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations
- CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning
- CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
- CASAM: Consistency-Anchored Sharpness-Aware Minimization for Improved Model Generalization
- Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs
- CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
- CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
- Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction
- CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
- CASQRec: Collaborative-Adaptive Semantic Quantization for Multimodal Recommendation
- CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
- CAST: Certifiable Aggregation of Smoothed Teachers for Robust Policy Adaptation
- Castle-in-the-Air: Probing the Foundational Visual Deficits of MLLMs via Bottom-Up Cognitive Factors
- Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
- Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production
- Cat-DPO: Category-Adaptive Safety Alignment
- Categorical Bayes filtering for computational phenotyping in adaptive learning
- Caterpillar GNN: Replacing Message Passing with Graph-Level Aggregation
- CATS: Acceptance-Oriented Critical Token Adaptive Selection for Multimodal Speculative Decoding
- Cauchy Scientific Networks: Loss–Architecture Alignment and Its Limit
- Causal Abstractions, Categorically Unified
- CausalAffect: Causally Guided Learning of Psychology-Aligned Facial Affect Relations
- Causal Attribution via Activation Patching
- Causal Benchmarks for Multimodal AI Should Measure Categorical Difference, Not Capability Gap
- Causal Bias Detection in Generative Artifical Intelligence
- CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
- CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
- CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios
- Causal Concept Explanations for Deep Neural Models
- CausalConflictBench: Can Multimodal Models Follow Local Mechanisms That Conflict with Commonsense?
- Causal Discovery from Unseen Environments
- Causal discovery needs explicit epistemic standards
- Causal Discovery over Clusters of Variables in Non-Markovian Systems
- Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
- Causal Discovery under Time-Varying Delays
- Causal Discovery via Transformed Low-Rank Quantile Surfaces
- Causal Discovery with False Positive Error Control
- CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
- Causal Edit Serialization
- Causal Effect Identification with a Single Agnostic Proxy
- Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
- Causal Evaluation of Membership Inference Attacks
- Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
- Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal
- Causal heteroscedastic structure learning from incomplete temporal data
- Causal Inference for Sequential Settings under Interference and Latent Confounding
- Causality can systematically address the monsters under the bench(marks)
- Causal learning with the invariance principle
- Causally Structured Differential Network Modeling for Single-Cell Perturbation Prediction
- CausalMix: Data Mixture as Causal Inference for Language Model Training
- Causal Multi-Task Demand Learning
- Causal pieces: analysing and improving spiking neural networks piece by piece
- Causal Representation Learning
- Causal Representation Learning for Generalisable Recommendation
- CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
- Causal Survival Forests with Negative Controls
- CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery
- Causal-VLM: Dense Causal Captioning in Videos
- CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
- CCDiff: Inverse Canonical Correlation Analysis for Discovering Visual Differences in Natural Language
- CC-GS: Low-Memory 3D Gaussian Splatting Training via CPU-GPU Block-Wise Context Compositing
- CCTimeBoost: Learning Time-Varying Relative Risk with Case-Control Boosted Trees
- CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy
- CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs
- CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
- CellMSA: Context Modeling for Single-Cell Representation Learning
- CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
- CENDRe: Concept Extraction with Natural Domain Representations
- CEO-Bench: Can Agents Play the Long Game?
- Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
- Certifiably Optimal Robust Angular Synchronization
- Certification-Enhanced Generalization Bounds
- Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
- Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks
- Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
- Certified Robust Interpretability via Concept-Space Stability under Interventional Proxies
- Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid Security
- CFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting
- C-GRPO: Conformal Group Relative Policy Optimization
- CHAIN: Complementary Signed Graph Propagation for Uncertainty Quantification in Large Language Models
- CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning
- ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
- ChainForge: Tool-Chain Hijacking Attacks against LLM Agents via Execution-Grounded Tool Synthesis
- Chaining 2-FWL GNNs for Combinatorial Graph Alignment
- Chain-of-Correction: Progress-Aware Policy Steering via Anchor-Grounded Predictive Reasoning
- Chain of Dual Structures in Transformer Attention
- Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
- Chain-of-Route: State-Aware LLM Routing for Multi-Turn Conversations
- Chain-of-Thought Is Not Explainability
- Chain-of-Thought Oversight Should Not Treat Faithfulness as Monitorability
- ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
- Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
- Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation
- Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers
- Channel-wise Vector Quantization
- ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
- Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator
- Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
- Characterizing the Aesthetic Defaults of Generative Image Models
- Characterizing the Edge of Stability in Variational Training Without Priors
- Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
- Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine
- Characterizing Underrepresentation in Generalizing Causal Survival Estimates
- Characterizing Universal Object Representations Across Vision Models
- Character Mixing for Video Generation
- CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism
- ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing
- Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification
- CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators
- Chatter Attack: Resource Consumption Attack for Large Language Models
- Cheap Per-Component Testing for PLS, Stable Under Rotation
- Cheap Talk, Real Stakes: Commitment and Exploitation in Human-LLM Strategic Interaction
- Chebyshev Differential Flows for Shape Matching and Interpolation with Endpoint Guidance
- Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
- Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
- ChildPose: Foundation for Children Pose Modeling
- Child Safety in AI
- ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip Routing
- Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
- CHoRD: Coordinating Scheduling and Data Placement for Efficient Deep Neural Network Inference on Chiplet-Based GPUs
- CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination
- Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
- ChronosAlign: A Large-Scale, Updatable Benchmark for Decomposing Temporal Alignment in LLMs
- ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
- CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
- CIG: Exploration via Conditional Information Gain
- CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models
- CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation
- CipherFlow: Hardware-Aware Compiler Framework for Low-Latency Hybrid Secure Inference
- CIPHERGRID Benchmark: From Multimodal Rule Inference to Sequential Action
- Circuit-Level Knowledge Distillation for Large Language Models
- CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
- CITE: Anytime Valid Statistical Inference in LLM Self-Consistency
- Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence
- City-RAG: Stepping Into a City via Spatially-Grounded Video Generation
- CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding
- CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
- Claims of AI emergence should be grounded in information decomposition
- CLAMP: A Sim-to-Real Benchmark for Closed-Loop Kinematic Pose Estimation and Assembly Reasoning
- Clapping: Removing Per-sample Storage for Pipeline Parallel Learning with Communication Compression
- Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
- Class Adaptive Conformal Training
- Class–Domain Discriminability Guided Representation Enhancement for Domain Generalization
- Class-Domain Incremental Learning with Extensible Multi-Center Modeling
- Classification at the Edge of Stability: Unifying Self-Stabilization and Convergence Rates
- Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
- Classification of high-dimensional data with spiked covariance matrix structure
- Class-Incremental Learning via LoRA-based Elastic Ensemble of Experts
- Class-Mixed Diffusion Augmentation for Shortcut-Breaking in Continual Learning
- Claude Coke: Prevent Automated Crime by Agents
- Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
- ClawBenchPro: Benchmarking How Well Agent Harnesses Work
- CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
- Clean-Label Poisoning for Gradient-Boosted Decision Trees
- CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer
- CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification
- Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
- CLEF: EEG Foundation Models for Learning Clinical Semantics
- Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks
- CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
- ClinMAS: A Knowledge-Grounded Multi-Agent Simulation Framework for Evaluating Clinical Reasoning in LLMs
- ClinStab: Stability-Oriented Learning for Medical Time Series via Dual-Stream Alignment
- CLIOPATRA: Extracting Private Information from LLM Insights
- C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models
- Closed-Form Implicit Neural Representations
- Closed-Form Last Layer Optimization
- Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
- Closed-Loop Alignment: Socially Coupled In-Context Learning and Relational Posterior Collapse
- Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
- CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
- Closing the Approximation Gap in Simulation-free Latent SDEs
- Closing the Gap on the Sample Complexity of 1-Identification
- Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
- Closing the Loop: Co-Evolving EM for Irregular Time Series Generation in Lifted Representations
- Closing the Loop with Fixed-Point Self-Attention
- Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
- ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
- CLR-voyance : Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics
- CLUE: Closing the Loop on Conflict and Collapse in LLM Unlearning
- CLUE: Correlated Latent Uncertainty for Single-Pass Deep Uncertainty Estimation
- ClusQuant: Mitigating Outliers with Clustering-Based Representations for Low-Precision LRMs
- Clustered Randomized Smoothing for Stochastic Prediction Functions
- Clustering-Free End-to-End Spoof Diarization with Encoder-Decoder Attractors
- Clustering with Weak Distance Oracles
- ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting
- Cluster with Auctions for Vector Search
- CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
- CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
- CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
- CMI-Trans: Cross Modal Inconsistency-aware Transport for HSI-LiDAR Classification
- CMPQ: Compensatory Quantization via Input-Aware Hessian Damping
- CoANeRV: Coordinate-Aware Token-Space Neural Video Representation
- Coarsening Linear Non-Gaussian Causal Models with Cycles
- Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
- Coarse-to-Fine Autoregression over Hierarchical Discrete Codes for Molecular Graph Generation
- Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
- Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes
- Coarse-to-Refine: Trajectory Self-Refinement in Single Autoregressive Pass for Driving VLA
- COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
- CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
- Code2World: A GUI World Model via Renderable Code Generation
- Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
- CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
- CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
- Code Review Bench: An Automated Benchmark for Evaluating the Software Factory
- CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
- CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
- Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
- CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation
- CoE-Agent: Co-Evolving Patient-Doctor Agents via Interactive Policy Graph Optimization for Clinical Decision Making
- Co-evolution: A "One-to-many" LLM Fine-Tuning Paradigm
- Co-Evolving Interpolants and Flows via Path-Flow Alignment
- Co-Evolving Policy Distillation
- CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
- CoffeeBench: A Benchmark for Long-Horizon Strategic Decision-Making in Multi-Agent Economies
- CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments
- CogBench: Evaluating Cognitive-Level Control in LLM Question Generation
- Cognitive bias benchmarks should incorporate insights from ecological rationality
- Cognitive constraints and thalamocortical architecture explain systematic biases and neural signatures in human hierarchical decision-making
- Cognitive Firewalls: A Synthetic Account of Cross-Lingual Reasoning Collapse
- Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation
- COHE: Auditing Non-Transitivity in Sample Difficulty Proxies for Vision Models
- Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps
- Coherence Mechanisms for Provable Self-Improvement
- Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
- Coherent Routing in Decision Trees: Phase-Interference Learning for Interpretable Tabular Prediction
- CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation
- CoLa3D: Composable Latent 3D Decomposition
- CoLaX: Context-Aware Local Explanations for Time Series Classification
- ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
- Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
- CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
- Collapse Hunter: Tackling the Dimensional Degeneration in Generative Ranking
- COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation
- Collective Supervision for Unified Biomolecular Conformation and Dynamics Modeling with CoDyna
- ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models
- Colored Noise Diffusion Sampling
- Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
- Colour me shocked: Exact Molecular Hessians from MLIPs in O(N) time using sparse differentiation!
- CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization
- Combating Camouflage and Forgetting: Spatio-Temporal Dual Denoising for Money Laundering Detection
- Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
- Combating Data Laundering in LLM Training
- COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection
- CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
- COMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning
- CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
- Commit Then Explore: Reasoning Models Diversify, Not Converge
- Communication-Efficient Federated Learning of Latent Patient Representations from Multi-Institutional EHRs
- Communication-Efficient LLM Adaptation over Decentralized GPU Meshes
- Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
- Community-Centered AI is Feasible and Beneficial for Impacted Communities
- CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
- Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
- Comp$^2$VLM: A Hybrid Framework Combining Quantization and Lossless Compression for Efficient Vision-Language Models
- CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
- Compact Representations of Impact-Based Fair-Ranking Policies
- Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction
- Comparing Explanations is not Enough,Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
- Comparing Linear Regions in ReLU-Type Networks: Theory and Monte Carlo Methods
- Comparing Transformers and Hybrid Models at the Token Level
- COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling
- Compatible Likelihoods for Flow Matching on Manifolds
- Competing Event Models: Next Event Prediction Under Interventions
- CompilerKV: Risk-Adaptive KV Cache Compression via Offline Experience Compilation
- CompJudge: Fine-Grained Comparative Evaluation using Multimodal LLM for Subject-Driven Generation
- Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time Adaptation
- Complementing DINO Features with Image Structure for Part Discovery
- Complete or Sparse: A Tale of Two Identifiabilities
- CompleteRXN: Toward Completing Open Chemical Reaction Databases
- Complexity Aware Continuous Level of Details for Gaussian Splatting
- Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification
- Complexity-guided Regularization for Generalizable Human Gaussian Splatting
- Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
- Complexity of Differentially Private Selection via Federated APIs
- Complex Optimization Modeling via Multiagent Fine-Tuning and Skill-Augmented Reasoning
- Complex Schrödinger Bridges
- COMPLLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
- Component-Based Out-of-Distribution Detection
- Composable Causality: A Toolkit for Systematic Time-Series Causal Discovery and Treatment-Effect Benchmarking
- COMPOSE: Composing Future Theorems from Citations and Formal Structure
- COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation
- ComPose: When to Trust Hands for Object Pose Tracking
- Compose Your Oracles: Off Policy Improvement with Aggregated Guidance
- Composing Diffusion Priors with Explicit Physical Context via Generative Gibbs Sampling
- Compositional Generalization Certificates via the Van Kampen Theorem
- Compositional Policy Optimization with Language Models
- Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
- Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks
- Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
- COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
- Compressible Representations: Functional Spines in Deep Neural Networks
- Compressing Collections of Trees with Decision Equivalence
- Computational Depth Predicts Quantization Sensitivity in Multimodal Models
- Computational Dynamic Mechanism Design
- Computationally Efficient Replicable Learning of Parities and Applications
- Computationally sufficient statistics for Ising models
- Compute Aligned Training: Optimizing for Test Time Inference
- Compute Allocation Under Model-Provider Competition
- Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods
- Compute-optimal data scaling for neural surrogates via multi-fidelity training
- Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow
- Computer Science Conferences Should Require Nonrepudiable Experimental Results
- Computer Use at the Edge of the Statistical Precipice
- Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
- Computing Thiele Rules on Interval Elections and their Generalizations
- Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction--Concealment Tradeoff in MLLMs
- Concentrated Gradients Amplify Forgetting: Dominant-direction Projection for Continual Multimodal Learning
- Concept-Aware Wasserstein Routing with Vision-Language Guidance for Few-Shot WSI Classification
- Concept-Based Mechanistic Interpretability Needs a Concrete Evaluation Paradigm
- Concept frustration: Aligning human concepts and machine representations
- Concept-Localized Generative Representations
- Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
- Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification
- Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
- Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
- Concise Reasoning Through the Lens of Lagrangian Optimization
- Conclusions from Circuit Extraction Depend on the Level of Description: A Controlled Comparison
- Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization
- Concord-SLAM: Cross-Render Concordance for Boundary-Native Semantic Gaussian SLAM
- Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
- Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Process
- CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA
- Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates
- Conditional Evaluation of Language Models with Cheap Auxiliary Signals
- Conditional independence and graphical models for rankings
- Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
- Conditional Multi-Event Temporal Grounding in Long-Form Video
- Conditional Optimal Bridge for Riemannian Activation Steering
- Conditioning Gaussian Processes on Almost Anything
- ConfDet: Learning Reliable Confidence for MLLM-based Detection
- Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
- Confidence-Based Diffusion Sampling with Geometric Readiness Awareness for Accelerated Structure-based Drug Design
- Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
- Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
- Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
- Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
- ConforFlux: Particle-Guided Trunk Repulsion for Diverse Protein Conformations
- Conformal Agent Error Attribution
- Conformal Cache: Reliable Proxy-Discrepancy Caching for Fast Generative Inference
- Conformal Language Modeling via Posterior Sampling
- Conformal Prediction for Distribution-to-Distribution Regression
- Conformal Prediction for Time-Dependent PDEs
- Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification
- Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
- Confounding-Aware Client Selection in Federated Learning via Causal Mediation Analysis
- ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading
- ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
- Conservation Laws for Diffusion Models
- Conservatism Controllable Compositional Guidance for Offline Safe Reinforcement Learning
- Conservative Continuous-Time Treatment Optimization
- Conservative neural posterior estimation via distributionally robust training
- Conservative Pareto Set Amortization for Offline Multi-Objective Optimization
- Consilience for Verifier-Free Test-Time Scaling
- Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
- Consistency-Preserving Concept Erasure via Unsafe–Safe Pairing and Directional Fisher-weighted Adaptation
- Consistency Regularised Gradient Flows for Inverse Problems
- Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
- Consistent 3D Surface Flow Model with Global State
- Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods
- Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
- Consistent One-vs-All Losses Robust to Misspecification of the Weak Label Transition Model
- Consolidating Reasoning with Test-Time Learning
- Consolidating Rewarded Perturbations for LLM Post-Training
- Constant Term Shrinkage for Federated Learning
- Constrained Bombieri Point Processes
- Constrained Code Generation with Discrete Diffusion
- Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
- Constrained Factorization with Diagonal Scaling: Rank-Revealing Training and Pruning
- Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning
- Constrained Graph Clustering: A Spectral Algorithm with Generalized Eigenvectors
- Constrained Look-ahead Guidance for Interference-Aware Flow Editing
- Constrained MDPs with Trajectory Constraints
- Constrained Modulatory Reservoirs for Context-Dependent Computation
- Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
- CONSTRAINER: Promptable Graph-Structured Optimization via Constraint Conditioning
- Constraint-Aware Influence Estimation in Deep Constrained Learning
- Constraint Retrieval Is Not Constraint Enforcement in Large Language Models
- Constructive Neural Policies for the Quadratic Assignment Problem via Multi-Expert Imitation
- Consumer Search and Social Learning in Agentic Markets
- Contact Geometry for Generative Models: An Unbalanced Optimal Transport Formulation
- Context as Low-Rank Weights: Bounded Parametric Dynamic Memory for Unbounded Context
- Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
- Context-Aware Generative Imputation for Robust Multimodal Learning in Missing Modality Scenarios
- Context Binding and Reusable Leakage in Threshold Decryption
- ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
- Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
- Contextual Flow Matching for High-quality Visual Content Generation
- Contextualized Evaluation of Vision Language Models through Dynamic Interviews
- Context Value Informed In-Context Reinforcement Learning
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- Continual Learning for Enterprise AI Agents
- Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
- Continual Learning in the Era of Foundation Models and Embodied Agents
- Continually Evolving Skill Knowledge in Vision Language Action Model
- Continual Robot Learning via Language-Guided Skill Acquisition
- Continual World Models
- Continuity Laws for Sequential Models
- ContinuLoc: Continuous Pose Inference over Neural Fields for UAV Geo-Localization
- Continuous Audio Thinking for Large Audio Language Models
- Continuous-depth Deep Gaussian Processes
- Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
- Continuous Latent Diffusion Language Model
- Continuously-Augmented Hybrid Masked Diffusion Model for Data Imputation
- Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs
- Continuous p-adic Optimization
- Continuous Personalized Diffusion Model via Spinor-Component Forward Geometry
- Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
- Contour Monte Carlo: Sampling via Energy Level Sets
- ContractBench: Can LLM Agents Preserve Observation Contracts?
- Contractive Monoids: The Algebra Behind Stable Residual Propagation in Deep Graph Neural Networks
- Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability
- Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
- Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning
- Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
- Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
- Contrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weathers
- Contrastive Identification and Generation in the Limit
- Contrastive Nonmyopic Objective Cost-Tradeoff Acquisition for Longitudinal Data
- Contrastive Pretraining Scales Agentic Exploration
- Contrastive Representation Shaping for LLM Unlearning
- Contrastive Retrieval Heads for Improved Attention-Based Reranking
- Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
- Contribution-Aware Structured Sparsity for Model Merging
- Control-Augmented Autoregressive Diffusion for Data Assimilation
- Control Charts for Multi-Agent Systems
- Control First, Robustness Next: Decoupled Representation Learning for Visual RL Generalization
- ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling
- ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
- Controllable and Content Based Recommendations
- Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
- Controllable Generative Sandbox for Causal Inference
- Controllable Molecular Generative Foundation Models
- Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
- Controllable Road Marking Generation
- Controllable User Simulation
- Controlling for Omitted Variable Bias in Deep Neural Networks
- Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time Adaptation
- Controlling Transient Amplification Improves Long-horizon Rollouts
- Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
- ControlSVG: Exploring Controllable SVG Generation with Autoregressive Models
- Control Under the Wrong Model Is Better Than Under the Correct One
- Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
- Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents
- Convergence of Near-Linear Width ReLU Networks with Unbalanced Initialization
- Convex Compositional Reasoning Models
- Conveyance: A Versatile Framework for Learning in Structured Class Spaces
- Cool Graphs: Active Property Search Towards Quantum Nano-Refrigerators
- COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
- Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
- Co-optimization for Adaptive Conformal Prediction
- Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
- Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
- CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
- Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
- COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
- CoQuant: Covariance-Aware Rotation for 2-bit KV Cache Quantization
- CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
- CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewards
- CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
- CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding
- CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
- CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
- Coreset-Induced Conditional Velocity Flow Matching
- Coresets for Clustering Using Noisy Comparisons and Few Distance Queries
- Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
- CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
- Correctable Fork Tokens: Verifier-Anchored Selective Credit Assignment for Tool-Integrated RLVR
- Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
- Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models
- Correction Space Steering for Hallucination Mitigation in Large Vision-Language Models
- Corrective Diffusion Language Models
- Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback
- Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
- Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
- Correpondence Alignment For Improved Virtual Try-On
- Correspondence Pruning by Iterative Structural Rectification
- CorridorLight: Cooperation as Task Negotiation with Causal Gating for Traffic Signal Control
- Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring
- Corruptions of Supervised Learning Problems: Typology and Mitigations
- CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
- Cortically-Resolved Recurrent Architecture for fMRI
- CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
- COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
- CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration
- Cosine is Human: The Reproducibility Ceiling of Perceptual Similarity
- COSMIO: A Benchmark for Cross-Survey Modality Imputation
- Cost-Aware Best-LLM Identification using Dueling Feedback
- Cost-Aware Learning
- Cost Efficient Fairness Audit Under Partial Feedback
- CoT-Guard: Small Models for Strong Monitoring
- CoTrek: Toward Scalable On-Policy Distillation for Long Chain-of-Thought Reasoning
- CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language Models
- Counterfactual Debugging the World Model Transfer Gap
- Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent
- Counterfactual Estimation under Composite Treatments via Progressive Distribution Alignment
- Counterfactual Explanations for Time-Series Classification via Constrained Flow Matching
- Counterfactual Instruction Grounding for Vision-Language-Action Models
- Counterfactual Maps: What They Are and How to Find Them
- Counterfactual Online Conformal Prediction Under Adaptive Logging
- Counterfactual Predictive State Representations: The Intrinsic Dimension of Partial-Information Games
- Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
- CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
- CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting
- CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs
- Coupled Guidance for Flow Matching
- Coupled Integral PINN for Discontinuity
- Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games
- Coupling Models for One-Step Discrete Generation
- Covariate-Adjusted Deep Causal Learning for Heterogeneous Panel Data Models
- COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
- Coverage-Based Calibration for Post-Training Quantization via Weighted Maximum Coverage over Outlier Channels
- Coverage-Verified Sparse Attention: Closed-Loop Quality Control for Long-Context LLM Decoding
- CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation
- CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
- CP-MLPs: A Tensor-Rank Theory of Tied and Untied MLP Blocks
- CPSea2: Composing Terminal Geometries for Structurally Diverse Cyclic Peptide Binder Design
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
- CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
- CRAFT: Conflict-Resolved Aggregation for Federated Training
- CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
- CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
- Crafter: Towards Automated Reproducible Machine Learning via Agentic Code Generation
- Crafting Reversible SFT Behaviors in Large Language Models
- CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
- Credit Assignment with Resets in Language Model Reasoning
- CREF: Forecasting Benchmarks for the Age of Agents
- CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
- CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation
- CRISP: Compositional Reasoning over Images via Stackable Programs for VLMs
- CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
- Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets
- CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
- Cross-Architecture Transferability is Width-Confounded:Diagnosis and Subspace Correction
- Cross-Attentive Bayesian Low-Rank Adaptation for Multimodal Uncertainty Estimation
- Cross-Cell-Line Perturbation Prediction Needs Controls
- Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning
- Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions
- Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
- Cross-Distribution Generalization in Longitudinal Behavioral Data Through Frozen Coherence Constraints
- Cross-Domain Knowledge Separation and Positive Transmission for Noisy Domain Incremental Learning
- Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
- Cross-Fitting for Neural Posterior Estimation
- Cross Flow: One-Step Generation Across Latent and Pixel Spaces
- Cross-Foundation Complementary Learning Systems for Continual Test-Time Adaptation in Open-Vocabulary Semantic Segmentation
- CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation
- Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly well
- Cross-Layer Evolution Graph Learning for Fine-grained VLM Hallucination Detection
- Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration
- Cross-Model Circuit Discovery
- Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
- Cross-Model Transfer Attacks against Large Vision-Language Models via Model Diversity Enrichment and Stochastic Parameter Sampling
- Cross-order Consensus Graph Matching
- Cross-Question Reliable Reinforcement Learning
- CrossSteer:Cross-Modal Safety Steering for Audio-Language Models
- Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
- CrossWeave: Emergent Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment
- Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
- CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
- CruxBench: A Benchmark of Information Discovery
- CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building
- CryoGeo: Latent Pose Equivariance for Amortized Ab Initio Cryo-EM Reconstruction
- CryptanalysisBench: Can LLMs do cryptanalysis?
- CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
- CSBench: A Comprehensive Benchmark for Evaluating Project-Level System Construction in Computer Science
- CSCN: The Crossed Subtree Convolutional Network
- CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
- CS-DICE: Offline Reinforcement Learning with Coherent Occupancy Regularization
- CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
- CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
- CSLA: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training
- CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
- CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization
- CTE-Bench: Audited Counterfactual Trace Evaluation for Stateful Software Simulators
- CT-Lesion: A Multi-Region CT Dataset for Co-existing Lesion Segmentation and Detection
- CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
- CTRL: Continual Test-Time Reinforcement Learning for Large Language Models
- CuBic: Curvature-Driven Dynamic Inference Caching for Fast, High-Fidelity Flow Matching
- CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
- CUDABench: Benchmarking LLMs for Text-to-CUDA Generation
- CultureRed: Benchmarking Culture-Specific AI Safety Based on Global Statutes
- CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate Assembly
- CURe: Conservative Unlearning with Soft-Gating Regularization for Offline Reinforcement Learning
- CURE: Counterfactual Unsafe-token Re-masking for Diffusion Large Language Model Test-time Alignment
- CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users
- CURE: Visual Reprogramming of Vision-Language Models under Limited Supervision
- Curriculum Learning for Safety Alignment
- Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations
- Curriculum proof repair with learned counterexamples
- Curvature Beyond Positivity: Greedy Guarantees for Arbitrary Submodular Functions
- Curvature-Dependent Lower Bounds for Frank-Wolfe
- Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization
- Curvature-Guided Parameter Initialization for Multi-Task Learning
- CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
- CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
- CutAttn: Discovering Cognitive Transition Layers for Efficient Long-Context Prefilling
- CUVET: A Partitioning Approach for Continuous Treatment Assignment At Scale
- CVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction
- CWAGraph: Retrieving What Was Never Explicitly Identified in Graph-Based RAG
- CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language Models
- CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
- CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation
- CycleSpectra: Cyclic Motion Spectra for Phase-Queryable 4D Cardiac Reconstruction
- Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
- Cyclic Discrete Diffusion: A Novel Multi-Class Segmentation Refinement Technique
- Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
- CytoWave: Perturbation-Centric Pretraining for Single-Cell Response Prediction
- D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
- D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation
- DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
- DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment
- DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks
- DACE RL for Compute Efficient Reinforcement Learning in Small Model Reasoning
- DAGA: Dynamic Attention-Guided Adaptation for Self-Supervised Vision Transformers
- DAG-Biased Graph Learning for Multimodal Survival on EHR
- DAGent: Evaluate-then-Grow Planning for Deep Research Agents
- Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints
- Dandelions: A Spherical Flower for Neural Simulation of Planetary Dynamics
- DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving
- DARE: Dual-Level Adversarial Learning with Domain-Aware Regularization for Whole Slide Image Classification
- DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax
- DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees
- DARPAN: Controllability-Aware Residual Filtering for Pretrained Physical Control
- DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection
- DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
- DART: Zero-Shot Dual-Side Alignment Routing for LLM Performance-Cost Tradeoffs
- Darwin-7B: A Multi-Omic Foundation Model for the Human Gut Microbiome via Sparsified Quality-Aware Tokenization
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
- DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy Alignment
- DASS: A Solver-Agnostic Dynamic Auxiliary Search Strategy for Symbolic Regression
- Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers
- Data Auctions for Retrieval Augmented Generation
- DataComp-VLM: Improved open datasets for Vision-Language Models
- Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
- Data Density Scaling Laws for Image Self-Distillation
- Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
- Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation
- Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution
- Data-Efficient Learning for Constraint Satisfaction Problems via Relational Biases and Hard Axiom Clamping
- DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
- Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations
- Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
- Dataset Collections: Challenges of Large-Scale Data Aggregation in 3D Medical Image Datasets
- Dataset Distillation via Drifting
- Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards
- DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
- DBPS: Doob-Bridge Posterior Sampler with Balanced Endpoint-Population Control for Unpaired Neurodegenerative Pathology Transport
- DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
- DC-Ocean: Deep Latent Compression for Global High-Resolution Ocean Forecasting
- DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
- DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
- DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images
- DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks
- DDBench: A Benchmark for Agentic Debugging on Distributed Systems
- DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging
- DDGE: Disentangled Dirichlet Geodesic Evaluation for Robust Few-Shot Learning
- DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models
- D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
- DD-Ranking: Rethinking the Evaluation of Dataset Distillation
- DDx-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
- Deadline-Constrained Dynamic Workflow Scheduling Can be Cast as a Representation Learning Problem
- DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents
- Debiased Counterfactual Generation via Flow Matching from Observations
- Debiased DPO for Diffusion Models
- Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions
- Debiasing Sketched Ridge Regression: A Functional Estimation Perspective
- DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
- Decentralized $\mu^2$-SGD: Narrowing the Parallelism Gap to Centralized Learning
- Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
- Decentralized AI Governance Must Decouple Policy Processing from Capability Enforcement
- Decentralized Coupled Representation Learning
- Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction
- Decentralized Q-Learning in Markov Potential Games
- Decentralized Ranking Aggregation via Gossip: Convergence and Robustness
- Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
- Decide Before You Record: Heterogeneity-Guided Pre-Acquisition Stimulus Selection for Cross-Day Neuroprostheses
- Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
- Decision-Focused Learning in MDPs: An Occupancy Measure Approach
- Decision Focused Scenario Learning for Contextual Stochastic Programming
- Decision Path Tracing for Causal Analysis in Transformers
- Decoding the Critique Mechanism in Large Reasoning Models
- DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
- Decomposed Graded Verifier for Generative World Modeling
- Decomposed Representations Mitigate the Alignment–Specificity Trade-off in Multi-Omics
- Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models
- Decomposing and Reshaping Scaling Laws through Token Learning Times
- Decomposing Conformal Uncertainty: Calibration- and Instance-Driven Feature Attribution
- Decomposing Earth Embeddings with Sparse Autoencoders
- Decomposing Effects in Neural Causal Models
- Decomposing how prompting steers behavior
- Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
- Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation
- Decomposing Temporal and Job-Induced Dynamics for Probabilistic Computing Workload Forecasting via Graph-Conditioned Dual-Branch Diffusion
- Decomposing the modulation of interactions between neuronal populations
- Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition
- DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
- Decoupled Complementary Fields on 3D Gaussian Maps for Embodied Navigation and Reasoning
- Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
- Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models
- Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student
- Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval
- Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
- Decoupling Action from Egocentric Observation for World Simulation
- Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning
- Decoupling Direction and Magnitude: Language-Steered Flow Matching for Super-Resolution in the Dark
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
- Decoupling is the Key: Scaling Deep Value Networks in Reinforcement Leanring
- Decoupling Label Shift and Surrogate Gradient Errors for Robust Federated Spiking Neural Networks
- Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting
- DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
- DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
- DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
- Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality
- Deep Double Q-learning
- Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective
- DeepfakeGenome: Toward Next-Generation Deepfake Attribution
- Deep Gaussian Processes on Directed Acyclic Graphs
- Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
- Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
- Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows
- Deep Minds and Shallow Probes
- Deep Probabilistic Supervision for Image Classification
- Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
- Deep Research as Rubric
- DeepVoting: Learning and Improving Voting Rules with Fine-Tuning
- DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs
- Default Feature Representations of the Cognitive Map
- Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
- Deferred Aggregation in Hierarchical Bayesian Optimization
- Defining Operational Conditions for Safety-Critical AI-Based Systems from Data
- DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models
- DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
- Deformable 2D Gaussian Splatting
- DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
- DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
- DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
- DegBins: Degradation-Driven Binning for Depth Super-Resolution
- DeGlare: Self-Supervised Specular Removal for Industrial Metallic Surfaces via Multi-Illumination Priors
- DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction
- Déjà View: Looping Transformers for Multi-View 3D Reconstruction
- Delayed homomorphic reinforcement learning for environments with delayed feedback
- Delay-Embedded Representations for Robust Saccade Classification in Noisy Oculographic Signals
- Delightful Distributed Policy Gradient
- Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
- DeltaFugue: Orchestrating Spatial and Associative Memory for Algorithmic Length Generalization
- DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule
- DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
- DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations
- DELTA-TTS: Adapting Autoregressive Model into a Diffusion Language Model for Text-to-Speech
- DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
- Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
- Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
- Demographic parity in regression and classification within the unawareness framework
- Demystifying Classifier-Free Guidance for Auto-Regressive Image Generation
- Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
- Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
- Denoising Distances in Metric Measure Spaces
- Denoising Implicit Variational Inference
- Denoising-Time Heterogeneity in VLA Action Generation: A Controlled Study via Step-Wise Expert
- Denoising Time Matters: Diverse Generation in Diffusion Language Models
- Dense Cross-Tokenizer Distillation via Semantic Optimal Local Alignment
- Dense Flow from Adaptive Correspondence
- Dense Structural Compression of Transformers via Gauge-Correct Channel Removal
- Density-Ratio Losses for Post-Hoc Learning to Defer
- Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
- Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
- Deployment-Time Online Imitation Learning from Corrective Demonstrations
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth
- Depth Exploration for LLM Decoding
- DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
- Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
- Depth through Recurrence: Towards Ultra-Efficient On-Device ASR
- Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency
- Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators
- Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
- Designing Cell-Type-Specific Regulatory DNA with Guided Discrete Diffusion
- Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL
- Designing Kernel Surrogate Models for Multimodal Attribution
- Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
- Despa: Resolving Spatial Collapse in VLMs via Depth-Grounded Geometry
- DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
- Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection
- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability.
- Detecting Hidden ML Training With Zero-Overhead Telemetry
- Detecting RLVR Training Data via Structural Convergence of Reasoning
- Detection and Classification in Latent Spaces: High-Dimensional Analysis and Validation
- DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention Discrepancy
- Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding
- DETS: An Interval-Censored Evidential Sampling Framework for Cross-Domain Scientific Discovery
- DevAI: Developmental Perspectives on AI
- Developmental Visual Experience Scaffolds Grounded Concept Acquisition in Vision-Language Models
- DexMirror: Real-to-Sim Scene Mirroring for Sim-to-Real Dexterous Manipulation
- DexOPE: 6D Object Pose Estimation in Dexterous Manipulation
- Dexterous Skill Discovery via Topology-Aware Wasserstein Dependency
- D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
- DGRAF: Observation-Quality-Aware Reinforcement Learning for Dynamic Reconfigurable Batteries
- DiA: Directional Adapter
- DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
- DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling
- Diagnosing and Correcting Bias in MLLM for Long Video Understanding
- Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
- Diagnosing and Repairing Citation Failures in Generative Engine Optimization
- Diagnosing and Repairing Visual Collapse in Compact Medical Multimodal LLMs
- Diagnosing Math-Reasoning Failure Structure with Milestone Oracles
- DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules
- Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
- DiagSQL: A Diagnostic Validator for Text-to-SQL with Reward Allocation and Co-occurrence Shaping
- DIAL: A Bounded-Monotone Adapter with Closed-Form Residual $L_\infty$ Bounds for Scalar-Controlled Refusal Modulation
- DialBandit: Adaptive Sequential Search with Tunable Evaluation Fidelity
- Dialect ASR based on Multi-View Pseudo-Parallel Augmentation and Noise-Robust Contrastive Learning
- Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
- DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
- DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections
- DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
- DICEQuant: Distortion-Compensated Rounding with Dual-Ended Shrinkage for LLM Quantization
- DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels
- DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization
- Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty Aware Differentiable Optimization
- Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
- DiffATS: Diffusion in Aligned Tensor Space
- DiffCap-RL: Differential QA Rewards for Dense Image and Video Captioning
- Diff-CA: Separating Common and Salient Factors with Diffusion Models
- DiffCool: Label-Free Synthesis of Chip-Tailored Heat Sinks via Thermal-Aware Diffusion
- Diffeomoprhism-Informed 3D Gaussian Splattings via Screen-Space Optimal Transport (OT)
- DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations
- Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization
- Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
- Differentiable Belief-based Opponent Shaping
- Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression
- Differentiable Cluster Discovery in Temporal Graphs
- Differentiable Exact Learning of Algorithms
- Differentiable Knapsack and Top-k Operators via Dynamic Programming
- Differentiable Learning of Lifted Action Schemas for Classical Planning
- Differentiable Nonlinear Model Predictive Control
- Differentiable Range-Partition Entropy for Entropy-Sensitive Geometric Algorithms
- Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
- Differentiable Systematic Resampling for Variational Sequential Monte Carlo
- Differential Item Functioning as an Item-Level Diagnostic for LLM Benchmarks
- Differentially Private Model Merging
- Differentially Private Sparse Reward Estimation with Preference Feedback
- Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
- Differentiating Network Design Objectives for Balancing Cost and Distance
- Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
- Diff-Kalman: Difference-Driven Learning for Structure-Preserving Kalman Filtering
- DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
- DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
- DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
- DiffRisk: Diffusion Representation Learning with Informative Missingness for Health Risk Prediction
- DiffScore: Text Evaluation Beyond Autoregressive Likelihood
- Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
- Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems
- Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models
- Diffusion fine-tuning with Rewarded Moment Matching Distillation
- Diffusion Guidance Is a Controllable Policy Improvement Operator
- Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
- Diffusion Language Models: Foundations, Efficiency, and Reasoning
- Diffusion LLMs are Natural Adversaries for any LLM
- Diffusion Masked Pretraining for Dynamic Point Cloud
- Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
- Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Diffusion Models without Classifier-free Guidance
- Diffusion Path Samplers via Sequential Monte Carlo
- Diffusion-State Policy Optimization for Masked Diffusion Language Models
- Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
- Diffusion Thinking for Fast Long-Form Spatial Reasoning in Vision--Language Models
- Diffusion-Time Concept Manifolds: Sparse Autoencoder Groups for Interpreting Denoising Language Models
- Diffusion Transformers with Residual Adaptive Layer Normalization
- Diffusion Tree Search for Inference Time Adaptation of Material Foundation Models
- Diffusion-warm sampling of the XY model enables fast thermalization at scale
- DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation
- DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling
- DiM$^3$: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
- Dimension Bounds for Contractive Reservoir Computing from Input Entropy
- Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
- DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
- DINOv3
- DiPhon: Diffusion on Graphons for Scalable Graph Generation
- DiPMInd: Distance profile based mutual independence testing for random objects
- DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
- DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning
- Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
- Direct Conditional Parameterization for N-Dimensional Splatting
- Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction
- Direct Estimation of Schrödinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees
- Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision
- Directional Noise Conditioning for Diffusion Models
- Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits
- Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
- DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
- DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding
- Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting
- DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
- Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
- DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
- DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
- DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance
- Discovering dynamical parameters of synthetic multicellular systems from image sequences
- Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
- Discovering Phase Space Structure in Learned Hamiltonian Systems
- Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers
- Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models
- Discovering Symbolic Differential Equations with Symmetry Invariants
- Discovering Unseen Degradations to Adapt Open-World Image Restoration
- Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
- DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO
- DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking
- Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
- Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models
- Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
- Discrete Langevin-Inspired Posterior Sampling
- Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling
- Discrete Stochastic Localization for Non-autoregressive Generation
- Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
- Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
- Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
- Disentangled Multimodal Learning for Scalable Dynamic IR-Drop Analysis
- Disentangled Representation Learning via Flow Matching
- Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
- Disentanglement as Identifiable Pushforward Factorisation
- Disentangling Channel Semantics in Vision Transformers via Token Decorrelation and Composition-Aware Modulation
- Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
- Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
- Disentangling generalization and memorization in large language models using chess
- Disentangling Homophilic and Heterophilic Patterns for Multi-Domain Graph Foundation Models
- Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental Learning
- Disentangling the Good From the Bad: Quantization-Induced Flips Are Not Random
- Disentangling Where and When: Factored Spatio-Temporal Explanations for Video Action Recognition
- Dispatchable Coordination Envelopes for Embodied Collaboration Under Sequential Uncertainty
- Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
- DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
- DisSparse: Pipelined Top-$p$ Sparse Attention for Long-Context LLM Serving
- Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics
- Distance Marching for Generative Modeling
- DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
- Distillation of Foundation Models for Time-dependent PDEs
- Distilling Conditional Image Generators into Spatial Effect Maps
- Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
- Distilling LLM Feedback for Lean Theorem Proving
- Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection
- Distilling Reasoning: From Chain-of-Thought to Agentic Capabilities in Smaller Models
- Distilling Sequential Computation in Transformer Language Models
- Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models
- Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
- Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning
- DISTMOE: Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
- Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications
- Distributed-Order Fractional Spiking Neural Network
- Distribution-Adaptive Policy Optimization
- Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
- Distributional Estimation of 3D Object Orientation
- Distributionally Robust Algorithmic Recourse for Tree Ensembles
- Distributionally Robust Black Box Optimization-based Bidding Strategy in Auction-based Federated Learning
- Distributionally Robust Domain Randomization with Learned Risk-Sensitive Dynamics Samplers
- Distributionally Robust Listwise Preference Optimization
- Distributionally Robust Mixture-of-Experts Training
- Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
- Distributionally-Robust Policy Learning from Observational Data
- Distributionally Robust Token Optimization in RLHF
- Distribution Corrected Decision Transformer for Offline Reinforcement Learning with Imbalanced Datasets
- Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules
- Distribution Free Fourier Sparsity Testing
- Distribution Matching Distillation without Fake Score Network
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR
- DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
- DiversePlace: Diversity-Seeking Curriculum Reinforcement Learning for Macro Placement
- Diverse Representative Rashomon Sets for Sparse Generalized Additive Models
- Diversity Combining for Multi-Path LLM Reasoning
- Diversity Curves for Graph Representation Learning
- Diversity Maximization: Algorithms for Distant $k$-Subsets
- Divide et Calibra: Multiclass Local Calibration via Vector Quantization
- Diving-R1: Empowering Multimodal LLMs with Traceable Progressive Reasoning for Interpretable Diving Action Quality Assessment
- DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
- DMax: Aggressive Parallel Decoding for dLLMs
- dMoE: dLLMs with Learnable Block Experts
- DN-Flow: Driver–Navigator Structured Flow Matching for Mixed-Type Tabular Data Generation
- DnNP: Denoising Input Uncertainty in Neural Processes
- DNS-Calibrated Local Stochastic Transition Closure for PDE-Free Long-Horizon Turbulence Diffusion
- DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
- DocAtlas: Long-Document Understanding as Mutable-State Interaction
- Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
- Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
- DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
- DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
- Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
- Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation
- Do Diffusion Models Learn to Generalize Basic Visual Skills?
- Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?
- Does Compression Imply Generalization? A Minimum Description Length Perspective
- Does Cross-Panel Pretraining Transfer Under Marker Heterogeneity? A Large-Scale Empirical Study in Clinical Flow Cytometry
- Does Inference-Time Reasoning Really Improve Video Understanding?
- Does Mixed Label Imbalance Matter to Minority Collapse in Imbalanced Learning?
- Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
- Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
- Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
- Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
- Does This Gradient Spark Joy?
- Does Weight Decay Enhance Training Stability?
- Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
- Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
- DoFP-Aligned Lookup Tables for Real-Time Polarization Demosaicking
- Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision
- Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs?
- DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring
- Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training
- Do Image Editing Models Understand Lighting?
- Do Joint Audio-Video Generation Models Understand Physics?
- Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
- Do Less, Decide Better: Optimal Human Dispatching in AI-Assisted Decisions
- Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues
- Do LLMs Feel Social Pressure? Locating and Steering Social Desirability Bias in LLMs
- Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains
- DOME: Drift-Adaptive On-Policy Motion Erasure in Video Diffusion Transformers
- Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
- Domination-Avoiding Learning Agents Cannot Collude
- Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness
- Do multimodal models imagine electric sheep?
- Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
- Do Not Let Spikes Flip: Margin-Resculpted Learning for Robust Spiking Neural Networks
- Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
- Don't Deploy Fine-Tuned Genomic Foundation Models Without Privacy Evaluation: Reconstruction Vulnerability Is Unpredictable Without Empirical Measurement
- Don't Discard Your Rollouts: Reusing Teacher RL Traces for Student Distillation
- Don’t Learn What You Can Compute: Arithmetic Residual Blocks for Exact Arithmetic in Transformers
- Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL
- Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
- Don't Match the Noise: Distribution Matching under Unknown Measurement Error with an Audit Sample
- Don't Pause! Every prediction matters in a streaming video
- Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
- Don't Waste Population: Post-Anneal Refinement for Combinatorial Optimization
- Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
- Doomed to Re-Annotate, Forever: The ImageNet Story
- Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
- DopplerWild: A Doppler Dataset and Benchmark for Human Kinematic Understanding in the Wild
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
- Do Reasoning LLMs Refuse What They Infer in Long Contexts?
- Do Robust LVLMs Hallucinate More? Uncovering Robustness-Induced Hallucination in Large Vision-Language Models
- Do Semantic Distance Tests Actually Predict Creativity in Large Language Models?
- Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
- Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling
- Do Thinking Tokens Help with Safety?
- Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
- Do We Really Need Diffusion for Generative Object Detection? A Minimal Prototype Perspective
- Do You CARE to Generalize? Extracting Robust Concept Directions from LLMs
- D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
- DPA: Decentralized Primal Averaging with Quasi-Global Momentum for Highly Heterogeneous Data
- DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private Optimization
- DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation
- DPLC: Dirichlet Process Guided Long-tail Clustering
- DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
- DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
- dRAE: Representation Autoencoder with Hyper-Spherical Codes
- Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
- DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
- DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models
- DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model
- Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images
- Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts
- Drift Flow Matching
- Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL
- Drifting Fields are not Conservative
- Drift Q-Learning
- Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
- Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
- DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation
- DRILL: Training World Models to Improve Policies, Not Predict Pixels
- DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
- DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization
- DriveFuture: Future-Aware Latent World Models for Autonomous Driving
- DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution
- DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
- Driver Attention as Competitive Allocation: A Scene--Task-Aware Dual-Branch Framework
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
- DriveStreamBench: Evaluating User-Conditioned Watch-and-Notify in Streaming Driving Video
- Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
- DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
- Driving on Memory
- Driving Video Retrieval for Complex Queries with Structured Grounding
- Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
- DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning
- DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
- DrPO: Drifting Preference Optimization for One-Step Generative Models
- DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
- DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
- DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
- DSAD: Dynamic Soft Anisotropic Diagrams for Reduced-Order Video Representation
- DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
- DSBTR: A Diffusion Schrödinger Bridge Trajectory Refiner for Multi-Agent Trajectory Prediction
- DSR-TSF: Spectrum-Driven Dynamic Routing for Efficient Long-Horizon Time Series Forecasting
- DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models
- DSSNet: Deep Spectral Structure Profiling Network for Traffic Flow Prediction
- DSSP: Diffusion State Space Policy with Hierarchical Full-History Conditioning
- dStructAD: Domain-Level Structured Normality Representation with Variation Calibration for Time Series Anomaly Detection
- DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
- DTGS: Physics-Embedded Dynamic Thermal 3D Reconstruction with Gaussian Splatting
- DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
- Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation
- Dual Dimensionality for Local and Global Attention
- DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling
- Dual Feature-Relational Alignment for Transferable Targeted Attacks on MLLMs
- Dual-Granularity Learning for Regression with Continuous Noisy Labels
- Duality Models: An Embarrassingly Simple One-step Generation Paradigm
- DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
- Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
- Dual-Pronged LoRA: Achieving Near-Zero Forgetting and High-Performance Adaptation for MLLMs
- Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
- DualSAT: A Dual-Branch GNN-Transformer Framework for SAT Solving
- Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems
- DualSteer: Dual-Space Steering for Robust Jailbreak Mitigation of Large Vision Language Models
- DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
- DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable Rewards
- DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
- DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
- DUIL: Deep Unsupervised Inverse Learning for in situ Macromolecular Morphology Identification
- DUST: Directional Uncertainty-aware and Scale-invariant Transfer Learning
- D-VLA: A High-Concurrency Distributed Asynchronous RL Framework for Vision-Language-Action Models
- DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation
- DyJR: Preserving Local Policy Plasticity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay
- DynaCell: an Evaluation Framework for Dynamic 3D Virtual Staining of Live Cells
- DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
- DynamAuction: a reinforcement learning environment for repeated auction with dynamic value
- Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
- Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
- Dynamic Causal Structure Discovery for Autoregressive Visual Generation
- Dynamic Context Modeling for Longitudinal Mental Health Monitoring under Distribution Shift
- Dynamic Convolutions Improve Transformers
- Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
- Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding
- Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting
- Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
- Dynamic k-center clustering with lifetimes
- Dynamic Latent Routing
- Dynamic Model Merging Made Slim
- Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
- Dynamic Physical Adversarial LED Patterns via Reinforcement Learning
- Dynamic Quadtree Tokenization for Autoregressive PDE Forecasting
- Dynamic Query as Budgeting for Tiny Object Detection
- DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
- Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
- Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics
- Dynamic Representation Modeling for Federated Medical Image Domain Generalization
- Dynamic Resolution Routing for Efficient Egocentric Grounding
- Dynamics at the Frontiers of Optimization, Sampling, and Games
- Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion
- Dynamics-Informed Adaptive Offline RL for Real-Time Tokamak Plasma Control
- Dynamics of Collective Diversity in Human–AI Co-Creation for Creative Tasks
- Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
- Dynamic Spectral Federated Graph-Level Clustering
- Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
- Dynamic Treatment on Networks
- Dynamic Video Generation: Shaping Video Generation Across Time and Space
- DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
- DynaPFN: Zero-Shot Dynamical System Forecasting with Tabular Prior-Fitted Networks
- DynaProto: Dynamic Prototypical Contrast for Temporally Consistent Object-Centric Learning
- Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
- DynaSub: Adaptive Subgrouping for Scalable Representation Learning
- DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time
- DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
- Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model
- DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models
- DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation
- DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs
- DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
- E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion
- E²Gen: Evidential Energy-Based Generation for Fair Federated Graph Learning
- E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
- Early Detection of Backbone Divergence via Neighborhood Structure in Learned Embeddings
- Early Failure Detection and Intervention in Video Diffusion Models
- Early Prediction of Future Behavioral Strategy from Process Traces
- Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
- Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
- EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
- EAT: Eviction-Aware Training for Long-Context LLM Inference on Edge Devices
- EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
- ECG Dataset with Multi-Expert Annotations and Delineations
- ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
- ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
- ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
- Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommender Systems
- Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting
- EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
- Echo learning enables biologically plausible temporal credit assignment
- EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
- Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding
- ECHO: Terminal Agents Learn World Models for Free
- EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
- ECLIPSE: A Spacecraft Rendezvous Trajectories Dataset with Controlled In-Orbit Lighting Conditions
- EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
- EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
- EconML: Economics for Machine Learning
- Economics of Generative AI
- Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
- EDEN: Emergent Dynamics in Evolutionary Neural-networks for Robust Continuous Control
- Edge of Stability Selectively Shapes Learning Across the Data Distribution
- Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
- EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization
- EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
- EditDistill: Is It Possible to Guide Video Editing with Image Editing
- EditFlowSR: Revisable Expression Generation for Symbolic Regression
- Editing Large Language Models with Geometry-Aware Regularization
- EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
- EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation
- Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
- Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
- EDMA: Entropy-Driven Multimodal Answering
- EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction
- EEGFaceSem: An EEG Benchmark with Paired Generative Latents for Semantic Visual Modeling
- EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG
- EENAS: Zero-Shot Energy-Efficiency-Aware Neural Architecture Search
- Effect-Driven Skill Abstractions for Offline Reinforcement Learning
- Effective Biological Representation Learning by Masking Gene Expression
- Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
- Effective Knowledge Conflict Detection via Joint Agentic Optimization
- Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
- Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
- Effect-Level Validation for Causal Discovery in Interactive Telemetry
- Efficient, Accurate and Stable Gradients for Neural ODEs
- Efficient Adaptive Data Acquisition via Pretrained Belief Representations
- Efficient Adaptive Data Analysis over Dense Data Distributions
- Efficient Adjoint Matching for Fine-tuning Diffusion Models
- Efficient Agentic GPU Kernel Optimization with a Compact Domain-Specific Language and Speed-of-Light Guidance
- Efficient Algorithms for Distributed Saddle Problems
- Efficient Algorithms For Fully Dynamic Bipartite Matching In Metric Spaces
- Efficient algorithms for linear regression with heteroskedastic errors
- Efficient Analytic Uncertainty Quantification for Multimodal Regression
- Efficient and Accurate Zero Shot Generation of Symmetric Protein Complexes
- Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
- Efficient and Simple Data Mixing All The Time
- Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
- Efficient Benchmarking Is Just Feature Selection and Multiple Regression
- Efficient bias mitigation in T2I diffusion models using Concept Graphs
- Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks
- Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network Tuning
- Efficient Computation and Best-Response Dynamics in Anonymous Two-Action Games with Linear Utilities
- Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
- Efficient Decoder Scaling Strategy for Constructive Neural Routing Solvers
- Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging
- Efficient Dynamic Algorithms for Graph Neural Networks with Non-Linearity
- Efficient evaluation and error pattern discovery for blackbox AI systems
- Efficient Evaluation of LLM Performance with Statistical Guarantees
- Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning
- Efficient Forecasting of Task Failures in LLM Agents through Adaptive Fault Injection
- Efficient Generative Transformer Operators for Million-Point PDEs
- Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training
- Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion
- Efficient Image Synthesis with Sphere Latent Encoder
- Efficient Knowledge Transfer in Federated Bayesian Optimization through Neural Network Surrogates
- Efficient Label Distribution Inference Attack and Defense on Classifier Weights in Federated Learning
- Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue
- Efficient LLM Adaptation with Forward-Only Passes
- Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning
- Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
- Efficiently Representing Algorithms With Chain-of-Thought Transformers
- Efficient Matrix Product State Learning in Logarithmic Depth
- Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
- Efficient Multi-Source Prompt Adaptation for Cross-Domain Open-Vocabulary Learning
- Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
- Efficient Off-Policy RL for Video Generation via Forward-Consistent Reward Matching
- Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
- Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
- Efficient Prediction of Pass@k Scaling in Large Language Models
- Efficient Pre-Training with Token Superposition
- Efficient Reasoning via Constrained Optimization in Latent Space
- Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion
- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
- Efficient SAM 3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive Representations
- Efficient Scaling of LLM Training with Flexible Context Parallelism
- Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
- Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
- Efficient Test-Time Adaptation For Robot Policies
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
- Efficient Training of Deep Spiking Neural Networks with Input-Driven Derivative-Free Updates
- Efficient Transferable Optimal Transport via Min-Sliced Transport Plans
- Efficient Tree Draft for Long-Context Speculative Decoding
- Efficient Variational Inference for Log-Gaussian Cox Processes via Voronoi Tessellation
- EGCA: A Spectral Perspective on Forward Process Design in Diffusion Models
- E-GEO: A Testbed for Generative Engine Optimization in E-Commerce
- EgoBabyVLM: Benchmarking cross-modal learning from naturalistic egocentric video data
- EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
- EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing
- Ego-HMB: Human Motion Bridging from Egocentric Images via Motion Bridge Diffusion Model
- EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues
- EgoMo3R: Joint Egocentric Motion and Scene Reconstruction
- EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
- EgoSurgHands: An Egocentric 3D Hand Pose Dataset & Benchmark for Open-Surgery Training
- EgoTac: In-the-wild Tactile Prediction from Egocentric Vision
- EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
- EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery
- EIPO: Efficient Inter-Step Parallel Optimization
- ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation
- Elastic Representations via Hyperbolic Geometry
- Elastic Spectral State Space Models for Train-Once Budgeted Inference
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
- Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding
- ELF: Embedded Language Flows
- Elicited Adaptation: Auditable Localized Fairness via Pairwise Queries
- Eliciting Secret Knowledge from Language Models
- Eliciting Zero-Shot Named Entity Recognition in Large Language Models via Instruction Semantic Elaboration
- ELLIS Workshop on the Foundations of LLM Post-Training in Changing Environments
- ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation
- ELPAC: Endpoint-Anchored Latent Progression with Stage-Varying Multimodal Coordination
- ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
- EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization
- Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers
- Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
- Embedding Security Properties into AI-Enabled Cyber-Physical Systems
- Embeddings for Preferences, Not Semantics
- Embodied AI Cannot Scale Without Open-Source Distributed Geometric Optimization Backends for Life-Scale Egocentric Data
- Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation
- EmbodiedObject: All-in-One Object Understanding with SLAT
- Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
- Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot
- EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge
- Emergence of a Shared Canonical Object Frame from In-the-Wild Videos
- Emergence of Distortions in High-Dimensional Guided Diffusion Models
- Emergence of Physical Intelligence via Controllable Information Production
- Emergence, Retention and Mitigation of Ill-conditioning due to Basis Lifting in KANs
- Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
- Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
- Emergent Misalignment as Data-Mediated Transfer
- Emergent representations of graphical structure in mechanistic neural models of causal judgment
- Emergent Semantic Role Understanding in Language Models
- Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models
- Emergent Visual Thinking in Text-Only Reasoning through Multimodal Training
- EM-NeSy: Expectation Maximization for Neurosymbolic Learning
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- EMO: Pretraining Mixture of Experts for Emergent Modularity
- Emotion-Trained Vision Models Do Not Necessarily Learn EEG-Aligned Facial Dynamics
- EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes
- EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue
- Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity
- Empirical Bayes Rebiasing
- Empirical Design in Reinforcement Learning for Physical AI
- Empirical regularities in subjective decision-making by LLMs
- Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers
- Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
- Enabling approximate joint sampling in diffusion LMs
- Enabling Denoising Score Matching Type Training for Manifold Diffusion Model via Momentum and Splitting
- Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
- Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
- ENACT: Single-Image Human-Scene Interaction Motion from Language via Foundation-Model Orchestration
- Encoding RNA Topology into Synthetic Alignments for 3D Structure Prediction
- EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
- Endowing Your Vision-Language-Action Model with a Predictive Mind
- End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization
- End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
- End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives
- End-to-End Training for Unified Tokenization and Latent Denoising
- End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
- EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference
- Energy-Adaptive Equivariant State Space Models for Noise-Robust Protein Structure Representation
- Energy-Based Operator Learning in Function Space
- Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
- Energy Is All We Need: Beyond FLOPs in Model-Heterogeneous Federated Learning
- Energy-Tweedie: Score meets Score, Energy meets Energy
- ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
- EngramState: Loadable Tool Priors for Efficient Function Calling
- Enhanced convergence guarantees of score-based generative models in $\mathcal{W}_2$-distance beyond log-concavity
- Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
- Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
- Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior
- Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
- Enhancing Speech Large Language Models through Reinforced Behavior Alignment
- Enhancing Tabular Learners with Context-Aware Semantic Embeddings
- Ensembits: an alphabet of protein conformational ensembles
- Ensemble Distributionally Robust Bayesian Optimisation
- Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach
- Ensemble Selective Classification
- Ensembling Language Models with Sequential Monte Carlo
- Ensuring Deployment-Time Safety of Neural Network Controlled Systems via Localized Certificate Repair
- Entangled Schrödinger Bridge Matching
- EnterpriseBench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance
- EntiRE: Invariant Learning for Robust Concept Erasure in Text-to-Image Generative Models
- EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
- EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
- Entropy Distribution as a Fingerprint for Hallucinations in Generative Models
- Entropy Dynamics of Agent Reinforcement Learning
- Entropy-Gated Latent Recursion
- Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
- Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
- Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
- EnvFaultBench: Benchmarking LLM Agents on Software Environment-Fault Troubleshooting
- Environment-Robust Representation Learning with Empirical Bayes
- EnvTrap: Revealing the Environment-Only Attack Surface in Embodied AI via Consequence-Blind Action Execution
- EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
- EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation
- EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
- EpicWorldModel: Exploration-driven Planning with Latent World Models
- Epigenomics-Guided Flow Matching for 3D Genome Super-Resolution
- EpiPivot: Learning to Control the Simplex Method under Epistemic Uncertainty
- Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
- EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language Models
- Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification
- Epistemic Pairwise Maximin Share
- Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent Interaction
- EpiStream: Utility-Aware Temporal Abstraction for Dense-Action Streams
- Epitope-Conditioned Nanobody CDR Design via Retrieval-Augmented Protein Language Models
- Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning
- Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
- Equivariant Force Field Calibration for Flow-based Protein Design
- Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
- Equivariant Spherical Transformer for Efficient Molecular Modeling
- Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning
- Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
- ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
- ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room
- Error-Guided Bellman Calibration for Semi-Offline Value Estimation
- eSAM: Editing SAM3 Attention for Training-Free Referring Segmentation
- Escape the Context Manifold: Preventing DiT In-Context Editing via Conditional Flow Hijacking
- Escaping Parameter Space: Tight Generalization Bounds via Representation Quality
- Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
- Escaping Reasoning Basins: Basin-Aware Search for Inference-Time LLM Reasoning
- Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
- Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative Models
- ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP
- ES-Merging: Biological MLLM Merging via Embedding Space Signals
- EsoLang-Bench: Evaluating Large Language Models via Esoteric Programming Languages
- ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning
- ESS-Flow: training-free guidance as Bayesian inference in source space
- Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
- Estimating Continuous Treatment Effects with Recourse Data
- Estimating Implicit Regularization in Deep Learning
- Estimating Model-Level Membership Inference Vulnerability Without Reference Models
- Estimating the expected output of wide random MLPs more efficiently than sampling
- Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
- Euclidean Embedding of Data Using Local Distances
- Euclidean Score-Based Generative Modeling with Permutation Semantics
- Euler-Mamba: Learning Resolution-Invariant State Evolution on Polar Manifolds for Asymmetric Pansharpening
- EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
- EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment
- EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning
- EvalAwareBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
- Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
- Evaluating and Understanding Scheming Propensity in LLM Agents
- Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning Diagnostics
- Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage
- Evaluating Deployable Inference-Time Error Prediction in Vision MoEs
- Evaluating Depth and Breadth in Test-Time Scaling for Compositional Visual Generation
- Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
- Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
- Evaluating Neural Data Tokenizers: A Framework for Assessing Learned Representations of Spiking Activity
- Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
- Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
- Evaluating Synthetic ECG Pretraining: When Can Patient-Free Simulators Substitute for Real ECG Data?
- Evaluating Test-Time Scaling of General LLM Agents
- Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
- Evaluating Whether LLMs Can Reliably Connect the DOTs?
- Evaluation Awareness in Language Models Has Limited Effect on Behaviour
- EVALUATION CARDS: An Interpretive Layer for AI Evaluation Reporting
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
- E-Values: From Statistics to ML
- EV-AUDIT: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems
- Even More Guarantees for Variational Inference in the Presence of Symmetries
- Even Sailors Need Calm Seas: Taming the Geometry of VLMs for Fast Adversarial Fine-Tuning
- Even Sharper Bounds for Transductive Learning and Its Applications
- Event based Multi-Velocity-Scale Imaging
- Event-Centric Perception in Weak-Signal Physical Streams with Multimodal LLMs
- Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
- EventLens: Event-Structure Reinforcement Learning for Video Understanding
- EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
- EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
- Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
- Every Measurement, Every Direction, All at Once: Multimodal Flow Matching for Molecules and Spectra
- Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints
- Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
- EviAttr-OW: Evidential Attribute Reasoning for Open World Object Detection
- Evidence Guided Dual Expert Memory with Joint Routing for VLLMs Online Correction
- Evidence-RL: Towards Evidence-intensive Visual Reasoning
- Evidential Semantic Uncertainty Decomposition for Large Language Models
- EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
- EviSAM3: Evidence-Driven SAM3 for Referring Remote Sensing Image Segmentation
- EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
- EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
- EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
- Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
- EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
- EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
- EvoInspect: A Unified Self-Evolving Multi-Agent Framework for Industrial Hardware Inspection
- Evolutionary Feature Engineering for Structured Data
- Evolutionary foraging in grids: Intermittent search emerges as an optimal strategy
- Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
- Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
- Evolving Agent Teams
- EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
- EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
- EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
- Exact Channel Decoupling via Joint Diagonalization and Uniform Splicing for Diffusion Transformer Quantization
- Exact Combinatorial Optimization for Partial Permutation Synchronization
- Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
- Exact-Form Regret and Conservative Correlated Equilibria
- Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
- Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement
- Exactness Matters for Physical Rule Enforcement
- Exact Posterior Score Estimation for Solving Linear Inverse Problems
- Exact power indices for plurality-voting ensembles
- Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
- Exact Regular-Constrained Sampling for Variable-Order Markov Generation
- Exact Topological Compliance: Generating Persistence-Equivalent Graphs
- Exact Unlearning via Quantized Sufficient Statistics
- Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models
- ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
- Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding
- Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting
- ExoC2T: An exogenous-driven spatio-temporal learning framework for cross-city transfer
- Expanding Flow Maps
- Expanding LLM Agent Boundaries with Strategy-Guided Exploration
- Expanding the Role of Diffusion Models for Robust Classifier Training
- Expected Batch Optimal Transport Plans and Consequences for Flow Matching
- Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
- Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
- ExperiGen: Agentic Hypothesis Discovery from Observational Data
- Expert-guided Bayesian optimization for sustainable protein formulation
- ExpertNavigator: Functionally Coherent Expert Grouping and Pairwise-Ranked Routing for High-Fidelity Dense-to-MoE Conversion
- Explainability matters: The effect of liability rules on the healthcare sector
- Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
- Explaining and Preventing Alignment Collapse in Iterative RLHF
- Explaining Cross-Modal Model Behavior with Gradient-Estimation-Based Feature Interaction
- Explanation Mechanism Influences Human Reliance on Reinforcement Learning Agents
- Explanation Multiplicity in SHAP: Characterization and Assessment
- Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
- Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks
- ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
- Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
- ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
- Exploiting Fine-Tuning Structures to Improve Adversarial Transferability on Downstream SAM
- Exploiting Negative Multi-Cluster Structure in Class-Wise Embeddings for Weakly Supervised Multi-Label Learning
- Exploiting Textual Semantics for Robust Cross-View Object Correspondence
- Exploration as Constrained Policy-Space Optimization
- Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
- Exploring Advertising Manipulation in Diffusion Image Generation
- Exploring Lifelong Adaptation: In-Context Reinforcement Learning in Non-Stationary Environments
- Exploring MLLM-Diffusion Information Transfer with MetaCanvas
- Exploring Multi-Order Self-Similarity for Motion Understanding
- Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts
- Exploring the Epipolar Consistency for Light Field Deraining
- Exploring the Limitations of Layer Synchronization in Spiking Neural Networks
- Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation
- Exponential Map Models as an Interpretable Framework for Generating Neural Spatial Representations
- Exposing and Mitigating Temporal Attack in Deepfake Video Detection
- Exposing Private Corpus Leakage in Multimodal RAG
- Exposing the Illusion of Erasure in Knowledge Editing for LLMs
- Expressive Power of Deep Homomorphism Networks over Relational Databases
- Express Language Modeling
- ExpRFT: Exponential Reward-Weighted Fine-Tuning for Offline RL in Multi-Turn Dialogue
- Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
- Extending 3D Reconstruction Models to Any Camera
- Extending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation
- Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
- Extending ROC Analysis to Uncertainty-Aware Risk Prediction with an Interval-Based AUC (iAUC)
- Externalized CPDAG Summaries Improve LLM Causal Deduction
- Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
- Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
- Extracting Training Data from Diffusion Language Models via Infilling
- Extraneous Cognitive Load in Large Language Models
- ExtrapAir: Air Quality Inference at Unmonitored Locations via Weather-Bridged Spatial Attention
- Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
- ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
- Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors
- Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
- F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation
- FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
- Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking
- FacEDiT: Talking Head Video Editing via Facial Motion Infilling
- FacePhys: State of the Heart Learning
- FaceProbe: Recovering HDR Environment Map via Masked Diffusion and Physical Preference
- FACETS: Cross-Granularity Vision--Language Modeling for 3D Anomaly Detection
- Factor Augmented High-Dimensional SGD
- Factored Generative Models through Mechanism Diversity
- Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
- Factorized Self-Supervised Speech Tokenization
- Factorized Spectral Representations for Reinforcement Learning
- Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
- Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
- FADE: Fractional Anomalous Dynamics Extrapolation for Training-Free Diffusion Transformers Acceleration
- Fail-Closed Alignment for Large Language Models
- Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
- Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
- Failure-Band Authorization for Filtered Retrieval
- Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation
- Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes
- Fair Division of Work in Collaborative Mean Estimation via Bargaining
- FairMT: Fairness for Heterogeneous Multi-Task Learning
- Fairness Failure Modes of Multimodal LLMs
- Fairness in limited resource prediction-driven decisions
- Fair Range k-Supplier Clustering in Offline and Streaming Models
- FairSplit: Decomposing the Embedding Space for Fair Classification
- FairTune Market: A Fair and Trustworthy Marketplace for Fine-Tuned LLMs via Posted-Price & Proper-Scoring Mechanisms
- Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
- Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
- FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
- FakeParts: a New Family of AI-Generated Video Forgeries
- FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
- FalconPerception-HD: High Density Perception via Reinforcement Learning
- Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
- FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
- FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators
- FASD: Hardware Acceleration for Multi-AI-Agent Discussion
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
- Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
- Fast Accurate Quantum Monte Carlo without Metropolis Adjustment
- Fast Algorithms for the Label Propagation Operator on Signed Graphs
- Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-Wasserstein
- Fast and Accurate Probing of In-Training LLMs' Downstream Performances
- Fast and Consistent Structure Learning in Graphical Models via Approximate Cross-Validation
- Fast and slow gradient descent dynamics of logistic regression through weak alignment
- Fast and Stable Gradient Approximation for Bilinear Forms of Hermitian Matrix Functions
- Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers
- Fast Approximate $\ell_p$ Chamfer Distance via Lopsided Embeddings and Structured JL
- FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model
- Fast Diverse Nearest Neighbor Search
- Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
- FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
- Faster Dynamic Graph Clustering with Hierarchical Graph Contraction
- Faster Rates For Federated Variational Inequalities
- FASTER: Rethinking Real-Time Flow VLAs
- FASTER: Value-Guided Sampling for Fast RL
- Fast Gauss-Newton for Multiclass Cross-Entropy
- Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
- Fast Learning Rates for Physics-Informed Kernel Methods
- Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching
- Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
- Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
- Fast, Relaxation‑ and Hyperparameter‑Free Pairwise Worst-Case Class Separation
- Fast-RL: Accelerating Reinforcement Learning for LongCoT Reasoning Models
- Fast Sandwich Products in Clifford Algebra
- Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models
- Fault Tolerance in Transformers Favors Output Alignment over Hidden-State Consistency
- Fault Tolerant Coresets
- FAUST: Federated Asynchronous Update with Staggered Timescales for Low-Communication Foundation Model Training
- FAVLA: A Force-Adaptive Multi-Rate VLA model for Contact-Rich Robotic Manipulation
- FC-DGCN: Deep Graph Convolutional Network for Face Clustering and Recognition
- 𝑓-Differential Privacy Filters: Validity and Approximate Solutions
- FEAD: Fine-Grained Epipolar Attention Diffusion for Large-Disparity Light Field Spatial Super-Resolution
- Feasible Policy Optimization for Safe Reinforcement Learning
- FeatCal: Feature Calibration for Post-Merging Models
- Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
- Feature Information Dynamics in Diffusion
- Feature Learning Dynamics in Infinite-Depth Neural Networks
- Feature learning in high-dimensions under structured covariance: Scaling laws in quadratic networks
- Feature Recovery for Object Understanding Under Physical Transformation
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
- Fed-AGA: An Anchor Graph Alignment Framework for Federated Unaligned Multi-view Clustering
- FedCAG: Federated Causality-Aware Graph Learning for Multi-Cloud Workload Forecasting
- FedCF: Fair Federated Conformal Prediction
- Federated Concept-Based Models: Interpretable models with distributed supervision
- Federated Dataset Simulation: Inducing Label-Free Heterogeneity Across Tasks
- Federated Distributionally Robust Neural Combinatorial Optimization with Convergence Guarantees
- Federated Graph Learning with Local Message Compensation
- Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
- Federated Logic Gate Networks via Boolean Feature Selection
- Federated Unlearning with Gradient Adaptive Shaping
- Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
- Federation Is the Way Forward for AI Agents
- FedIBS: Federated Vision-Language Adaptation via Intrinsic Bias Selection
- FedIndex: Federated Domain Adaptation with Continuous Domain Indices
- FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
- FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated Learning
- FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation
- FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
- FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
- Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
- FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning
- FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
- FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning
- FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
- FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning
- Feedback Forensics: A Toolkit to Measure AI Personality
- Feedback World Model Enables Precise Guidance of Diffusion Policy
- Feed-Forward 3D Gaussian Splatting for High-Fidelity Animatable Hand Avatar Reconstruction from a Single Image
- Feedforward Novel View Synthesis for Heterogeneous Cameras
- Feeling of Knowing in Large Language Models
- Felid: A Flexible and Efficient Design for Transformer Fine-Tuning over Encrypted Data
- FELPS: Fair and Efficient Scheduling for Multi-LoRA Serving System
- FENet: Functional Embedding Neural Network for Change-Point Detection in Functional Time Series
- FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
- FerQ: Fermat Quotient Reformulation of High-Order Binary Optimization
- Ferrogen: Generative Pipeline for Guided Search of Novel Ferroelectric Material for Logic and Memory
- FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices
- fev-bench: A Realistic Benchmark for Time Series Forecasting
- Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
- Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models
- Fewer Tokens, Fewer Layers: Efficient Vision Token Pruning and On-Policy Distillation to Accelerate VLMs
- Few-shot Task Learning via Compositional Concept Inference
- Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
- Few-Shot Visual Concept Extraction for Steering Diffusion Transformers
- Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
- Few-Step Cofolding with All-Atom Flow Maps
- Few-Step Diffusion Language Models via Trajectory Self-Distillation
- FFTSparse: Relative-Position Correlation Guided Sparse Attention for Long-Context Language Models
- FiedlerPrune: Connectivity-Preserving Cross-Layer Pruning for Large Language Models
- Fiedler-Regularized Causal Discovery for Sparse Connected DAGs
- Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
- FiLM-CAM: Keyed Feature Modulation for Conditional-Access Watermarking
- FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
- FILOsofer: A TEE-Shielded Model Partitioning Framework based on Fisher Information-Guided LoRA Obfuscation
- Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting
- Filtered Conformal Ellipsoids for Graph-Native Time Series
- Filtered-Trace Online Variational Training for Probabilistic Spiking Neural Networks
- FinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining
- FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection
- Finding Interpretable Prompt-Specific Circuits in Language Models
- Finding Koopman Invariant Subspaces via Personalized PageRank
- Finding Simple Proofs for First-Order Optimization
- FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis
- Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
- Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
- FineRMoE: Dimension Expansion for Finer-Grained Expert with an Upcycling Approach
- Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language Models
- Fine-Tuning Improves Information Conveyance in Language Models
- Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG
- Fine-Tuning Language Models to Know What They Know
- Finetuning with Sampling: Make SFT Generalize, Not Forget
- FineVision: Open Data Is All You Need
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
- Fingerprinting Inference Systems of Large Language Models
- Finite-Memory Control of POMDPs: Fundamental Limits and Efficient Design
- Finite-Resolution Decision Sufficiency for Linear Optimization
- Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces
- Finite-Sample and Communication-Efficient Networked Information Aggregation
- Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
- Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
- Finite Time Analysis of Risk-Sensitive RL via Noisy Power Iteration
- FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation
- FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting
- FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation
- Firefly: Illuminating Verified Real-world Tool Call Data Generation
- FireMPC: A Multi-Source Pan-Canadian Wildfire Benchmark Revealing Spatiotemporal Generalization Gaps
- First-Order Regret for Online Convex Optimization with Memory and Online Nonstochastic Control
- First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems
- First-Token Attraction in Mamba Dynamics
- FISC: Time-Series Forecasting via First-Layer Statistical Calibration Constraints
- Fisher Decorator: Refining Flow Policy via A Local Transport Map
- Fisher-Glass: Tail Sample Complexity from Nuisance-Projected Fisher Information
- Fisher information and the geometry of memorization in neural networks
- Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
- FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
- FIVE-VLA: Fast and EffectIVE Closed-Loop Autonomous Driving with Recurrent Action Memory
- Fixed-Point Masked Generative Modeling
- Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models
- Fixed-Size Active Statistical Inference
- Fixed Universal Transformers
- Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
- FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
- FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
- FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
- FLARE: Diffusion for Hybrid Language Model
- FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
- FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare Removal
- FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
- FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention
- FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers.
- Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
- FLASH: Efficient Visuomotor Policy via Sparse Sampling
- FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
- FlashFFN: Multi-Head Decomposition Enables I/O-Aware Feed-Forward Network
- Flash-KMeans: Fast and Memory-Efficient Exact K-Means
- FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention
- FlashMol: High-Quality Molecule Generation in as Few as Four Steps
- Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
- FlashPlanner: Real-Time Goal-Conditioned Flow-Matching Planning for Autonomous Driving with Online RL Fine-Tuning
- FlashRelight: Portrait Video Relighting with Dynamic Lighting
- Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
- FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction
- FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps
- FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
- Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
- Flexible Flows for Biological Sequence Design
- Flexible Intensities Matter: A comprehensive re-evaluation of Classical and Neural Temporal Point Processes
- Flexible Routing via Uncertainty Decomposition
- FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
- FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
- FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems
- FLIP: Fast and Accurate Global Lipschitz Estimation for Large Feedforward Networks
- Flipping Bits, Not Gradients: Sharpness-Aware Minimization Directly on the Boolean Hypercube
- FloatDoor: Platform triggered Backdoors in LLMs
- FLoRA-Chef: Making A Good LoRA Recipe in Federated Generalization
- Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
- FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
- Flow-Based Conformal Predictive Distributions
- Flow-based Spectral Kernel Learning for Nonstationary Attention
- FlowBatt: Flow Matching for Probabilistic Battery Degradation Prediction
- Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
- Flow+Diff: Unifying Flow and Diffusion Representations for Multivariate Time Series Anomaly Detection
- Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
- Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
- Flow Equivariant State Space Model
- Flowette: Flow Matching with Graphette Priors for Graph Generation
- Flow-Guided Target-Space Alignment via Path Consistency
- FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
- FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems
- Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems
- Flow Map Language Models: One-step Language Modeling via Continuous Denoising
- FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network
- Flow Matching for Count Data
- Flow Matching for Offline Reinforcement Learning with Discrete Actions
- Flow Matching from Viewpoint of Proximal Operators
- Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints
- Flow Matching Reinforcement Learning via SDE Inference
- Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
- Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
- FlowMoP: Stochastic Multi-Person Motion Prediction
- Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
- FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
- FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
- FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
- FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing
- Flow-Transformed Implicit Processes for Function-Space Variational Inference
- Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
- FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
- FLUX: Geometry-Aware Longitudinal Flow Matching with Mixture of Experts
- FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models
- Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials
- Fluxtrapolation: A benchmark on extrapolating ecosystem fluxes
- FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
- FlyingDrones: A Dataset and Benchmark for Optical Flow Estimation from UAV motion
- FM-ChangeNet: Learning Change through Pathwise Feature Transport
- FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
- FMMI: Flow Matching Mutual Information Estimation
- fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
- fNIRSAtlas: A Large-Scale Benchmark for Functional Near-Infrared Spectroscopy Classification
- FOAM: Factored One-sided Adam-Moment for Practical and Scalable SOAP
- Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
- Focusable Monocular Depth Estimation
- Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
- FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification
- Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
- Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
- Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models
- FocusNav: Learning Task-directed Perception via Action-Aware Future Reconstruction in Vision-and-Language Navigation
- Focus on Where You Aggregate: Restricted SAM for Non-IID Federated Learning
- FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models
- FogGS: Physics-Grounded 3D Foggy Effects
- FOGO: Forgetting-aware Orthogonalization Optimizer
- FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening
- Follow-Bench 2.0: An End-to-End 3D Benchmark for Socially-Aware Robot Person Following
- Follow the Mean: Reference-Guided Flow Matching
- Follow the Regularized Leader Does Not Converge in Constrained Optimization
- Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT
- FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization
- FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance
- ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty
- Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
- Forced Orders: What LLM Leaderboards Hide About Model Comparisons
- ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
- ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation
- ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
- Forecasting Downstream Performance of LLMs With Proxy Metrics
- Forecasting Microbial Dynamics: Evaluation Protocol and Prior-Spectrum Benchmark
- ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models
- Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
- Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
- Forgery Evidence Peaks Mid-Stack: Forensic Evidence Relay for Multimodal Forgery Detection
- Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
- Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
- Forgetting to Improve: Principled Data Removal in Active Learning
- Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
- Formal Guarantees for Frontier AI Systems
- Forward Shapley Scoring for Non-Myopic Active Feature Acquisition
- Foundation Model Informed Acquisition Functions for Molecular Discovery
- Foundation Models for Particle Accelerators
- Foundation Models for Temporal Systems: From Forecasting to World Modeling
- Foundation Models for the Brain and Body
- Foundation Pareto Flow Policy for Multi-Objective Reinforcement Learning
- Foundations of Agentic Systems Theory (FAST)
- Foundations of Categorical Equivariant Deep Learning
- Foundations of Language Model Security: Theory, Practice, and Fundamental Limits
- Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
- FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images
- Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification
- FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models
- Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space Models
- Foveated BagNet: Inherent Interpretability Does Not Exclude Global Context
- FracEncoder: Towards Adaptive Cognitive Trajectories via Fractional-Order Context Encoding
- Fractal-G: Topology-Aware Heterogeneous Graphs for Medical Image Segmentation
- Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference
- Fractional State Space Transition for Long Sequence Modeling
- FracTS: Hierarchical and Autoregressive Time Series Generation
- FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond
- FrameScout: Scouting Query-Relevant Frames for Long Video Understanding
- FrameSelect: A Unified Library for Video Frame Selection and Evaluation
- Frame the adversary: a structure-aware attack methodology
- FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
- Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large Models
- Frank-Wolfe Beyond 1/t Convergence
- FraudBench: A Legal Evaluation of AI Deception on Realistic Tasks
- Fréchet Regression on the Bures-Wasserstein Manifold
- FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding
- FreDRec: Frequency-Decoupled Knowledge Distillation for Multimodal Recommendation in Missing Modalities Scenarios
- FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated Videos
- Free Decompression with Algebraic Spectral Curves
- Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
- Free energy Estimation on Any State Space
- Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success
- Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
- Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
- FreeOcc: Decoupling Ego-Motion for Efficient 4D Occupancy Forecasting via Continuous Flow Matching
- FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
- FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching
- Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
- FrequencyBooster: Advancing Pixel Diffusion for High-Fidelity Image Generation
- Frequency Domain Reservoir Computing
- Frequency-Structured Hamiltonian Neural Network for Multi-Timescale Dynamics
- Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation
- FRESCO: A Novel Consistency Control for Asynchronous Pipeline Parallel Training
- FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
- Freshness-Gated Imagination: Step-Level Trust for Latent World Models
- FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry
- From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
- From Approximation to Computation: Universal Power of Deep Narrow Networks at Constant Width
- From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model
- From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
- From Benchmark to Adoption: Coding Agent Evaluation Needs User-Level Harness
- From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
- From Claims to Context: Holistic Information Verification Requires Contextual Signals
- From Click Imitation to Transition Equivalence: Rethinking Supervision for GUI Agents
- From Clips to Streams: A Unified Framework for Streaming Sign Language Translation
- From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
- From Contexts to Conditionals: Statistical Self-Consistency of Persona Prompting
- From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination
- From Cursed to Competitive: Closing the ZO–FO Gap via Input-to-State Stability
- From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
- From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability
- From Detection to Understanding — A Multi-Task Dataset for Traffic Anomaly Reasoning
- From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
- From Expert Knowledge to Optimization Modeling: Prototype-Based Data Synthesis and Logical Reinforcement Learning
- From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs
- From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
- From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
- From Finding to Linking: Benchmarking and Advancing Cross-Long-Video Reasoning for Multimodal LLMs
- From Generation to Restoration: Residual Diffusion for Neural Channel Decoding
- From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
- From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers
- From Heartbeat to Cardiochoreography: A Mechanics Foundation Model for Individualized 4D Cardiac Motion Generation Conditioned on Electrophysiology
- From Heuristics to Guarantees: Bandit and RL Blueprint for Reliable Agentic-AI
- From History to State: Constant-Context Skill Learning for LLM Agents
- From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMs
- From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
- From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization
- From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents
- From I/O to Code with Discovery Agent
- From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment
- From Jumps to Signatures: a Generative Method for Temporal Point Processes
- From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
- From Likelihood Convergence to Parameter Convergence in POMDPs
- From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph Pretraining
- From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
- From Local to Global: Progressive Consensus via Hierarchical Communication in Multi-Agent Reinforcement Learning
- From Matching to Reasoning: Query-Aware Long Video Summarization
- From Matrix Inversion to Constraints: Provably Tighter Confidence Regions for Importance Weights in Label Shift
- From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
- From Nodes to Pixels: Topological and Structural Two-View Graph Imaging
- From Noise to Diversity: Random Embedding Injection in LLM Reasoning
- From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
- From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient
- From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
- From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes
- From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
- From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
- From POMDP Theory to Deep RL with Particle Filters
- From Post-Hoc to Ante-Hoc: Consistently Explainable Semi-Supervised Time Series Classification
- From Preference Data to Personalization: Tracing Sycophancy in Large Language Models
- From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
- From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
- From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
- From Representation to Intervention: Using Emotion Vectors to Monitor and Guide Language Models
- From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
- From Retrieval to Recognition: Knowledge-Enhanced Foundation Models for Time Series Classification
- From Sample to Subset Construction: Coverage-Aware Curation of Robot Demonstrations
- From Scores to Evidence: Robust Evaluation of Foundation Models
- From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
- From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
- From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations
- From SGD to Muon: Adaptive Optimization via Schatten-p Norms
- From Small to Large: Cross-Scale Graph Domain Adaptation via Local-Global Structural Alignment
- From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation
- From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
- From Static Geometry to Dynamical Singularity: Detecting Memorization in Diffusion Models via Score Evolution
- From Static Policies to Adaptive Priors in Offline Reinforcement Learning
- From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors
- From Table to Cell: Attention for Better Reasoning with TABALIGN
- From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
- From Tokens to Tactics: Adversarial Text Optimization in an Axis-Aligned Rhetorical Strategy Space for Harmful Content Detection
- From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
- From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation
- From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models
- From Walls to Synergy: A Joint LLM-Evolution Framework for MILP Solvers
- From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning
- From “Weak” Signals to Strong Models: Preference Delta Aggregation with LoRA Merging
- From Weeks to Hours: Fast and Principled SFT Curation for LLM
- From Zero to Hero: Training-Free Custom Concept Spawning in World Models
- Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
- Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering with Generative Optimization
- Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
- FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
- FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
- Frontier Task Synthesis Via Solution-Centric Evolution
- Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
- FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
- FTerViT: Fully Ternary Vision Transformer
- Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow Matching
- Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
- Full-Duplex Speech-Motion Model for Dyadic Interaction
- Full Fine-Tuning Is Not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP Adaptation
- Full-Sequence Masked Diffusion for Generative Recommendation
- Fully Distributed Tâtonnement for Chores Markets
- Fully First-Order Algorithms for Online Non-Convex Bilevel Optimization
- FuncFormer: Circuit Representation Learning via the Flow of Functional Propagation
- Functional Gradient Descent with Adaptive Representations
- FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
- Function graph transformers universally approximate operators between function spaces
- FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
- FuseAdapt: Adaptation-Space Fusion for Multi-Modal Semantic Segmentation with Missing Modalities
- FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
- FusionNeXt: Sequence-First 3D Multi-Modal Fusion in the Era of LLMs
- Fusion or Confusion? Multimodal Complexity Is Not All You Need
- FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning
- FUTON: Fourier Tensor Network for Implicit Neural Representations
- FutureSim: Replaying World Events to Evaluate Adaptive Agents
- fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets
- G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
- G2Fusion: Geometric-to-Generative Image Fusion via Registration-Restoration Evolution
- GADMVP: Adaptive Few-Shot Graph-Level Anomaly Detection with Multi-View Structured Prompting
- GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
- Gaeta-Lie Neural SDEs: Symmetry-Regularized Learning of Stochastic Dynamics
- GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
- GaitLingo: Self-Supervised Gait Representation Learning with Language Priors
- GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
- GAMMA: Scalable 4D Gaussian Reconstruction Model for Novel View Synthesis of Monocular Videos
- GAPS: Gradient-Aware Adaptation-Gap Scoring for Time-Series Anomaly Detection with Foundation Models
- GARDO: Reinforcing Diffusion Models without Reward Hacking
- GATE-AD: Graph Attention Network Encoding for Few-Shot Industrial Visual Anomaly Detection
- Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
- GauGal: Gaussian-Galerkin Electromagnetic Inverse Scattering Imaging
- GAUGECAST++: A Physics-Informed Latent Forecasting System for Localized Flood Prediction
- Gauge-Symmetric Dual Lagrangian Frameworks for Born-Oppenheimer Molecular Dynamics
- GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization
- Gaussian Density Splatting Network
- Gaussian Mixture Models in Hilbert Spaces via Kernel Methods
- Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors
- GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction
- GCD: Correcting Hidden-State Bias in Off-Policy Agentic RL
- GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs
- GDMD: Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
- GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
- GEAR: A GPU-Accelerated Global Solver for Nonlinear Programs via Linear Bound Propagation
- GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
- GEAR: Bridging the Planner-Actor Gap via Gradient-Aligned Policy Extraction
- GEAR: Generator-Adaptive State Space Models for Associative Recall
- GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs
- GEM: A Dual-Scale Architecture for Graph-Level Hierarchical Representation Learning
- GEM: Interpretable Language Models via Geometric Embedding Alignment
- GEMS-3D: A Large-Scale 3D Gravity, Electrical, Magnetic, and Seismic Earth Simulation Dataset for Multimodal Geophysical Learning
- GenAI Evaluation Results are Largely Artifacts of Evaluation Design Choices: Evidence from Audit Studies of Resume Screening
- GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking
- Gender Artifacts from Art History to Text-to-Image Generation
- GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- General Agent Evaluation
- Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
- Generalizable Physics Simulation through Compositional Energy Minimization
- Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems
- Generalization at the Edge of Stability
- Generalization Bounds for Neural Networks with Sparse Connectivity
- Generalization Dynamics of Linear Diffusion Models
- Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
- Generalization for Time Series in Tight Settings: Latency, Inference, Memory, prIvacy and Sustainability (TS-LIMITS)
- Generalization in Neural Networks Through the Lens of Magnitude Potential
- Generalization Measures for Deep Learning Should Be Audited for Fragility
- Generalization Without Compression Penalty: A Stability Analysis of Error Feedback
- Generalized Adaptive Boosting and the Geometry of Mistakes
- Generalized Bayes for Causal Inference
- Generalized Influence Functions for Better Model Change Estimates
- Generalized Intention Modeling in Multi-Agent Reinforcement Learning
- Generalized Laplacian in Spectral Seriation on Manifold Data
- Generalized Priority-Aware Shapley Value
- Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise
- Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates
- Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
- Generalizing Action-Conditioned Latent World Models with Video Model Rewards
- Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
- Generalizing the Geometry of Model Merging Through Fréchet Averages
- Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
- Generating Financial Time Series by Matching Random Convolutional Features
- Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems
- Generating in the Limit with Infinitely Many Hallucinations
- Generating Physically Consistent Molecules with Energy-Based Models
- Generating Symmetric Materials using Latent Flow Matching
- Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
- Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife
- Generation-Drift-Guided Block Pruning for Large Language Models
- Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
- Generation Navigator: A State-Aware Agentic Framework for Image Generation
- Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data
- Generative Actor-Critic with Soft Bridge Policies
- Generative AI and Stochastic Thermodynamics: A Tale of Free Energies
- Generative Conformal Prediction with Optimized Coverage Allocation
- Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
- Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification
- Generative Modeling by Value-Driven Transport
- Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows
- Generative Modeling via Drifting
- Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport
- Generative Object Detection with Co-Training
- Generative OOD-regularized Model-based Policy Optimization
- Generative Scenario Rollouts for End-to-End Autonomous Driving
- Generative Structure from Motion with Native 3D Diffusion
- GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- GeneZip: Region-Aware Compression for Long Context DNA Modeling
- GenRec: Knowing Where to Reconstruct and Where to Generate
- GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
- GenRM-Flow: Generators are Process-aware Reward Models in Flow Matching
- GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
- Gen-Searcher: Reinforcing Agentic Search for Image Generation
- GenZ: Hybrid statistical–foundational models for knowledge discovery from real-valued multidimensional targets
- GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
- GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation
- GeoCurv-TTT: Geometry-Aware Deformation Restoration for 3D Test-Time Training
- GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
- GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity of Street-View Generation
- GeoG2U-Bench: When Does Generation Help Understanding in Ultra-High-Resolution Remote Sensing?
- GeoMamba: Geometry-Aware State Space Modeling for Image Restoration
- GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video Generation
- Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap
- Geometrically Disentangling Concept Learning from the Language Modeling Loss
- Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
- Geometric Factual Recall in Transformers
- Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG
- Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer
- Geometric Instability of Hidden-State Trajectories Predicts Reasoning Failures in Large Language Models
- Geometric Latent Reasoning Induces Shorter Generations in LLMs
- Geometric Prompt-Trajectory Planning for Test-Time Scaling
- Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
- Geometric Velocity Regularity for Flow Matching on Manifold-Concentrated Data
- Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
- Geometry-Aware Directional Alignment for Coherent Model Merging
- Geometry-Aware Flow Matching for Sparse-View 3D Gaussian Splatting
- Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
- Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning
- Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction
- Geometry-Aware Score-Repellent Monte Carlo
- Geometry-Aware Self-Supervised Electrophysiology Representation Learning
- Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds
- Geometry-Aware Subspace Perturbation for Heterogeneous Federated Learning
- Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMs
- Geometry-Calibrated Conformal Abstention for Language Models
- Geometry-Centered 3D Latent World Models for Growing Surfaces
- Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
- Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation
- Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMs
- Geometry Matters in Packed 3D Attention
- Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
- Geometry over Density: Few-Shot Cross-Domain OOD Detection
- Geometry-Regularized Collapse Resistance via Consensus Enhancement for Federated Learning
- GeoMIND: A Benchmark for Spatial Understanding in Robotic Manipulation
- GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
- GeoPano: Towards Geometrically Accurate Panoramic 3D Reconstruction from a Single Panorama
- GEOPHYS: The Geometry of Physical Plausibility
- GeoPMR: Preserving Relational and Hierarchical Geometry in Multimodal Molecular Representation Learning
- GeoRad-3D: Factorized Geometry Transport and Residual Radiometry for 3D Radar Nowcasting
- GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing Segmentation
- Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images
- GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
- GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
- GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
- GeoTransolver: Learning Physics on Irregular Domains using Multi-scale Geometry Aware Physics Attention Transformer
- GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning
- GeoWorld: A Geometry-First World Model for Reconstruction and Imagination
- GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
- Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
- gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
- GGQR: Gaussian-Grounded Query Refinement for Feed-Forward 4D Gaussian Splatting
- gHAWK: Structural Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
- Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
- GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
- Gibbs Gradient Descent: A Langevin Approach to Optimization
- GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection
- GISA: A Benchmark for General Information-Seeking Assistant
- GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
- Git Context Controller: Manage the Context of Agents by Agentic Git
- GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
- GIVLA: Deep Geometry Internalization for A Lightweight VLA via Geometry Instruction and Gradient-Informed Training
- GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem
- Glance Before You Tell: Anomaly-Guided 3D Radiology Report Generation with Heat-Conduction Slice Encoders
- GLARE: Generating Listening Heads with Appropriate REactions
- GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
- Glob3R: Global Structure-from-Motion with 3D Foundation Models
- Global Context Guidance for Diffusion Large Language Models
- Global Convergence in Deep Networks via the Second Law of Thermodynamics
- Global convergence of adjoint-optimized neural PDEs
- Global Convergence of Four-Layer Matrix Factorization under Random Initialization
- Global Importance Estimation for KV Cache Eviction
- Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs
- Global Optimality for Constrained Exploration via Penalty Regularization
- Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
- GLOBE: Accurate Surrogates for Boundary-Driven PDEs via Domain-Inspired Architectures and Equivariance
- GLOVE: Global Verifier for LLM Memory-Environment Realignment
- GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
- GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting
- Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
- GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation
- GlycoGen: Crystallizing Flows for De Novo Glycan Structure Prediction
- GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors
- GMO-E²DIT: Grounded Multi-Operation Editing for E-Commerce Images
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time
- GNES: Neural-Guided Evolutionary Program Search for Interpretable Multi-Agent Control
- GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
- Goal-Conditioned Supervised Learning for Multi-Objective Recommendation
- GOAT-AL: Pseudo Neural Collapse Guides Adaptive Coverage for All-Budget Active Learning
- Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
- Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
- GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
- GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning
- GOLIATH: Gradient Inversion of Tabular Diffusion Models
- Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
- GoT: A Game-Theoretic Approach to the Game of Twenty Questions
- G-PAC: Constructing Cohesive Pseudo-Features for Generalizable Physical Adversarial Camouflage
- GPA: General Principled Framework for Linearizing Softmax Attention via KV Cache Approximation
- GPA: Generative Population Annealing for Test-Time Sequence Design with Pretrained Generative Models
- GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
- GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
- GPU Hierarchy Meets Structured Matrices: Fast Algorithms for State-Space Models
- GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
- Gradient-based Graph Structure Optimisation for Research Networks
- Gradient Boosted Trees for Retrieval-Augmented Generation
- Gradient descent inference in empirical risk minimization
- Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics
- Gradient Descent’s Last Iterate is Often (slightly) Suboptimal
- Gradient-Free Editing for Attribute Invariance in Graph Neural Networks
- Gradient-Guided Smoothing for LLM Safety Defense
- Gradient-Mine Units: Scorched-Earth Strategy for Model Protection against Unauthorized Fine-Tuning
- Gradient Regularized Newton Boosting Trees with Global Convergence
- Gradient Routing Localizes and Removes Unintended Behaviors in RL
- Gradient Span Algorithms Make Predictable Progress in High Dimension
- GradShield: Alignment Preserving Finetuning
- GradTrack: Detecting Noisy Labels via Temporal Trajectories of Class-wise Gradient Misalignment
- Gram-Calibrated Anchoring for Class-Incremental Learning
- GRAM: Group-wise Rank-Aware Modal Merging via Subspace Alignment
- GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis
- GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
- Graph and Simplicial Complex Prediction Gaussian Process via Hodgelet Representations
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes
- Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation
- Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
- Graph Distance Based on Cause-Effect Estimands with Latents
- Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
- Graph-Enhanced Attribute-Aware Modeling for Cloth-Changing Person Re-Identification
- GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
- GraphIP–Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
- Graph Label Alignment: A Diagnostic Atlas for Graph Classification
- GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
- Graph Learning from Label Proportions using Topology-Aware Pseudo Labeling and Aggregation
- Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
- Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
- GraphMemRL: Action-Native Reinforcement Learning for Persistent Graph Memory Construction
- Graph-Regularized Sparse Autoencoders for LLM Safety Steering
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
- Graph Topology Augmentation for Prioritized Sweeping in Non-stationary Reinforcement Learning
- GraphUAT: Uncertainty Attribution in Graph Neural Networks
- GraphWrit3R: End-to-End Writing of Scene Graphs for Multi-Modal 3D Scenes
- GRASP: Guided Residual Adapters with Sample-wise Partitioning
- GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
- Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation
- Grassmannian Geodesic Steering: Rank-Preserving Subspace Control for Inference-Time Alignment of Language Models
- Greedy Alignment Principle for Optimizer Selection
- GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement
- GridDiffuser: Constraint-Guided Graph Diffusion for AC Optimal Power Flow
- Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models
- GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
- GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
- GRNAgent: A Multimodal Graph Reasoning Agent for Gene Regulatory Network Inference
- Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
- Grounded and Faithful Vision-Language Models for Real-World Deployment
- Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
- Grounded or Fabricated? Unsupervised Detection of LLM Hallucinations via Contextualized Influence on Response Embeddings
- Grounded User Simulation for Model Evaluation and Training:\\ Diversity, Fidelity, and Validity
- Ground False: Uncovering Errors in Formal Mathematics Benchmarks
- Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
- Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement Learning
- Grounding Driving VLA via Inverse Kinematics
- Grounding Multimodal Reasoning with Evidence-Ablated Negatives
- Group-Aware Matrix Estimation and Latent Subspace Recovery
- Group Distributionally Robust Optimization with Flexible Sample Queries
- Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement Learning
- Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
- GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
- Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
- Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
- Growing a Neural Network in Breadth, Depth, and Time
- GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
- GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems
- GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
- Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
- Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
- Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent
- Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
- GUARD: Scalable Gradient-based Unlearning with Adversarial Robustness Defense
- Guidance For Prior Change via Density Ratio Estimation
- Guided Data Generation for Understanding Model Behavior
- Guiding Data Allocation for Robust Subpopulation Generalization
- Guiding Visual Autoregressive Models through Spectrum Weakening
- GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
- GUI-Libra: Data-Efficient Post-Training for Reliable Reasoning-and-Acting in Native GUI Agents
- GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions
- Gumbo: Gumbel Optimized High-Temperature Speculative Sampling
- GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
- GWScore: A structural diversity metric for consistent text-to-image generation
- Gym-Anything: Turn Any Software into an Agent Environment
- G-Zero: Self-Play for Open-Ended Generation from Zero Data
- H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
- HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
- Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
- HACO: Hedged Agent Computing for Reliable LLM Systems
- Hadamard Representation: Scaffolding Performance Across Model-free RL
- HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models
- Half-Truths Break Similarity-Based Retrieval
- Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
- Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories
- Hallucination in World Models is Predictable and Preventable
- HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image Restoration
- HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
- HALMES: Knowing When to Intervene in LVLM Hallucination Mitigation
- HALO: Heterogeneous-Aware LoRA Optimization via Rank Allocation and Client-Aware Projection
- HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training
- HALO-VGGT: Heterogeneity-Aware Lightweight Online Compression Allocator for Efficient VGGT
- Halt Fast! Early Stopping for Certified Robustness
- HAMSTAR: Hamiltonian Structured Inter-Period Refinement for Long-Term Time Series Forecasting
- HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
- HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
- HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields
- Handwriting decoding as a challenging motor task for EEG Foundation Models
- Handwritten Text Recognition Lives in the High-Pixel Variance Subspace
- HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models
- HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
- haphazard: A unified library and benchmark for online learning under varying feature availability
- HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
- Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
- HARC: Coupling Harmfulness and Refusal Capabilities for Robust Safety Alignment
- Hard Attention Transformers and BSS-Machines
- Harder the Task, Sparser the Representation: Sparsity as a Learning Signature of Capability in LLMs
- Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
- Harmless in Pieces, Harmful in Motion: Detecting Multi-Agent Jailbreaks
- Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking
- HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly Detection
- Harnessing Accurate and Automatic Trend Detection in Data Streams via Tbps-Level Inference
- Harnessing Agentic Evolution
- Harnessing Data Asymmetry in Manifold Learning
- Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration
- Harnessing Streaming Video in the Wild
- Harnessing Textual Refusal Directions for Multimodal Safety
- Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
- HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
- Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision
- HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices
- HDCS: Hierarchy Discovery and Critic Shaping for Reinforcement Learning with Automaton Specification
- HDL-RepoBench: Multi-Paradigm Repository-Level Code Completion for Hardware Design Languages
- Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models
- Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO
- Hearing the Unspoken: Simulator-Induced Asymmetric-View Policy Optimization for Proactive Task-Oriented Dialogue
- Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-visual LLMs
- HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?
- HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
- HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
- Heavy-Tailed Flow Matching via Random Clocks
- HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
- HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching
- HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
- HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
- Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
- HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
- Hessian-Dependent Sample Complexity in Zeroth-Order Stochastic Optimization: Suboptimality of Convex-Support Sampling and Optimal Sample Complexity
- HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
- HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs
- Heterogeneity-aware Distillation for Federated Continual Learning
- Heterogeneous Agent Collaborative Reinforcement Learning
- Heterogeneous Graph Federated Learning with Structure-Aware Data-Free Distillation
- Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and Confidence
- Heterogeneous Parallelism for Multimodal Large Language Model Training
- Heteroscedastic TrueSkill: Modeling Match Noise and Player Consistency
- Heteroscedastic Variational Last Layers
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily
- Heuresis: Evaluating Search Strategies for Autonomous Machine Learning Research Agents
- H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
- H-GenPO: Hierarchical Generative Policy Optimization via the Option-Critic Framework
- Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
- Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
- HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths
- Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
- Hidden Tails: Certifying Tail-Risk Claims under Selective Labels
- Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search
- Hide to Guide: Learning via Semantic Masking
- Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
- HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning
- Hierarchical Adaptive Frame Sampling For Video Understanding
- Hierarchical Agglomerative Clustering via Relaxed Representatives
- Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence
- Hierarchical Conformal Classification
- Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment
- Hierarchical Denoising For Multi-Step Visual Reasoning
- Hierarchical Graph Alignment for Cross-Modal 3D Scene Grounding
- Hierarchical Graph Representation Learning with Pooling-Induced Substructures
- Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs
- Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
- Hierarchical Task Network Planning with LLM-Generated Heuristics
- Hierarchical Variational Policies for Reward-Guided Diffusion
- Hierarchical World Models with Implicit Dynamics
- HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation
- HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection
- HierSVA: A Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification
- HIFC-IQA: Train-Free Cross-Domain Image Quality Assessment via Dual-Process Cognition
- HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
- HiFloat4 Format for Language Model Pre-training on Ascend NPUs
- High-arity Sample Compression
- High-Dimensional Conditional Independence Testing via Random Projection Aggregation
- High-dimensional Gaussian Graphical Model Testing for Long-Memory Time Series
- High-Dimensional Learning Dynamics of Attention-Indexed Models
- High-dimensional Limit of SGD for Diagonal Linear Networks
- High-Dimensional Robotic Reinforcement Learning with Developing Synergies
- High dimensional theory of two-phase optimizers
- High Entropy Regularization Leads to Symmetry Equivariant Policies in Dec-POMDPs
- Higher-Order Action Supervision Makes A Strong Policy Class
- Higher-Order Cell Tracking Transformer
- High-Fidelity Boltzmann Samplingvia Physical Prior Lifted Continuous GFlowNets
- High Performance Differentially Private Fine-Tuning using Dataset Distillation
- High-probability Convergence of Gradient Methods under Markovian Stochasticity
- High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch
- High Probability Risk Control for Online Policy Learning
- HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
- HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation
- HiLoc: A Hierarchical Representation Method for Spatial Localization in Multimodal Large Language Models
- HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
- HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding
- Hindsight Relabeling is All You Need for Reach-Avoid Learning
- Hint Tuning: Less Data Makes Better Reasoners
- HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
- Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
- HIRaD: Hidden Interaction Inference from Predictive Radar Dynamics
- HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
- HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction
- Historical Relative Policy Optimization for Bootstrapping LLM Reasoning
- History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes
- Hit Expansion via Localized Exploration of Synthesizable Chemical Space
- Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift
- Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
- Hodge Laplacian Quasi-Harmonic Flows for Option Discovery
- HOGWARTS: Mitigating Perspective Distortion for 6DoF Head Pose Estimation via Virtual Camera Space
- Holistic EvoLution via Intrinsic eXchange for Unified Multimodal Models
- Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
- Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
- HoloCode: A Code-Centric Multi-Agent Framework for Image-to-3D Scene Generation
- HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields
- HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation
- HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement
- Homological Barriers to Stable Local Nash Dynamics in Quadratic Zero-Sum Games
- Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
- HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
- HOPE: Hand-Object Pressure Estimation from Monocular Videos
- HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
- Horizon Adaptive Offline Policy Learning via Value Stitching
- HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics
- Horizon-Stream: Long-Horizon Attention for Streaming 3D Reconstruction
- Horizontal Diffusion Models: Score-based Generative Modeling on Frame-Connection Geometry
- HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration
- How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates?
- How are linear representations learned? Exact solutions to the dynamics of abstraction
- How Can SignSGD Outperform SGD? A Functional Scaling Law Perspective
- How Complete Should a Reference Be? A Benchmark Audit for Fluorescence Spot Detection
- How Data Augmentation Shapes Neural Representations
- How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
- How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
- How deep is your network? Deep vs. shallow learning of transfer operators
- How Diffusion Models Memorize
- How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression
- How Does Cutout Benefit Out-of-Distribution Generalization?
- How does feature learning change the function space evolution?
- How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
- How Does Pruning Change Decisions in Large Language Models?
- How does RL Post-training Induce Skill Composition? A Case Study on Countdown
- How Do Language Models Compose Functions?
- How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
- How do Small Transformer Models Learn Hard Math Tasks?
- How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
- How Far Is Too Far? Object Recognition Declines Monotonically with Semantic Distance
- How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
- How Finite-Rank Bottleneck Shape the Low-Rank Adaptation Landscape
- How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?
- How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness
- How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
- How Language Models Compress and Compare: Understanding Selection with Token Covariance Maps
- How Likely Are Voting Rules Equitable?
- How LLMs Distinguish Threats from Offers
- How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
- How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?
- How Much Information is Needed for Accurate Kalman Filtering?
- How Much is Left? LLMs Linearly Encode Their Remaining Output Length
- How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
- How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
- How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
- How New Strategies Emerge in RL Post-Training: A Controlled Study
- How Post-Training Shapes Biological Reasoning Models
- How Private is Private? A Comparative Study for Face De-Identification
- How Selection Shapes Diversity in LLM Ecosystems
- How Should Parallel Langevin Chains Share Noise?
- How to Have a Sensitive Debate
- How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
- How to Interpret Agent Behavior
- How to make the most of your masked language model for protein engineering
- How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
- How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding
- How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
- How Useful Is Cross-Domain Generalization for Training LLM Monitors?
- How well behaved is finite dimensional Diffusion Maps embedding?
- How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction
- HPC-Bench: A Comprehensive Benchmark for High Performance Computing Codes
- HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
- HRIL: Isolating Multimodal Synergy via Higher-Order Dependence
- HSCO-Bench: An Agent-Driven End-to-End Hardware-Software Co-design Benchmark for Systems-on-Chip
- Human-AI Coevolution: Measuring Human-Agent Teams in the Agentic Era
- Human–AI Collaboration Requires a High-Order Dynamic Abstraction Substrate
- Human-AI Teaming Through the Lens of Calibration
- Human-Inspired, Task-Dimension-Guided Exploration for Efficient Learning and Transfer in High Dimensions
- HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
- Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating
- HumanScore: Benchmarking Human Motions in Generated Videos
- Humans Correct Their Judgements Through Debate, but Weaker AI Models Not
- HumanStereo: A Benchmark for Metric Facial Depth Estimation and Its Evaluation
- HuPER: A Human-Inspired Framework for Phonetic Perception
- HybridCache: Enhancing Prefix Caching for Linear–Softmax Language Models
- Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
- Hybrid Neural World Models for Physical Dynamics
- Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
- Hybrid Reinforcement Learning for One-step Degraded Infrared and Visible Image Fusion
- HyCO: A Hybrid Neural Solver for Combinatorial Optimization
- Hydra-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
- HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
- Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
- Hydra-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
- HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation
- Hyperagents
- Hyperbolic Concept Bottleneck Models
- Hyperbolic Concept Embedding Model for Interpretable Medical Image Diagnosis
- Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning
- Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry–Task Alignment
- Hyperbolic Language Models: From Zipf to Compute-Optimal Scaling
- HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification
- HyperGen: Learning Structure-Aware Spectral Flows for Hypergraph Generation
- Hypergraph Generation via Structured Stochastic Diffusion
- Hypergraph Generation with Latent Diffusion
- Hypergraph-guided Global Mean-field Negotiation For Multiview Evidential Classification
- Hypergraph Modeling of Transformer Attention for Hallucination Detection
- Hypergraph Representation Learning with Hyperlink Random Effects
- Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
- Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
- Hypernetworks for Dynamic Feature Selection
- HyperNSDE: Personalized Neural SDEs for Joint Static—Longitudinal Clinical Data Generation
- Hyperparameter Transfer for Dense Associative Memories
- HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere
- HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution
- Hyperspherical Local Margin Retraction for Zero-Shot Instance-Wise Machine Unlearning
- HyperTransport: Amortized Conditioning of T2I Generative Models
- HyperTree: Scalable Unsupervised Hierarchy Discovery in Hyperbolic Space
- HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
- HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
- HypMoE-ReID: Hyperspherical Mixture-of-Experts for Large Scale Person Re-Identification
- Hypothesis generation and updating in large language models
- HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
- HYVE: Hybrid Views for LLM Context Engineering over Machine Data
- I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video Generation
- IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow
- I Can’t Believe It’s Not Better (ICBINB): Failure Modes of AI in Biology
- ICAT: Incident-Case–Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
- iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity
- IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs
- IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories
- IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder
- IDEAL: Interaction Dynamics and Force-Aware Learning for Dual-Humanoid Collaborative Manipulation
- IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition
- Idempotency Exposes Consistency Problems in Sparse Autoencoders
- Identifiable alignment of unpaired representations
- Identifiable Feedback-Controlled Latent Flow for Unpaired Single-cell Spatio-Temporal Dynamics
- Identification and Bounding of Joint Expectation over Potential Outcomes
- Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access
- Identifying and Mitigating Diversity Collapse in Zero-Shot Personalization with I2I Editing Models
- Identifying Latent Neural Dynamics with Recognition-Parameterized Gaussian Process Dynamical Systems
- Identifying Structural Biases from Causal Mechanism Shifts
- i-DEQ: A stable inertial Deep Equilibrium model for image restoration
- iDETR: Implicit DETR for Tiny Object Detection
- idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
- IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
- IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
- I Have a Stream: Making Self-Supervised Learning Work on Continuous Video
- IIDiff: Learning Cross-Domain Frequency Transitions with Diffusion Mixture-of-Experts
- Illusory Pattern Perception Drives Spurious Inference in Large Language Models
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
- Image Generation for Automotive Lidar Open-vocabulary Semantic Segmentation
- Image Matting without Matting-Specific Annotations via Eikonal Fields
- ImageNet FID is a Pass Check, Not a Finish Line
- Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
- Imagine Before You Draw: Visual Prompt Engineering for Image Generation
- Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction Dynamics
- Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
- Imitation from Observations with Trajectory-Level Generative Embeddings
- ImmuVis: Hyperconvolutional Foundation Models for Imaging Mass Cytometry
- Impacts of Aggregation on Model Diversity and Consumer Utility
- Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
- Imperfect World Models are Exploitable
- Implicit Bias in State Space Models and Linear Autoregressive Training
- Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
- Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
- Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual Flow
- Implicit Goal Conditioning via Value Disaggregation
- Implicit Neural Representations for Variational Problems on Graphons
- Implicit Value Probing: Inferring Human Value Preferences via Strategic Multi-Turn Conversations
- Importance-Aware OBS Pruning for Diffusion Models
- Importance-Weighted Operator Learning Under Probability Measure Shifts
- Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects
- Improved Algorithms for Online Classification with Surrogate Losses
- Improved Baselines with Representation Autoencoders
- Improved Leverage Score Sampling for Constrained Active Linear Regression
- Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
- Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy
- Improved Robust Verifiable Federated Learning Based on Packed Secret Sharing
- Improved Sample Complexity for Markov Games via Variance-Aware Bandit Learning
- Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks
- Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
- Improved Weakly Supervised Semantic Segmentation with A Relationally Optimized Prototype Memory Bank Framework
- Improving Audit Realism with Inference-Time Compute and Deployment Scaffolds
- Improving Causal Explanations
- Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
- Improving Consistency in Retrieval Augmented Systems With Group Similarity Rewards
- Improving constraint-based discovery with robust propagation and LLM priors
- Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy
- Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters
- Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
- Improving Flexible Image Tokenizers for Autoregressive Image Generation
- Improving Function Space Flow Matching with Kernel Optimal Transport
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- Improving Generative Adversarial Networks with Self-Distillation
- Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation
- Improving LLM Final Representations with Inter-Layer Geometry
- Improving Neural Decoding Performance for Language BCIs by Explicitly Modeling Context-Induced Noise
- Improving Neural Processes in the Low-Data Regime via Context-Subset Training and Self-Distillation
- Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures
- Improving Self-Supervised Vision Transformers with Cross Distillation
- Improving the Diffusability of Motion Tokenizer
- Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
- Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
- IMTS-Tokenizer: Time-Aware Tokenization for Irregular Multivariate Time Series Forecasting
- Inadvertent Context Leakage in Language Models
- IncAgg: Efficient Memory-Enhanced Graph Learning via Incremental Aggregation
- Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
- Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
- InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection
- In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL
- In-Context Black-Box Optimization with Unreliable Feedback
- In-Context Learning Can Help Vision Language Models Overcome Training Prior
- In-Context Learning for Remote Sensing Vision: A Semantic-Aware Rotation-Robust Diffusion Framework
- In-context Learning in Presence of Spurious Correlations
- In-context learning to predict critical transitions in dynamical systems
- In-Context Multi-Operator Learning with DeepOSets
- In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
- Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
- Incorporating Neural Network Structure in the Bayesian Learning Rule
- Incremental Learning in Transformers for In-Context Associative Recall
- Incremental Multiple Oracle
- Independent Latents, Robust Neural Operators
- Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
- Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
- Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement
- InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
- Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
- IndustryCode: A Benchmark for Industry Code Generation
- Inertia-1: An Open Exploration of Wearable Motion Foundation Models
- INEUS: Iterative Neural Solver for High-Dimensional PIDEs
- Inexact Bregman Sparse Newton Method for Efficient Optimal Transport
- In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
- InfCLIP: Unified Data Valuation for CLIP Pretraining via Influence-Inspired Scoring
- InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction
- Inference and estimation with unidentifiable latent treatment effects
- Inference and Uncertainty Quantification for Streaming $r$-PCA
- Inference for Many Quantiles under Local Differential Privacy
- Inference-time Alignment via Sparse Junction Steering
- Inference Time Nash Alignment
- Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
- Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
- Inference-Time Self-Aligned Drifting for Few-Step Flow Matching
- Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
- Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
- Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
- Inferring Computational Structure from Neural Recordings with Gain-Modulated Linear Dynamical Systems
- Inferring how internal brain state shapes neural responses with state-dependent diffusion models
- Inferring learning rules in deep neural network architectures from animal learning data
- InfiniteVL: A Systematic Approach to Highly-Efficient, Ultra-Long Multimodal Understanding
- InfoFlow: A Framework for Multi-Layer Transformer Analysis
- InfoNav: A Unified Value Framework Integrating Semantic Relevance and Information Gain for Zero-Shot Object Goal Navigation
- Information bottleneck dynamics during learning across artificial and biological neural systems
- Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis
- Information-Directed Offline-to-Online Reinforcement Learning
- Information Discernment in Large Language Models
- Information-Geometric Forward Policy Training in GFlowNets
- Information Loss and Disparate Effects in Network Embeddings
- Information Parity for Code: The Scope of Transfer in Multilingual Code Models
- Information Propagation via Sign-Flip Dynamics
- Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
- Information-Theoretic Generalization Bounds for Sequential Decision Making
- Information-Theoretic Generalization for Set-Input Optimization-Valued Objectives
- Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
- InformedXRD: Reproducible Benchmarks and Physics-Informed Evaluation for Powder Diffraction Symmetry Classification
- InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
- INFUSER: Influence-Guided Self-Evolution Improves Reasoning
- Inline Critic Steers Image Editing
- Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
- Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
- Inpainting physics: self-supervised learning for context-driven fluid simulation
- InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse
- In search of a definition of importance: Do attributions capture it?
- Inside Emergence: Structure-Behaviour Gaps in Language Model Training
- Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks
- Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models
- InSpect: A Curated Natural History Collection Dataset for Insect Specimen Understanding
- INSPO : Unlocking Intrinsic Self-Reflection for LLM Preference Optimization
- Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning
- Instance-Adaptive Online Multicalibration
- Instance-Dependent Bandit Convex Optimization in One Dimension
- Instance-Optimal Estimation with Multiple LLM Judges on a Budget
- Instantiation of Human Values in Image Generation
- In STeP: Speculative Tensor Parallelism for Concurrent Heterogeneous Inference of LLMs
- Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards
- Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
- Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors
- Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
- InTAct: Interval-based Task Activation Consolidation for Continual Learning
- Integral Probability Boundaries
- Integrated Imputation-Classification for Supervised Learning with Missing Data
- Integrating Background Knowledge for Scalable Causal Discovery
- Integrating digital twins with randomized experiments
- Integrating Generative and Experimental Platforms for Biomolecular Design (GEM)
- Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
- Integrating Strengths of Different Multi-Agent Workflows via Step-Aware Hybrid Topology Planning
- IntegrityBench: Can LLMs Be Trusted as Co-Scientists? A Research Integrity Benchmark
- Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
- Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving
- Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation
- Intent-Aware Caching for Efficient LLM Serving
- Intent Factored Generation: Unleashing the Diversity in Your Language Model
- IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning
- Interaction-Aligned Robot Learning from Human Videos with Structured Graph Modeling
- Interaction Value Inference for Multi-Agent Reinforcement Learning via a Hierarchical Agent-Centric World Model
- Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction
- Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
- Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems
- Inter-domain Inference for Gaussian Process Variational Autoencoders
- Interleaved Head Attention
- Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMs
- InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
- Internal Evaluation of Unsupervised Anomaly Detection Algorithms with Explanation
- Internalize External Competence for Visual Instruction Editing
- Internal Safety Collapse in Frontier Large Language Models
- Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
- Interpretability as a Science: Toward Rigorous Foundations for Understanding LLMs
- Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
- Interpretability for Discovery: Understanding and Discovering Novel Knowledge in AI Models
- Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
- Interpretable Machine Learning Evaluates Differential Therapy Effects in Parkinsonian Gait
- Interpretable Multiway-Split Trees
- Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
- Interpreting Agent Behavior (IAB): Human-Centered Interpretation for Understanding Agents, Humans, and Interaction
- Interpreting Latent Protein Language Model Features with Geometric Annotations
- Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
- Intersectional Fairness via Mixed-Integer Optimization
- Intervene3D: Intervention-Based Controlled Inference for Multimodal Perception under Partial Observability
- Intervention-Guided Image-Free Classifier Expansion for Fine-Grained Recognition
- interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
- Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data
- Intrinsically Interpretable Attention via Sparse Post-Training
- Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators
- Intrinsic Information Theoretic Analysis of ReLU Nets
- Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
- Intrinsic-Preserving Schrödinger Bridge for Direct Part-Aware 3D Generation
- Intrinsic Riemannian Cross-covariance for Manifold-valued Random Objects
- Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
- Introspection Tools Help LLMs Understand and Control Themselves
- Introspective Coupling: LMs Learn to Explain Themselves Better Than Their Training Targets
- Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
- Invariance and Body-Order Compose Additively: Minimax Rates on $\mathrm{SO}(3)^n$
- Invariant Features in Language Models: Geometric Characterization and Model Attribution
- Invariant Hyperbolic Unfolding: Radial Canonicalization for Label-Free Cross-Graph Link Prediction
- Inverse Linear Bandits via Linear Programs
- Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
- Inverse Modeling of Neural Recordings via Differentiable Biophysical Simulation
- Inverse Reinforcement Learning with Just Classification and a Few Regressions
- Inverted Detection and Control in Steering Vectors
- Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
- Inverting Retargeting: Humanoid Datasets Remember Their Operators
- Inverting the Bellman Equation: From $Q$-Values to World Models
- InvestigationWorlds: An Agentic Environment for Legal Investigation
- Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
- INVITA-WheatFieldState: A Real-World Benchmark for Crop-State Estimation in Wheat Field Trials
- I-Perceive: A Foundation Model for Vision-Language Active Perception
- IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
- I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
- IRCasDiff: Two-Stage Cascaded Diffusion for Compound Infrared Face Reconstruction
- Iris: Empowering Video MLLMs with High-Frequency Pose Priors via Spatiotemporal Binding
- IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning
- IRPO: Boosting Image Restoration via Post-training GRPO
- Irreducible Supervision Enables Compositional Generalization in Post-Training
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?
- Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
- Is a Linear Probe Evidence of a Linear Representation?
- Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
- Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
- Is Decentralized LLM Agent RL Robust to Heterogeneity? An Asymmetric Tale
- Is Dimensionality a Barrier for Retrieval Models?
- Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing
- Is Memorization Actually Necessary for Generalization
- Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies
- Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs
- Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?
- Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
- It Cancels: O(r²) Cholesky Updates for Whitened Operators
- Iterative Chow Filtering for Learning with Distribution Shift
- Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
- Iterative Gumbel Planning for Continuous Control
- Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection
- Iterative Latent Refinement for Value Learning in Offline Goal-Conditioned RL
- Iterative Nonlinear Computation Underlying Abstract Reasoning
- Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow Support
- It Just Takes Two: Scaling Amortized Inference to Large Sets
- Itô maps for any-step SDEs
- ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
- ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers
- It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs
- It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
- Jacobian Descent for Multi-Objective Optimization
- Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions
- Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
- JailBound: A FOL-Guided Jailbreak Evaluation Framework for Revealing Safety Boundaries of LLMs
- Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
- JARVIS-Bench: Benchmarking Personal Intelligence Agents on Long-Horizon Real-User Daily Traces
- JaSpec-LID: Local Intrinsic Dimension Estimation via Jacobian Spectra of ODE-based Generative Models
- JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment
- JEDI: Real-Time Jailbreak Defense for LLMs via In-Generation Detection and Intervention
- JEPAWG: Interpretable Hypernetworks for Weight-Space Physics
- Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
- JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
- JobBench: Aligning Agent Work With Human Will
- JODA: Composable Joint Dynamics for Articulated Objects
- Joint Adaptive Neighborhood Constraint for Offline Multi-Agent Reinforcement Learning
- Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness
- Joint Confounder Selection for Causal Mediation Analysis in High Dimensions
- Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization
- Joint EM Image Super-Resolution and Segmentation with Semantic and Structural Priors
- Joint Learning of Hierarchical Neural Options and Abstract World Model
- Jointly Reinforcing Diversity and Quality in Language Model Generations
- Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise
- Joint Optimization of Tool Creation and Use for Large Language Model Agents
- Joint protein, mRNA, DNA sequence design and optimization with nucleotide-level Potts models
- Joint Sequence--Vocabulary Selection for Efficient LLM Distillation
- Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- JRDB-AVR: An Active Visual Reasoning Benchmark for Real-World Embodied Environments
- JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
- JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
- Jump Start Your Policy Learning with Lessons from 145,000 Training Runs
- Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
- Just Ramp-Up: Debiasing Regression-based Estimator for A/B Tests under Network Interference
- K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
- K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos
- Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
- KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
- KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task
- Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
- Keep or Preempt? Termination-Aware Scheduling for LLM Serving with Speculative Decoding
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
- KernelDNA: Cross-Layer Kernel Sharing via Decoupled Neural Adapters
- Kernel-Gradient Drifting Models
- Kernel Granger Component Analysis for Nonlinear Directed Component Discovery
- Kernelized Activation Steering
- Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests
- Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification
- Kernel Value Regression in Offline Reinforcement Learning
- KerONet: A Single Softmax Readout Suffices for Physics-Informed Operator Learning
- KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
- KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
- Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech
- KiteNorm: Variance Regularisation for Stable and Scalable Post-LN Transformers
- KL for a KL: On-Policy Distillation with Control Variate Baseline
- KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
- Knocking-Heads Attention: Drop-in Shared Projections for Cross-Head Coordination
- KNOT: A Knowledge Entanglement Benchmark for Robust Unlearning Evaluation
- KnowEvo: Knowledge Evolution for Protein Optimization
- Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
- Knowing When Multivariate Forecasts Are Wrong
- Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
- Knowing Without Saying: How Contextual Evidence Survives but Fails to Surface in Transformers
- Knowing You before You Speak: User State Modeling for LLM-Based Personalized Dialogue
- Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents
- Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
- Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
- Knowledge Transfer Scaling Laws for 3D Medical Imaging
- Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
- KnowVis: A Dual-View Benchmark for Diagnosing World-Knowledge Grounding in Text-to-Image Models
- Know What You Need: Efficient Activation Checkpointing
- Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents
- Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
- Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting
- K-prop: Deep Online Learning by Backpropagating Temporal Kernels
- K-PWM: Control-Oriented Structured World Models under Partial Observation
- KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
- k-th Order Deep Homomorphism Networks
- KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation
- KVBuffer: IO-aware Serving for Linear Attention
- KV Cache Compression via Attention Output Distortion Minimization
- KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
- KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
- kVNN: Learnable Volterra Network Kernels
- KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
- KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
- L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
- L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education
- L2P: Unlocking Latent Potential for Pixel Generation
- Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
- Label-Free Consistency Correction for Weak-to-Strong Generalization
- LaCache: Robust Semantic Caching for LLM Serving
- LACE: Latent Alignment via Counterfactual Embeddings
- LACE: Lattice Attention for Cross-thread Exploration
- LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation
- LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
- LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
- LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
- LAMP: Language-Modulated Geometric Preservation for Multi-Modal Object Re-Identification
- LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
- Langevin-Informed Transfer Learning: Replacing the Target Samples by Black-Box Feedback
- LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
- Lang-SVG: Hierarchical Image Vectorization with Language Priors
- Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers
- Language-Based Agent Control
- Language-Conditioned World Modeling for Visual Navigation
- Language Denoising Objectives Extend the Value of Limited Data
- Language-Induced Priors for Domain Adaptation
- Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
- Language Model Memory and Memory Models for Language
- Language Models Can Coarsely Modulate Entropy Under Instruction
- Language Models Demand New Computer Science
- Language Models Need Sleep
- Laplacian Heads Improve Transformers by Smoothing Token Representations
- LAPLEX: The FFT of Learnable Laplace Kernels
- LAPrune: Logits-Aligned Scoring Proxy for KV Pruning via Vector Quantization
- LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
- Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring
- Large Language Model Failures from Hallucination to Homogenization Are Different Facets of Miscalibration
- Large Language Models as Graph Computational Solvers via Topology-aware Residual Attention
- Large language models can not and should not be banned from peer review
- Large Language Models Develop Belief State Geometry In-Context
- Large Language Model Selection with Limited Annotations
- Large Language Models Enhanced Covariate-adjusted Response-adaptive Randomization Design
- Large language models suffer from a curse of ambiguity
- Large-Scale Pretraining unlocks Few-Shot Prediction for Relational Data
- LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
- LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
- LaSA-Net: A Language-Guided Network for Outdoor Generalized 3D Referring Expression Segmentation
- LASER: Latent Space Adjoint Matching for Support Constrained Entropy Regularized Offline RL
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
- LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
- LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
- Latency-Conditioned Selection Bias in RLHF
- Latent Abstraction for Retrieval-Augmented Generation
- Latent Action Reparameterization for Efficient Agent Inference
- Latent Barrier Steering: Hierarchical Safety for Generative Planning
- Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary Decisions
- Latent Generative Solvers for Generalizable Long-Term Physics Simulation
- Latent Introspection: Models Can Detect Prior Concept Injections
- Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
- Latent Motion Alignment for Video Diffusion
- LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
- Latent Process Generator Matching
- Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
- LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
- Latent Reasoning in Continuous Space for Unified Multimodal Models
- Latent Refinement Decoding: Enhancing Diffusion Language Models by Refining Belief States
- Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
- LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
- Latent-space Attacks for Refusal Evasion in Language Models
- Latent Spatial Reasoning: Building Innate 3D Awareness via Latent-Space Distillation
- LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
- Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
- LAtte: Hyperbolic Lorentz Attention for Joint-Subject EEG Classification
- Lattice Deduction Transformers
- Layer Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
- Layer Precision Reduction for Deep Anomaly Detection
- Layerwise LQR for Geometry-Aware Optimization of Deep Networks
- Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
- Layout Before Pixels: Topology-Anchored Transcriptome-to-Histology Generation
- LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan Generation
- LCD$^3$: Layout-Conditioned Diffusion for Dataset Distillation in Object Detection
- LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection
- LDM-is-AE: Latent Diffusion is an Intrinsic Auto-Encoder for End-to-End Image Generation
- LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models
- LeAct: Learning to Reason from Expert Actions
- Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation
- LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
- LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces
- Leakage Thresholds for Sandwich Equilibria Under Partial Information
- Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks
- Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
- Leaner transformers can easily learn to cluster
- LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning
- Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
- LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
- LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models
- Learnable Chernoff Baselines for Provable Inference-Time Alignment
- Learnable Diffusion-based Positional Encodings for Link Prediction
- Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
- Learnable Spectral Activations
- Learned Lagrangian Models of PDEs via Euler–Lagrange Residual Minimization
- Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
- Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
- Learn from your own latents and not from tokens: A sample-complexity theory
- Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances
- Learning Actionable Information Landscapes for Multimodal Active Sensing in Hawkmoths
- Learning Active Perception and Manipulation via Spatio-temporal Visual Memory
- Learning Agentic Policy from Action Guidance
- Learning Agentic World Vision-Language-Action Models for Autonomous Driving
- Learning a Maximum Entropy Model for Visual Textures using Diffusion
- Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification
- Learning a Trajectory-Geometric Condition from Reasoning for VLA Planning
- Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
- Learning-Augmented Coordination Mechanisms
- Learning Augmented Exact Exponential Algorithms
- Learning-Augmented Mechanism Design for Facility Location under $L_p$-Norm Social Costs
- Learning-Augmented Online Portfolio Selection: Optimal Robustness-Consistency Tradeoffs
- Learning-Augmented Online Scheduling with Parsimonious Preemption
- Learning-Augmented Streaming Algorithms for Approximating Boolean Max-CSPs
- Learning a Unified Cross-Model Semantic Dictionary via Gated Bottleneck Sparse Autoencoders
- Learning Better Certified Models from Empirically-Robust Teachers
- Learning Biological Hierarchies in Single-Cell Foundation Models
- Learning Causal Orderings for In-Context Tabular Prediction
- Learning Chance-Constrained MDPs with Bellman Distributional Certificates
- Learning CLI Agents with Structured Action Credit under Selective Observation
- Learning Collision‑Free Dispatch Policies for Route‑Wise Decision‑Dependent Anomaly Detection
- Learning Compositional Latent Structure with Vector Networks
- Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning
- Learning Continuously Evolving Spatio-Temporal Explanations for Traffic Flow Forecasting
- Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving
- Learning Cultural Vectors for Cross-Cultural Generation
- Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness Regularization
- Learning Density Operator Latent Variable Models via Quantum Information Projection
- Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
- Learning Digital Twins under Drift: Optimal Tracking Rates for Non-Stationary Dynamical Systems
- Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance
- Learning Distributions from Multiple Data Providers
- Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation
- Learning Dynamic Evidence Routes for Vision Transformer Probing
- Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
- Learning Event-to-Field Operators Without Interpolation
- Learning Evidence Highlighting for Frozen LLMs
- Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions
- Learning Fractional-Order Dynamics from a Single Trajectory
- Learning from Disagreement: Maximum Divergence Knowledge Distillation
- Learning from Disagreement: Multi-Teacher Distillation for Chinese Spelling Correction
- Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory
- Learning from Language Feedback via Variational Policy Distillation
- Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
- Learning from the Self-future: On-policy Self-distillation for dLLMs
- Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
- Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard
- Learning Generalizable Hand-Object Tracking Control without Human Demonstrations
- Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints
- Learning Global Probabilistic Explanations
- Learning Global Temporal Dynamics in Sparse Networks via Cycle Counts
- Learning Hierarchical Forward Processes For Discrete Diffusion Language Models
- Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
- Learning How to Cube
- Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation
- Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
- Learning in Causal Markov Games
- Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
- Learning inexact alternating minimization
- Learning Informative Invariant Representations via Hierarchical Latent Decomposition
- Learning in Policy Transparency Games: Wedge Structure and Adaptive Certification
- Learning interpretable Schur forms of recurrent weight matrices
- Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space
- Learning Joint Semantic-Geometric Uncertainty for Structured Prediction with Closed-Loop Calibration
- Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
- Learning Latency-Aware Orchestration for Multi-Agent Systems
- Learning Lotteries with Minimal Violations from Membership Queries
- Learning Menu-Based Mechanisms for Truthful Budget-Feasible Procurement
- Learning Minimal Sufficient Evidence Graphs for GraphRAG via Nash-Guided Optimization
- Learning Modular Addition with Auxiliary Modulus
- Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems
- Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
- Learning Neuronal Wiring Rules from Morphological Token Sequences
- Learning Optimal Transport Plans Via Autoregressive Token Regression
- Learning Options for Compositional Motor Control with Adapter Banks
- Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
- Learning Orthonormal Bases for Function Spaces
- Learning Pareto Stationary Fronts via Single-Pass Backpropagation
- Learning Planning Budgets in Real-Time RL
- Learning Polyhedral Conformal Sets for Robust Optimization
- Learning POMDP World Models from Observations with Language-Model Priors
- Learning Preference Representations for Preference-Conditioned Image Generation
- Learning Process Rewards via Visitation Matching for Efficient RL
- Learning Provable Neural Network Observer for Uncertain Dynamical Systems
- Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
- Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex Functions
- Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
- Learning Rate Transfer for Hybrid Transformer-SSM Architectures
- Learning Rate Transfer in Normalized Transformers
- Learning Reach-Set Geometry for Tighter Probabilistic Neural Network Verification
- Learning Recoverable Neural Networks against Weight Corruption via Simple Zero-Sum Projection
- Learning Reusable Motor Motifs for Continuous Animal Behavior Modeling
- Learning Reusable Options by Decomposing Neural Policies
- Learning Reveals Invisible Structure in Low-Rank RNNs
- Learning Robust Reasoning through Guided Adversarial Self-Play
- Learning Robust Representations for Defending White-Box Adversarial Attacks in Continual Learning
- Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
- Learning Scene-Grounded Interaction Priors for Scene-Aware Human Motion Prediction
- Learning Semantic Consistency for Open-Vocabulary Dense Perception
- Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
- Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding
- Learning Spectral Compositional Koopman Operators for Global-to-Regional Weather Forecasting
- Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data
- Learning Survival Models with Right-Censored Reporting Delays
- Learning Task-Centric World Models from Visual Foundations
- Learning the Committor Function using Weighted Ensemble Simulations
- Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models
- Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity
- Learning the Signature of Memorization in Autoregressive Language Models
- Learning through Internalization
- Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
- Learning to Ask: Metacognitive Action Policy for Large and Small Language Model Collaboration
- Learning to Audit ML Models with Theory of Mind
- Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
- Learning to Commit: Next-Commit Prediction via Online Supervised Contrastive Reflection
- Learning to Complete Extremal Mathematical Structures
- Learning to Continually Learn via Meta-learning Agentic Memory Designs
- Learning to Correct Geometry in Generated Videos
- Learning to Cut: Reinforcement Learning for Benders Decomposition
- Learning to Deaggregate: Large-scale Trajectory Generation with Spatial Priors
- Learning to Decide with AI Assistance under Human-Alignment
- Learning to Discover Iterative Spectral Algorithms
- Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable
- Learning to Drive in New Cities Without Human Demonstrations
- Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs
- Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
- Learning to Follow In-Context Watermark Instructions via Self-Distillation
- Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
- Learning to Generate Multiple Objects from Dense and Occluded Layouts
- Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs
- Learning to Inject: Automated Prompt Injection via Reinforcement Learning
- Learning to Learn from Multimodal Experience
- Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation
- Learning to Persuade a Biased Receiver
- Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
- Learning to play with spikes. Characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
- Learning to Price with Persuasion
- Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
- Learning to Recommend in Unknown Games
- Learning to Sample From Diffusion Models via Inverse Reinforcement Learning
- Learning to Search, Searching to Learn: A Closed-Loop Framework for Large-Scale Vehicle Routing
- Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual Representations
- Learning to Solve Compositional Geometry Routing Problems
- Learning to Solve Generative ODEs Beyond the Linear Span
- Learning to Surpass: Training Tool-Using Agents with Anchored Feedback
- Learning to Synergize Textual and Visual Prompts for Fine-Grained Traffic Element Detection in HD Maps
- Learning to target with network interference
- Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
- Learning to Undo: Transfer Reinforcement Learning under State Space Transformations
- Learning Transferable Cross-Day Representations for Few-Shot Neural Decoding
- Learning Transferable Representations from Operating System Entities via Provenance Graph Distillation
- Learning Unbiased Permutations via Flow Matching
- Learning under Localized Minority Imbalance
- Learning Visual Feature-Based World Models via Residual Latent Action
- Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
- Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
- Learning What Evaluators Value: A Reliable Approach to Modeling Evaluator Preferences
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness
- Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics
- Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
- Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
- Learning What to Remember: Test-Time Training via Context Distillation
- Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
- Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion
- Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
- Learning When to Think: Adaptive Internal Computation for Reinforcement Learning
- Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
- Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
- Learning When Visual Context Matters for Mouse Behavior Analysis
- Learning Where and What to Restore for Composite Image Restoration
- Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
- Learning Where to Look: Observation Policy Optimization for Thinking with Images
- Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
- Learning with Enumeration: Neural-Guided SAT Framework for Cryptographic Key Recovery
- Learning with Multiple Correct Answers - Regret Bounds under Different Feedback Models
- Learning with Synthetic Data via SGD in High-Dimensional Linear Regression
- Learn Locally, Recurse Globally: Neural Circuit Synthesis Beyond Training Depth
- Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
- LeCellModel: Interpretable Density Estimation over the Gene Expression Manifold
- Ledger: A Path-Validated, Database-Grounded Benchmark for Enterprise Web Agents
- Leech Lattice Vector Quantization for Efficient LLM Compression
- LEGO: Sizing Rules for Budget-Aware Dense-to-MoE Conversion of Vision-Language Models
- LEIA: Learned Environment for Interactive Architected Materials
- Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents
- LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling
- Length Generalization for Transformers via Compression
- LensCT: Fine-Grained AI-Involved Text Detection via Temporal-Hierarchical Tomograms of LLM Internals
- LensDesigner: A Self-Improving Agent for Optical Lens Design
- LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
- LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
- Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
- Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
- Less is More: Compact-Token Masked Feature Learning for Skeleton Representation Learning
- Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More Generalizable
- Less Language, More Latents: Annotation-Efficient VLAs for Driving
- LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field Representations
- Less Structure is More: Minimal Representations for Supervised Learning
- Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
- Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
- LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics
- Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
- Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
- Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
- Leveraging Latent Visual Reasoning in Silence
- Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling
- Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
- Leveraging unlabelled data for generalizable neural population decoding
- Leviathan: Decoupling Input and Output Representations in Language Models
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark
- L-Flow: Longitudinal Flow Matching for Progression-Aware Speech Biomarker Modeling
- LG-Bench: A Graph-Structured Evaluation Benchmark for Life Science
- Liars' Bench: Evaluating Lie Detectors for Language Models
- LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
- LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
- LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
- LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
- Lie Generator Networks for Nonlinear Partial Differential Equations
- LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance
- Lifting Biomolecular Data Acquisition
- LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
- LiFT: Likelihood-Free Tree-Structured Policy Optimization for Flow-Based VLAs
- Lift, See, Act: Hierarchical Robot Policy Pretraining with 3D Foundation Models
- LIGHT: Deployable Small Foundation Models
- LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing
- Likelihood-Free Generative Policy Optimization
- Likelihood-free inference of phylogenetic tree posterior distributions
- LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling
- Limits and Potential of Score-Based Data Valuation: Redundancy, Complementarity, and Non-Monotonicity
- LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing
- Linear approximations to HMM filtering
- LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
- Linear Contextual Bandits with Quasi-Optimism
- Linear Ensemble Sampling with Fewer Ensembles
- Linear Regression Under Misalignment: Algorithms and Theoretical Results
- Linear-time rule mining under formal guarantees
- LINE: LLM-based Iterative Neuron Explanations for Vision Models
- Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
- LINK: Learning to Localize from Known to Unknown Scenes
- LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
- LIPAR: Latent Inter-Frame Pruning with Attention Recovery
- Lipschitz Dueling Bandits over Continuous Action Spaces
- LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
- Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
- Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models
- ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models
- Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
- LITE: A Lightweight Lazy Sampler for Efficient SGD
- LiteNav: Lightweight Map-free Outdoor Visual Navigation
- Literati: Towards Anytime Optimal Shape Generalized Trees via AO*
- LITHE: Lattice-Indexed Twin Hadamard Encoding for Diffusion Personalization
- LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
- LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
- LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
- Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
- LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs
- LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
- LLM-ACES: Closed-Loop Discovery of Dynamic Systems with LLM-Guided Adaptive Search
- LLM Active Alignment: A Nash Equilibrium Perspective
- LLM Agents Already Know When to Call Tools - Even Without Reasoning
- LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
- LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
- LLM-Auction: Generative Auction towards LLM-Native Advertising
- LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
- LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
- LLM-enabled Applications Require Systematic Threat Monitoring
- LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning
- LLM Flow Processes for Text-Conditioned Regression
- LLM Is a Good Conditioner: End-to-End Sign Language Video Generation with VQ-Diffusion
- LLM Judge Validation Under Sparse Overlap: From Inference to Design
- LLM Rheology: Auditing Refusal Geometry in Aligned Language Models
- LLM Routing Through the Lens of Recommendation: A Roadmap for Efficient AI Orchestration
- LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation
- LLMs can construct powerful representations and streamline sample-efficient supervised learning
- LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
- LLMs Keep Thinking When Told Not To
- LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference Acceleration
- LLMs Show No Signs Of Individuated Metacognition
- LLM-WikiRace: A Benchmark for Planning and Reasoning over Real-World Knowledge Graphs
- Load Balancing Mixture of Experts with Similarity Preserving Routers
- LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency
- Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization
- Local Gaussian Processes on Compact Lie Groups
- Local–Global Sparse Autoencoders for Multiscale Interpretability in Vision Models
- Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions
- Local-Interaction Learning Dynamics: A Markov Random Field Framework for Convergence of Deep Neural Network Learning
- Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
- Locality-Controlled OOD Guidance for Robust Regulatory DNA Sequence Design
- Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation
- Localize Any Object in X-Ray Security Scans without Human Annotation
- Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
- Localizing and Repairing Sparse-Prompt Failure in SAM Decoders via Box-to-Point Counterfactual
- Localizing Concepts in Visual Autoregressive Models
- Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values
- Local linear convergence of gradient methods for overparameterized Gaussian mixtures
- Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization
- Local Manifold Identification with Latent Linear Models and OT Flows
- Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning
- Local Sparsity Enables Unsupervised LLM Safety Detection
- Locating and Repairing Domain Shift in VLM Trajectory Planning
- Locking Pretrained Weights via Deep Low-Rank Residual Distillation
- LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
- LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition
- LOCU: Löwdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
- LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
- Logarithmic Depth Suffices for In-Context Gradient Descent
- Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space
- Logical Distillation of Transformer Encoders
- LogicDirector: Enforcing Temporal Composition in Text-to-Video Generation
- LogicSR: A Unified Benchmark for Logical Discovery from Data
- LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
- Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs
- Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
- Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
- Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text
- LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
- LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
- LogT: Logically Think with Images for Visual Search
- LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
- LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
- Long-Context Generation Is a Sampling Problem
- Long-Context Language Models Require Extreme Sparsity in Context Dimension
- Long-Horizon Agency Belongs in the Harness, Not the Context Window Only
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
- Long-Lived AI Agents Age Too: They Quietly Decay After Deployment
- LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
- Long-Range Spatio-Temporal Graph Propagation Through Oscillations
- Long-Rollout Stability in AI Weather Models: A Quantitative Benchmark and Analysis
- LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
- LongSCOP: Semantically Consistent Long Video Outpainting
- LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
- Long-Term Composition of Human-Object Interactions
- Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models
- Long-Term Risks of Risk-Based Allocation
- Long Video Instructional Editing in the Wild
- Look-ahead Variational Flow for Generative Online Reinforcement Learning
- Lookalike3D: Seeing Double in 3D
- Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
- Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
- Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
- Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits
- Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics
- LookThere! Sparse Vision by Reinforced Selection
- LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
- Loop alignment: Self-organized Weight Transpose in Predictive Coding through Independent Hebbian Plasticity.
- Looped Diffusion Language Models
- Looped Transformers with Layer Normalization Provably Learn the Power Method
- Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery
- LoopNav: Benchmarking Spatial Consistency in World Models
- LoopPrune: Evolutionary Module Selection with Iterative Execution for Efficient Large Language Model Compression
- LoopRPT: Reinforcement Pre-Training for Looped Language Models
- LoopWeaver: Weaving Feedback Loops into Hierarchical Generation under Constraints
- LoRAcles: Self-Supervised Weight-Space Interpretability at Scale
- LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
- LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
- LoRAtorio: An intrinsic approach to LoRA Skill Composition
- LoReC: Rethinking Large Language Models for Graph Data Analysis
- LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
- LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
- Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning
- Lost in the Slots: Revisiting Object-Centric Representations in the era of Foundation Models
- Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
- Lost on Campus: Evaluating Embodied Spatial Reasoning of Vision-Language Models in the Wild
- Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
- LOTION: Smoothing the Optimization Landscape for Quantized Training
- Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
- Lower-Level Agnostic Bilevel Optimization
- Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
- LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression
- Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
- Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models
- LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
- LP-RAG: Learning to Retrieve with Link Predictors
- LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
- LR-V2X: Loss Resilient Collaborative Perception under Low-Bandwidth Communication
- LSC-Parlament: An Automatically Aligned Catalan Sign Language Dataset from Parliament Videos.
- LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models
- LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
- Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
- LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
- Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks
- LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection
- M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
- M$^3$: Reframing Training Measures for Discretized Physical Simulations
- M$^\star$: Every Task Deserves Its Own Memory Harness
- M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
- M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection
- M3-HNTM: Hyperspherical Multimodal Topic Modeling with Symbolic and Contextual Evidence
- M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
- Machine Learning-Driven RAG System Design
- Machine Learning for Simulations in Biology and Chemistry - The 2nd SIMBIOCHEM Workshop
- Machine Learning for Spatially Resolved High-dimensional Biology
- Machine Unlearning in Diffusion LLMs
- Machine Unlearning in Low-Dimensional Feature Subspace
- Macrocanonical Generator Networks: data-efficient neural surrogates for amortized physics simulation
- MACRO: Training-free Multi-plane Attention for Closeup Render Optimization
- MAdam: Metric-Aware Multi-Objective Adam
- MAEB: Massive Audio Embedding Benchmark
- MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
- MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
- MAGE: Towards Generalizable Multi-timescale EEG Representations
- Magnetic Resonance Unpaired Image Translation with Pseudometric Schrödinger Bridges
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
- Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension
- Magnitude-preserving Layers Enable Efficient GANs
- MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
- MainFL: Intertemporal Data Valuation for Robust Auction-based Federated Learning
- Majority Bit-Aware Watermarking for Large Language Models
- Majority-of-Three is an Optimal PAC Learner
- Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
- Making LoRA Identifiable: Orthogonal Alignment for Continual Learning
- Making Open-Source Text LLM Watermarks Durable Against Merging
- Malicious Node Injection: A Transferable Adversarial Attack on GNN Fairness
- Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
- Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields
- MammoGPS: A Benchmark for Visual Grounding, Perception, and Spatial Reasoning in Mammography
- M*: A Modular, Extensible, Serving System for Multimodal Models
- MAMQ-Net: A Robust Framework Leveraging Multi-level Tamper-aware Queries and Complementary Representations of Tampering Features for Progressive Image Forgery Localization
- Managing Agents that Manage Agents: Workshop on Responsible Use of Meta-Agents that Build, Optimize, and Supervise Other Agents
- Managing Self-Learning Experts under Per-Round Budget Constraints
- MANGO:Multi-Angle Neural Gated Operators for Chirp-Perturbed PDEs
- Manifold-Aligned Adversarial Perturbation for Anti-Customization under Diffusion-based Purification
- ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching
- Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
- Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps
- Manifold-Guided Stereo-Monocular Refinement for Endoscopic Stereo Disparity Estimation
- Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction
- Manifold Random Features
- Manifold Sampling via Entropy Maximization
- Manifold-weighted neural networks
- ManiFusion: Unlocking High-Throughput Generation via Superposition in Manifold Space
- ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
- ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
- ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making
- Many Benign Errors are Better than A Few Severe Ones: Evaluating Hallucination Severity
- Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery
- Map-Guided Caching: A Global Perspective for Efficient Diffusion Transformer
- MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
- MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
- MapPFN: Learning Causal Perturbation Maps in Context
- Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
- MapPolicy: Structure-Aware Imitation Learning for Robot Manipulation via Physically Constrained Scene Map
- MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
- MapShift: Controlled Post-Intervention Evaluation for Embodied World Models
- MAPS: Margin-Aware Priors and Verifier-Guided Search for Embodied Planning
- MARBLE: an Agent Benchmark for Spatial Reasoning and Visual Abstraction
- marc.jourdan@epfl.ch
- Marginal-Nonuniform Multiclass Learning
- Margin Dynamics for Large Language Model Alignment
- MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
- Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
- Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems
- Market Incentives for AI Safety Investment
- Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
- MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
- Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dyanmics Manifolds
- Markovian Experimental Design under Concept Drift
- Markov Metrical Task Systems
- MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
- Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
- MARS: Enabling Autoregressive Models Multi-Token Generation
- MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search
- MARS: Multi-resolution Adaptive Routing for Sequential Recommendation
- Martine: Benchmarking Multi-View 3D Surface Reconstruction Across Viewpoint Coverage, Resolution, and Lighting
- MaSC: A Masked Similarity Metric for Evaluating Concept-Driven Generation
- Mask-Conditioned Gradient Masking for Fine-Tuning Mixture-of-Experts Diffusion Language Models
- Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
- Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
- Masked Diffusion Vision-Language Models for Temporal Action Localization
- Masked Generative Pretraining Improves Cross-Dataset Transfer in Pixel-Space Diffusion
- Masked Sobolev Training for Feasibility-Reliable Optimization Proxies
- Masked Visual Actions for Unified World Modeling
- MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
- MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation
- Massively Parallel Exact Inference for Hawkes Processes
- MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Protocol Modeling and Analysis
- MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
- MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training
- Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
- Matched-Control Tests of Partition-Source Claims in One Routed Distillation Family
- MatchEx: Model-Level GNN Explanations with Multi-Granular Insights
- Matching2Matching: Zero-Shot Light Field Image Denoising with Matching View Construction
- Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
- Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment
- Match the Geometry, Skip the Surrogate: Extreme Low-Budget Optimization in High Dimensions
- MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning
- MaterialsPilot: An Execution-Feedback Framework for Generative Design of Complex Atomistic Architectures
- MaterialsSaddles: 34 Million Transition States and a Flow-Matching Saddle-Point Predictor for Materials
- MATH-AI: The 6th Workshop on Mathematical Reasoning and AI
- MathCD: A Benchmark Dataset for Cognitive Diagnosis with Semantic Information
- MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries
- MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
- Matrix-Free Natural Gradient via Stochastic Truncated Metrics
- Matrix-Free Stochastic Training of Low-Rank Spectral Graph Learning via Randomized Adaptive Spectral Estimation
- Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors
- Matryoshka Transcoders and Hierarchy Misalignment: When SAE Absorption Protection Does Not Transfer
- Maximin Robust Bayesian Experimental Design
- MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
- MaxSketch: Robust Distinct Counting in Streams via Random Projections
- MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
- MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving
- MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing
- MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
- MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process
- MCM-DM: Towards Better Spatio-Temporal Event Representation Learning via Discrete Morse Theory
- MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
- MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
- MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
- MCSplat: Multi-View Photometric and Geometric Consistent Feed-Forward Gaussian Splatting for Driving Scenes
- MDK-MoE: Multi-view Decomposed Kalman Mixture of Experts Framework for Non-stationary Time Series Forecasting
- MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation
- MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
- Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
- Mean-Field Parallel Decoding for Discrete Diffusion Language Models
- Mean Testing under Truncation beyond Gaussian
- Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition
- Measure-to-measure Regression with Transformers
- Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
- Measuring and Decomposing Mode Separation via the Canonical Diffusion
- Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
- Measuring and Strengthening Behavioral Suppression in Language Models
- Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
- Measuring Coherence in Predictive Models
- Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
- Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
- Measuring Layer-wise Intrinsic Dimensionality of FFNs in LLMs via PCA
- Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model on a Collision-Detection Task
- Measuring Safety Alignment Effects in Autonomous Security Agents
- Measuring Weak-to-Strong Legibility of Reasoning Models
- Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
- Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
- Mechanism Design for AI Overviews: Creator Incentives and Long-Term Profit
- Mechanism-Level Chemical Reaction Simulation with Electron Bookkeeping Transformer
- Mechanisms of Misgeneralization in Physical Sequence Modeling
- Mechanistic Circuit Identification for Controllable Data Generation
- Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration
- Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching
- Mechanistic Interpretability Needs Philosophy
- Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
- Mechanistic Interpretability with Sparse Autoencoder Neural Operators
- Mecha-nudges for Machines
- MechParser: A Vision-Language Framework for Parsing Chemical Reaction Mechanism Diagrams
- Med-Agentic: Distilling Agentic Medical Reasoning with Internalized Meta-Capabilities
- MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video Generation
- MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
- MedFlowBench: Auditing Medical Agents in Full-Study Workflows
- MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
- MedHEB: Benchmarking Medical Embeddings Across Heterogeneous Clinical Evidence
- MedHorizon: Towards Long-context Medical Video Understanding in the Wild
- Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization
- Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search
- Medical Reasoning with Multimodal Foundation Models
- MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning
- MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
- MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
- MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
- MedPsy: State‑of‑the‑Art Small Medical Language Models for Efficient Edge Deployment
- MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence
- MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
- MedVTok: A General-Purpose Medical Visual Tokenizer
- MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
- MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
- MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
- MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
- Membership Inference on Synthetic Single-Cell Genomic Data
- Membrane Sensitivity and Deployment Fragility of Learnable Time Constants in Spiking Neural Networks
- MemCode: Discrete Semantic Representations for Long-Term Agent Memory
- MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
- MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory
- MemDLM: Memory-Enhanced DLM Training
- MemeEconomy : Do LLM Agents Trade Ethics for Survival?
- MEME: Lightweight Hierarchical Mixture-of-Experts for Unified Affective Computing
- MEME: Multi-Entity & Evolving Memory Evaluation
- Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization
- MEMEVO: A Memory-Evolved Video Agent for Long Video Understanding
- MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
- MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
- Memoir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing
- Memorization Is Folding: Topological Signatures of Noisy-Label Learning
- Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
- Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
- Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
- Memory-Driven Contrastive Embedding Enhancement for Fine-Grained Open-Set Semi-Supervised Learning
- Memory-Efficient Federated Fine-Tuning of LLMs via Block-wise Progressive Training
- Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
- MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion
- Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
- Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
- Memory is Not Search: Towards Proactive, Lifelong Memory in AI
- Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- Memory Retrieval for Changing Preferences
- Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
- MemPilot: Learning Transferable Latent Memory Mechanisms for LLM Reasoning
- MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
- MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
- MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
- MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
- MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
- MENDR: Manifold-Embedded Neural Data Representations for Channel-Agnostic EEG Foundation Modeling
- Mental Health AI Must Move Beyond Diagnostic Prediction and Chat-Based Support: Toward Perspective-Aware, Multisensory Co-Experience
- MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
- Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning
- Mental-Models for Multi-Agent Systems
- Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology
- Merging RLVR-Trained Experts via Policy-Shift-Guided Spectral Alignment
- Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
- MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
- Mesh-Free Convolution: Learned Spectral Attenuation and Transport
- Mesh Invaiant Infinite Dimensional Adaptive MCMC for Latent Gaussian Processes
- MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
- MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement
- Meta$^n$: Recursive Self-Improvement through Emergent Depth
- MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network
- Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
- METAFORGET: Audit-Driven Update-Policy Learning for Reliable Language Model Unlearning
- Meta Inverse Prompting for Video Generative Models
- MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
- Meta-Learning Preferences for Multilingual LLM Alignment
- MetaLoop: Benchmarking the Full Metacognitive Loop in LLMs
- Meta-memorization and memorization scaling laws in transformers
- META-PAP: Meta-learning for Prompt-aware Preference Pairing in LLM Alignment
- Metaphor Is Not All Attention Needs
- MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks
- Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning
- Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning for T2I Generation in Unified Multimodal Models
- METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
- Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts
- METRO: Metric-Enhanced Token Routing Operator
- Metropolis-Adjusted Diffusion Models
- Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
- MEV: A Multi-Event Video Dataset for Long-Take Generation
- MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
- MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory
- MHWA: Multi-timescale Hierarchical World-Action Model
- MICA: Activation Checkpointing for Double-Backward Training of Machine Learning Interatomic Potentials
- MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior
- MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-Resolution
- Microstructure Descriptor Fields as Supervision for Scientific Images
- MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph
- MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
- Midpoint Generative Models
- Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
- MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
- MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation
- Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
- MIND-DDI: Multi-Omics Interpretable Drug-Drug Interaction Prediction with Joint Optimization of Graph Structure, Neural Architecture, and Symbolic Rules
- MindGames:A Multi-Agent Benchmark and Trajectory Dataset for Evaluating Social and Strategic Reasoning in LLMs
- MindGuard: Guardrail Classifiers for Multi-Turn Mental Health Support
- MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis
- MIND: Monge Inception Distance for Generative Models Evaluation
- MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI
- Mind the Gap: Dataset and Fine-grained Evaluation for Inline Audio Descriptions
- Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
- Mind the Gap: The Divergent Rebound Dynamics of Diffusion and Autoregressive Model
- Mind the Heads: Topological Representation Alignment for Multimodal LLMs
- Mind the Parameters: Lightweight and Efficient Brain Visual Decoding with Shared Tensor Cores
- MindVLM: Neural-Grounded Visual Captioning via Subject-Aware Semantic Evidence Selection
- MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
- MINEGRID: A Multi-Modal Benchmark for LLMs Evaluation on Dynamic Modeling of Power Systems
- MinerU2.5-Pro: Pushing the Limit of Document Parsing via a Calibrated Evaluation-Data Flywheel
- Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions
- Mini-batch kernel $k$-means
- Minimally Invasive Steering of Language Models
- Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
- Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport
- Minimax Optimal Kernel Two-sample Testing in Sub-quadratic Time
- Minimax-Optimal Transformer Classification for Functional Data with Dense-Sparse Phase Transition
- Minimax Optimal Two-Sample Testing under Local Differential Privacy
- Minimax Optimization without Spurious Solutions in Optimal Transport Learning
- Minimax Private Estimation of Smooth Optimal-Transport Maps
- Minimax Rates and Spectral Distillation for Tree Ensembles
- Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM
- Mining Logic under Uncertainty: Probabilistic Soft Logic with Energy-Based Inference for Chain-of-Thought Verification
- MiniPIC: Flexible Position-Independent Caching in <100LOC
- Min-Max Optimization Requires Exponentially Many Queries
- MinMax Recurrent Neural Cascades
- MinPath: Learning Efficient LLM Reasoning via Minimal Dependency Paths
- MinSteer: Minimal-Pair Steering via Two-Stage Cached Continuation
- MINT: Meeting-time INdicators for Truncation in Multi-Step Off-Policy RL
- MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding
- MIRAGE: Duality-Inspired MILP Augmentation for Representation Learning
- MIRAGE: Hierarchical MI-Surrogate Regulation for Graph Contrastive Learning
- MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
- MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
- MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
- MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
- Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence
- Mirror Descent-Ascent for mean-field min-max problems
- Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
- MIRROR: Manifold Ideal Reference ReconstructOR for AI-Generated Image Detection
- Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
- (Mis)generalization of Helpful-Only Fine-Tuning
- Missing data and cluster graphs: cluster-level missingness vs variable-level missingness
- Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
- Mission Impossible: Diagnosing and Fixing Non-Operative Instruction Following in Image Editing
- MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series
- MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
- Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
- Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow Matching
- Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning
- Mitigating Data Heterogeneity Effect in Client-Reshuffling-Based Federated Learning
- Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
- Mitigating Knowledge Conflicts in Retrieval-Augmented Generation via Inference-Time Representation Editing
- Mitigating Label Bias with Interpretable Rubric Embeddings
- Mitigating Memorization Where It Happens
- Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting
- Mitigating Overgeneralization in RND via Spectral Target Design
- Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
- Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
- Mitigating Retaliatory Algorithmic Collusion in Repeated Games
- Mitigating Reward Hacking via Task Representations
- Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception
- Mixed-Curvature Geometric Latent Diffusion Model for Graph Generation
- MixForensics: Blend Before You Encode for Generalizable AI-Generated Video Detection
- MixNLQ: An Effective Post-Training Nonlinear Low-Bit Quantization Method for Large Language Models
- Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models
- MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing
- MixScentNet: A Multiscale Graph-based Framework for Predicting Scent Mixture Perception
- Mixture of Activations: Token-Adaptive Mixing for Expressive Feedforward Layers
- Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval
- Mixture-of-Chains: Learning Causal Graphs from Human Knowledge
- Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
- Mixture-of-Experts for Online Matrix Completion on a Drifting Union of Subspaces
- Mixture-of-Hierarchical Experts: Optimized Mamba Architecture for Vision Diffusion
- Mixture of Layers: Dynamic Layer Routing for Visual Reasoning
- Mixture of Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing
- Mixture-of-Top-$k$ Attention: Efficient Attention as Scalable Fast Weights
- Mixture-Trained Merging for Unified Multi-Objective Models
- MixUni: Joint Multi-Property Prediction for Chemical Mixtures with Physics-Informed Heads
- MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
- MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
- ML-assisted Randomization Tests for A/B Experiments
- ML Configuration Artifacts Should Be Closed Under Review
- ML for Systems
- MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing
- MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
- MLLM Makes Strong Backbone for Multi-Modal Object Detection
- MLLMs Fail to Refuse when Using Tools Agentically
- MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
- MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation
- MMCompass: Diagnosing Position Bias in Generative Multimodal Reward Models
- MMDiff: Multimodal Model Diffing for Feature Discovery and Control
- MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs
- MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
- MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
- MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
- mmLIP: mmWave Radar-Language Interactive Pretraining via Point Confidence
- MMLongCite: A Benchmark for Evaluating Faithfulness of Long-Context Vision-Language Models
- MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
- MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos
- MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models
- MMSkills: Towards Multimodal Skills for General Visual Agents
- MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
- MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support
- MobileMoE: Scaling On-Device Mixture of Experts
- MobileWan: Closing the Quality Gap for Mobile Video Diffusion
- Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement
- MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
- MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection
- MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic
- MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
- MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting
- MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes
- Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
- Modality-Depth Routing for Visual Reasoning in VLM Post-Training
- Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
- Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
- Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP
- Model-Aware Tokenizer Transfer
- Model-based Bootstrap of Controlled Markov Chains
- Model-Based Online Decision Making via Generative Trajectory Planning
- Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
- Model Cascades with Provable Per-Class Quality
- Model Collapse is a Singular Complexity Trajectory
- Model Distribution-Aware Multimodal Dataset Distillation
- Model-Free Assessment of Simulator Fidelity via Quantile Curves
- Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning
- Model Immunization Beyond Condition Numbers: The Importance of Plateau Regions
- Model Incrimination: Investigating Whether Concerning Behavior Reflects Misalignment
- Modeling quantum neural network gradient with reinforcement learning
- Modeling the Vividness of Imagined Natural Scenes Reveals a Model-Common Image-Level Component in Vision Models
- Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields
- ModelLens: Finding the Best for Your Task from Myriads of Models
- Modelling Opinion Dynamics at Scale with Deep MARL
- Models Designed to Forget: Machine Unlearning via Key Deletion
- Model Spec Midtraining: Improving How Alignment Training Generalizes
- Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
- Models That Know How Evaluations Are Designed Score Safer
- Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
- MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion
- Module-Aware Optimization for Graph Neural Networks
- Module Specialization in Transformer Factual Recall under Correlated Fact Distributions
- MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario
- MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs
- MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
- Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
- MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
- MolSpecFlow: Modality-Incomplete Molecular--Spectral Learning for MS/MS
- MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
- Moment-Constrained Latent Steering for Flow Policy
- Momentum Smooths the Path to Gradient Equilibrium
- MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
- MonarchRT: Efficient Attention for Real-Time Video Generation
- MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
- Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
- Monitoring Violations of Differential Privacy over Time
- MonoChunk3D: Monocular Online 3D Instance Segmentation with Persistent Instance States
- Monoculture Robust Learning
- MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
- Monotone Inclusion Approach to Weakly Monotone Discrete-Time Finite-Horizon Mean-Field Games
- Monroe: A Molecular Foundation Model for In-context Probabilistic Inference
- MOOD: Benchmarking Post-Hoc OOD Detection for Materials Property Prediction
- MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
- More Is Not More: What Matters for Diversity in LLM Opinions？
- MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
- More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
- More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding
- MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment
- MorphoGen: Free-Form XML Evolution for Robot Morphology Design
- MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
- Morpho-Temporal Decoupling: How Primate Neurons Expand Dendrites Without Losing Speed
- MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport
- MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
- Mosaic: A Benchmark Suite for Differentiable Physics Solvers
- MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
- MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport
- MOSAIC-CONUS: A Multimodal, Multi-Temporally Paired dataset for Earth Sciences
- MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
- MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
- MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control
- MoSE3: Learning World-Space SE(3) at Every Pixel
- Most ReLU Networks Admit Identifiable Parameters
- MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
- Motif-Mamba: network motif improved mamba for long-range sequence modeling
- MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening
- Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
- Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
- MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer
- MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
- Motion-o: Trajectory-Grounded Video Reasoning
- MoTo: Mixture of Tokenizers Towards Fair Multilingual Language Modeling
- MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding
- Mouse Total Capture: A multi-view Dataset for 3D Motion and Expression Capture of Freely Moving Mouse
- MOVEBENCH: A Benchmark for Global-Scale Wildlife Movement Forecasting
- Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
- MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
- MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
- M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
- MPQ: A Message-Passing View of Post-Training Quantization
- mRNABench: A curated benchmark for mature mRNA property and function prediction
- MSAlign: Aligning Molecular and Mass Spectra Foundation Models for Metabolite Identification
- MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling
- MSC-Mol: Modality-Synergy Contrasting for Multimodal Molecular Representation Learning
- MSConsensus: A Hundred-Million-Scale, Batch-Effect–Suppressed Dataset and Benchmark for Proteomics Machine Learning
- MSCR: Jointly Balancing Modality Utilization and Discovering Synergistic Information
- MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
- MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding
- MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning
- MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
- MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts
- MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
- MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
- Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
- Multi-agent Collaboration with State Management
- Multi-Agent Coordination via Support-Preserving Distillation
- Multi-Armed Bandits With Best-Action Queries
- Multi-bit LLM Watermarking with Certified Semantic Distortion
- Multi-Bridge Denoising Diffusion Probabilistic Models
- Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism
- Multi-Constrained Randomized Smoothing Certificates
- Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment
- Multi-Environment POMDPs with Finite-Horizon Objectives
- Multiform Attack for Transferable Cross-Modal Person Re-Identification
- Multigroup Fairness and Omniprediction: Separations and Equivalences
- Multi-Head Recurrent Memory Agents
- Multilateral Resistance-Guided Graph Message Passing for Trade Flow Prediction
- Multi-Level Alignment Framework for Long-Term Olfactory Neural Decoding
- Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance
- Multilingual Safety Alignment via Self-Distillation
- Multi-Marginal Couplings for Metropolis--Hastings
- Multimodal AI Detection In Two Words
- Multimodal Context-Aware Human Motion Generation with Language, Vision, and Object
- Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision
- Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
- Multi-Nonsmooth-Nonconvex-Objective Optimization
- Multi-Objective Causal Bandits: Minimal Intervention Space and Policy-Level Learning
- Multi-Objective Optimization for Modern Machine Learning: Foundations, Recent Advances, and Emerging Applications
- Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
- Multiobjective Submodular Maximization with Concave Aggregation
- Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA Design
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery
- Multiple Descent of Generalization Curve for Optimally Regularized Ridge Regression
- Multiple Instance Verification
- Multiscale Microenvironment Vector Space Projection for Uncovering Diverse Pathological Biomarker
- Multi-Scale Representation Learning for Single-Cell Multi-Omics
- Multiscale Supervised Unbalanced Optimal Transport Flow Matching
- Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-Site Wearables
- Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
- Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires Anchoring
- Multi-step Consistency Models: A Complete Error Theory and Optimal Step Selection
- Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
- MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents
- MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
- Multi-Token Residual Prediction
- Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
- Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
- Multivariate Time Series Forecasting needs Cross Variable Loss
- Multi-view Relational Distillation for Spatial Reasoning with Vision-Language Models
- MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
- Muon Does Not Converge on Convex Lipschitz Functions
- Muon Dynamics as a Spectral Wasserstein Flow
- MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
- MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
- MUST: Stage-Adaptive Stability Control for Test-Time Scaling in Multimodal Reasoning
- Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
- MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection
- MutQA: A Cross-Validated Q&A Dataset for Genetic Mutations
- Mutual Predictability Decomposition: Learning Interpretable Cross-Set Structure via Bi-Directional Prediction
- MUX: Continuous Reasoning via Multiplexed Tokens
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
- MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks
- MVVBench: Benchmarking 4D Reasoning in Vision-Language Models
- MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence
- MySign: A High-Fidelity Motion-Capture Dataset for 3D Sign Generation in Bahasa Isyarat Malaysia
- My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization
- NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
- NAGO: Noise-Aware Generative Operator via Flow Matching
- Nahual: A Sequence Model for Language and Atoms
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
- NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling
- NARRA-Gym for Evaluating Interactive Narrative Agents
- NarrativeBench: Benchmarking Multi-trait Automated Scoring and Feedback Efficacy of Large Language Models for Chinese Narrative Essays
- Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
- Narrowing the Collaboration Gap, Probably
- NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
- NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
- Native Audio-Visual Alignment for Generation
- Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
- Natural Jammers: When Non-Robust Features Become Antagonistic
- Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
- Natural-Language-Guided Protein Generation for Ligand-Binding Design
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework
- Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
- Nature3D-AD: Geometry-Aware Feature Learning for Natural-Growth 3D Anomaly Detection
- Nautilus: From One Prompt to Plug-and-Play Robot Learning
- NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation
- Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
- NavOCR: A Dataset Generator for Navigation-Relevant Text Detection in Mobile Robots
- NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation
- Nearest-Neighbor Radii under Dependent Sampling
- Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
- Nearly-Optimal Algorithm for Adversarial Kernelized Bandits
- Nearly Optimal Attention Coresets
- Nearly Optimal Bounds for Orthogonal Trace-Sum Maximization
- Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
- Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians
- Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits
- Near-Optimal Decentralized Stochastic Convex Optimization over Networks
- Near-optimal Explainable $k$-means Clustering under $\ell_p$ Norm
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
- Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback
- Near-Optimal Regret in Adversarial Kernel Bandits
- Near-Optimal Sample Complexity of Robust Reinforcement Learning with KL Uncertainty Set
- Near-Optimal Stochastic Linear Bandits with Delay
- NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
- Necessary but Not Sufficient: Spectral Tests for Value-Linear Attention Surrogates
- Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
- Negation Neglect: When models fail to learn negations in training
- Negative-Only Policy Optimization for One-Sided Verifiable Rewards
- Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
- Neighbor-Aware Snapshot-Based Temporal Graph Learning
- NEmo: Neuro-Symbolic Embodied Intelligence
- Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
- Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception
- NeRFix: fixing subtle mistakes in the quadrature of the NeRF volumetric integral
- Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
- NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Model
- NEST: Nascent Encoded Steganographic Thoughts
- NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming
- NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents
- NesyProAct: Proactive Neural-Symbolic Control for Web Agents
- Network Intervention by Polling Strategic Agents
- Network Learning with Semi-relaxed Gromov-Wasserstein
- Network of Theseus (Like the ship)
- Neural Backward Filtering Forward Guiding
- Neural Bayesian Filtering
- Neural-Behavioral Representation of Natural Whole-body Movement in Monkeys
- NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
- Neural Causal Models under Markov Equivalence
- Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors
- Neural Circuit Architectural Priors for Rat Locomotion
- Neural Compression of Long ADMM Trajectory for Multiparametric Quadratic Program
- Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
- Neural-Corrected Operator Learning for Homogenization and Inverse Design
- Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity
- Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP
- Neural Expansion: A Unified Mechanism for How Deep Neural Network Generalize
- NeuralFieldManifold: Reconstruction of LFP manifold with Lag Embedding
- Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
- Neural Fourier Transform for Multiple Time Series Prediction
- Neural Fractional Stochastic Differential Equations
- Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries
- Neural Garbage Collection: Learning to Forget while Learning to Reason
- Neural Harmonic Measure Operator
- Neural Modal Decomposition: Architectural Priors from Observables
- Neural Network Artifacts as a New Data Modality
- Neural networks are more modular than single neurons suggest
- Neural Networks With Dense Weights Are Not Universal Approximators
- Neural Neural Scaling Laws
- Neural Operator-based Curriculum Learning for Physics-Informed Neural Networks
- Neural Optimal Transport in Hilbert Spaces
- Neural population tuning statistics as priors for multitask generalization
- Neural Preconditioned Born Series: A Metric-Matched Framework for Learning-based Preconditioners
- Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generative Modeling
- Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
- Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
- Neural Refraction Fields for Image Verification
- Neural Scaling Laws in Particle Jets
- Neural Signals Generate Clinical Notes in the Wild
- Neural Slack Variables for Shape Constraints
- Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone
- Neural Statistical Functions
- Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
- Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment
- NeurIPS 2026 Workshop on Dynamic Alignment in Human-AI Coupled Systems
- NeurIPS 2026 Workshop on SaTQuML: Secure and Trustworthy Quantum Machine Learning
- NeurIPS 2026 Workshop on Tackling Climate Change with Machine Learning
- NeurIPS’26 Workshop on AI-Native Academia: Authorship, Peer Review, and Conference Governance under AI
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
- Neuroevolution of Intelligent Agents
- NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level
- NeuroHorizon: Long-Horizon Forward Prediction of Neural Population Activity via Autoregressive Decoding with Hierarchical Memory
- NeuroInk: Retinomorphic Spiking Sequence Modeling for Handwritten Text Recognition
- Neuro-Inspired Inverse Learning for Planning and Control
- Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models
- NeuroMem: A Neuroplastic Memory Framework for Lifelong Agents through Delayed Consolidation
- Neuromodulated Constrained Autoencoders for Context-Dependent Manifold Learning
- Neuronal Identity as an Organizational Basis for Analyzing Neural Population Dynamics
- Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
- NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
- Neuron Populations Exhibit Divergent Selectivity with Scale
- NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy
- NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models
- Neurosymbolic Learning for Inference-Time Argumentation
- Neuro-Symbolic Learning in the Era of Large Language Models
- Neurosymbolic Object-Centric Learning with Distant Supervision
- NeuroSynTheos: Learning to accelerate counterexample-guided reactive synthesis modulo theories
- Neutral-atom quantum features as complementary structural encodings for graph learning
- Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference
- Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models
- NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity
- New Coresets for Fair Clustering
- Newton-PINet: A fast physics-informed neural network with Newton linearization for meta-learning nonlinear PDEs
- Next Forcing: Causal World Modeling with Multi-Chunk Prediction
- Next-Latent Prediction Transformers Learn Compact World Models
- Next-Token Prediction Enables Scalable Learning of Sleep Physiology
- NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
- Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
- NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
- NicheIB: Targeted Spatial Bottlenecks for Predictive Microenvironment Discovery
- NIKA: Efficient Neural Video Representation via Structured Latent Diversity
- NINJA: A Navigator–Inspector Joint Architecture for Context-Efficient Issue Localization
- NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
- NIV: Neural Axis Variations for Variable Font Generation
- Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
- NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization
- NNCoxKL: Risk-Set Distillation from Probability-Free Prognostic Teachers for Deep Cox Models
- nnTrace: Detecting and Localizing Silent Bugs in Distributed Training
- NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling
- No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
- No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning
- NOFE – Neural Operator Function Embedding
- No Free Alignment: Observability-Aware Alignment for Multimodal Heterogeneous Learning
- No Free Best-of-Both-Worlds Learning in Repeated Bilateral Trade
- Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates
- Noise-Regularized Training for Learned Image Compression
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
- Noisy2Latent: Nonparametric Deconvolution and Denoising via Maximum Mean Discrepancy
- Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
- Noisy isomorphism: Robust expressivity of GNNs under structural perturbation
- No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse
- No More, No Less: Task Alignment in Terminal Agents
- Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
- Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
- Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
- Non-Expanding Gated Continued Fraction Architecture for Feedforward Layers in Language Models
- Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free Training
- Non-Linear Pricing Restores Tractability for a Data Seller
- Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
- Nonparametric Estimation of a Factorizable Density using Diffusion Models
- Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers
- No One Knows the State-of-the-Art in Geospatial Foundation Models
- No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
- NORA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning
- No-Regret Caching with Delayed Hits
- Normalized Architectures are Natively 4-Bit
- Normalized Friedkin–Johnsen Opinion Dynamics
- Normalized SGD in the Convex Regime: First High-Probability Guarantees and Momentum Extension
- Normalizing Flows are Capable Trajectory Planners
- Normalizing Trajectory Models
- Norm Anchors Make Model Edits Last
- NORMA: Norm-Guided Explanation Subgraph Discovery
- Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
- Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
- NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting
- NorSA: Accelerating LLM Decoding via Normalized Sparse Activation
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
- Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
- Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL
- Not All Layers Are Equal in Image-to-Video Transfer
- Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
- Not All Low-Confidence Tokens Are Equal: Calibrated Confidence for Efficient Test-Time Reasoning
- Not All Noise Is Harmful: Towards Perception Aware and Controllable RAW Image Joint Denoising and Demosaicing
- Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
- Not All Routing Drift Is Harmful: Trust-Region Projection for Class-Incremental Learning
- Not All Slots Are Equal: Non-Co-Progressive Markov Bridge for Bundle Construction
- Not All Spines Are Created Equal: How CT Segmenters Fail on Lumbosacral Transitional Vertebrae
- Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
- Not All Tokens Should Be Treated Equally: Context Credits Reassignment
- Not all uncertainty is alike: volatility, stochasticity, and exploration
- NoTA: Normalized Tensor Adaptation for Parameter-Efficient Continual Learning
- Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models
- Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models
- Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
- Not Just Oversmoothing: Detecting Echo Chamber Effect in Graph Neural Networks
- Not Only Where, But When: Temporal Scheduling for RLVR
- No Triangulation Without Representation: Generalization in Topological Deep Learning
- Not Suppressing or Purifying: Backdoor Containment via Expert Quarantine and Shutdown in LLMs
- Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
- NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
- NPCBench: A Clinical Apprenticeship Benchmark for Guideline-Constrained Care-Pathway Reasoning in Nasopharyngeal Carcinoma
- NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
- NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs
- NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting
- NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
- NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
- NTK Regression under dual power-law model: Deterministic Equivalents via SDE and PDE Methods
- NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
- nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
- Nuwa: Evaluation-Grounded Agentic Construction of Time Series Forecasting Systems
- Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure Infusion
- N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
- NyoomFloat12: Accelerating LLM Inference via Lossless 12-bit Weight Compression
- OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
- OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation
- OASIS: Online Adaptive Steering for In-Training Safety of LLMs
- OATS: Online Data Augmentation for Time Series Foundation Models
- Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty
- Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly
- Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
- OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
- ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning
- OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
- ObsConDA: Observability-Constrained Data Assimilation with Control-Space Inference
- Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
- Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals
- OccStress: Stress-Testing the 4D Occupancy Forecasting Chain
- Occupancy-based Quantile Risk Control
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
- OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
- ODDR: One-Step Deshadow Diffusion via Reward Guidance
- ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
- OdysSim: Building Foundation Models for Human Behavior Simulation
- OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
- OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
- Offline Constrained Reinforcement Learning under Partial Data Coverage
- Offline Inverse Reinforcement Learning with Unified Diffusion Planning
- Offline Materials Optimization with CliqueFlowmer
- Offline-Online Reinforcement Learning for Linear Mixture MDPs
- Offline Preference-Based Trajectory Evaluation
- Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
- Offloading Score: Measuring AI Reliance through Counterfactual Workflows
- Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings
- Off-policy Learning with Excursion Policies
- OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
- OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
- OHATP: Graph Anomaly Detection with Orthogonal-Hyperspherical Augmentation and Topology Perception
- OLA-Place: Cross-Modal Place Recognition without Global Descriptors
- OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting
- OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
- OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes
- OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction
- OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
- Omni-Interactive Universal Embedder
- OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
- OmniMechanism Design for Human-AI Collaboration with Impressionable Minds
- OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
- OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
- Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment
- OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
- OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning
- OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
- OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling
- OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
- Omni-SpikeDet: A Spiking Open-World Detector with Dynamic Text–Image Alignment
- OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
- OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
- On approximation and estimation of Schrödinger potentials without the curse of dimensionality
- On Communication-Efficient Training of Ensembles in Federated Learning
- On Computing Diverse Solutions in the Earth Movers Distance
- On Concentration Inequalities for Sampling without Replacement
- On Data Engineering for Scaling LLM Terminal Capabilities
- On-Device Intelligence: Foundation Models under Real-World Constraints
- On Differentially Private Mechanisms for Linear Regression
- On Differential Private $\ell_1$, $\ell_2$ and $\ell_p^p$ Distance Queries
- One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception
- One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
- One Avatar, Any Budget: Robust LoD for Dynamic Gaussian Avatars
- One-Bit Clustering for Two Component Sub-Gaussian Mixture Models
- OneCanvas: 3D Scene Understanding via Panoramic Reprojection
- One for All: A Non-Linear Transformer can enable Cross-Domain Generalization for In-Context Reinforcement Learning
- One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
- One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
- One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
- One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
- One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation
- OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
- ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration
- One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration
- One-Shot Generative Flows: Existence and Obstructions
- One-Shot Private Confidence Regions via Resampling
- One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms
- One Temperature to Rule Them All?
- One-Time Soft Alignment Enables Resilient Learning without Weight Transport
- One Unified Representation: Resolving the Appearance-Semantics Dilemma via Structural Regularization
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
- OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
- OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
- One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
- On Fitting Flow Models with Large Sinkhorn Couplings
- On Generalization in Bilevel Optimization with Overparameterized Models
- On Generation in Metric Spaces
- On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework
- On JEPA Isotropy
- On Length Bias in EEG-to-Text Decoding
- Online Active Testing: Adaptive Importance Sampling for Unbiased Risk Estimation in Data Streams
- Online Allocation with Differential Privacy
- Online Allocation with Unknown Shared Supply
- Online Bayesian Calibration under Gradual and Abrupt System Changes
- Online Bayesian Recalibration of Brain–Computer Interfaces with Language Model Potentials
- Online Bernstein-von Mises theorem
- Online Budget Allocation with Censored Semi-Bandit Feedback
- Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning
- Online Change-point Detection using Foundation Probabilistic Forecasting Models
- Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback
- Online Control with Multiple Sensors
- Online Data Selection for Instruction Tuning via Gaussian Processes
- Online Decision-Focused Learning under Semi-Bandit Feedback
- Online Differentially Private Consistent Clustering
- Online Directional Regression for Streaming Sufficient Dimension Reduction
- Online Evaluation of LLMs via Dyadic Designs
- Online Fair Division Meets Reordering Buffers
- Online Finetuning Decision Transformers with Pure RL Gradients
- Online Imitation Learning for Stabilizing Vlasov--Poisson Plasmas
- Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
- Online Learning of Group-Stable Coalition Structures
- Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
- Online Learning via Learned Latent Bayesian Tracking
- Online Learning with Certified Unlearning over Graphs
- Online Localized Conformal Prediction
- Online Maximization of Non-Decomposable Test and Population Utilities
- Online Minimum Description Length Passive-Aggressive Algorithms
- Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
- Online Quantile Omniprediction for Proper Losses
- Online Resource Allocation With General Constraints
- Online Set Learning from Precision and Recall Feedback
- On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Robustness
- On Making $SE(2)$-Invariant Networks Optimal
- On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
- On Nash Equilibria in Participatory Budgeting with Donations and Beyond
- On Neural Scaling Laws for Weather Emulation through Continual Training
- On objective mismatch in molecular retrieval from tandem mass spectrometry
- On Observation Time for Recovering Latent Hawkes Networks
- On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
- On-Policy Counterfactual Influence
- On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
- On-Policy Hindsight Distillation for Early Risk Prediction
- On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
- On Reparameterizing the Score Function
- On the Bias of Group-Based Advantage Estimation
- On the Burden of Achieving Fairness in Conformal Prediction
- On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
- On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
- On the Complexity of Preference-Based Bandits
- On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
- On the Convergence Analysis of Muon
- On the Convergence of First-Order Methods in Signaling Games
- On the Convergence of Multicalibration Gradient Boosting
- On the Convergence of Success Conditioning for Policy Optimization
- On the Depth of Monotone ReLU Neural Networks and ICNNs
- On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
- On the Divergence of Differential Temporal Difference Learning without Local Clocks
- On the Effect of Token Correlations on Semantic Transfer in Transformers
- On the Efficiency of Structured Pruning in Small Language Model Pretraining
- On the Error Correcting Effects of Stochasticity in Discrete Diffusion
- On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
- On the Expressive Power and Limitations of Multi-Layer SSMs
- On the Faithfulness of Visual Thinking: Measurement and Enhancement
- On the Feasibility of Identity Manipulation for Diffusion-Based Face Privacy Preservation
- On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
- On the fundamentals of gradient-based SAT solvers
- On the Geometry and Latent-Space Composition of Hypernetwork-Generated LoRAs
- On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
- On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models
- On the Information Loss of Multi-Token Prediction: Origin and Solution
- On the Instability and Stabilization of Blockwise Muon
- On the Invariance and Generality of Neural Scaling Laws
- On the Last-Iterate Convergence of Clipped Gradient Methods
- On the Limits of Latent Reuse in Diffusion Models
- On the Memorization of Consistency Distillation for Diffusion Models
- On the Meta-Design of Allocation Problems
- On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
- On the Necessity of Guidance Decay: From Three-Phase Analysis in Gaussian Mixture Models to Dynamic Optimization
- On the Nonlinearity of Learning Rate Scaling for LLM Training
- On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
- On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training
- On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
- On the Parallel Optimality of Exponentiated Gradient Descent
- On the Pitfalls of Instance-Based Dynamic Curricula
- On the Price of Privacy for Language Identification and Generation
- On the Primacy Bias in RLVR Training
- On the Provable Emergence of Hierarchical Concept Structure in CLIP Embeddings
- On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry
- On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
- On the Recoverability of Causal Relations from Bulk Gene Expression Data
- On the Relaxation of Conditional Independence Assumption for Image Segmentation
- On the Robustness of Watermarking for Autoregressive Image Generation
- On the Runway Cascade of Transformers for Language Modeling
- On the Selectivity of Generative Models in Structure-Based Drug Design
- On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime
- On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
- On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences
- On the Token Value Inequality in Efficient Reasoning
- On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
- OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning
- On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search
- OopsWorld! Operation-Grounded Seamless World Generation
- OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation
- OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
- OpenCoF: Learning to Reason Through Video Generation
- Open, Collaborative, and Decentralized Training of Foundation Models
- Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks
- Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
- OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models
- OpenMHC: Accelerating the Science of Wearable Foundation Models
- OpenSanctions Pairs: A Large-Scale Dataset for Pairwise Entity Matching
- OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
- OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- OpenView: Empowering MLLMs with Out-of-view VQA
- Open-Vocabulary 3D Part Segmentation with Semantic Propagation Hawkes Process
- Open Vocabulary Domain Unlearning
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
- OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
- OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
- OPERA: An Agent for Image Restoration with End-to-End Joint Planning–Execution Optimization
- Operads for compositional reasoning in LLMs
- OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators
- OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
- OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in Policy Optimization
- Opponent Modeling in Incomplete-Information Continuous Colonel Blotto
- OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal Regret
- OPT 2026: Optimization for Machine Learning
- Opt-Arena: Evaluating, Selecting, and Generating Optimization Modeling Data via Tripartite Graphs
- OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
- Optimal algorithmic complexity of inference in quantum kernel methods
- Optimal Algorithms for Fixed-Graph Multi-Attribution Privacy
- Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
- Optimal Ansatz-free Hamiltonian Learning In Situ
- Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy
- Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
- Optimal Convergence Analysis of DDPM for General Distributions
- Optimal Dimension-Free Sampling for Regularized Classification
- Optimal Experiments for Partial Causal Effect Identification
- Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
- Optimal In-context Adaptivity and Distributional Robustness of Transformers
- Optimal In-Context Learning of Autoregressive Processes under Heterogeneous Second-Order Moments of the Prompts
- Optimal Learning-Augmented Algorithm for Online Bidding
- Optimal Linear Regression Without a Variance
- Optimal Rates for Adaptive Private $k$-PCA
- Optimal Rates for Differentially Private Hypothesis Testing with E-values
- Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails
- Optimal Real-Data Allocation for Synthetic-Data-Augmented Inference
- Optimal Recalibration of an Online Predictor
- Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
- Optimal Risk Bounds of Stochastic Gradient Descent for Shallow ReLU Networks
- Optimal scaling laws in learning hierarchical multi-index models
- Optimal sequential tests yield log-optimal e-processes
- Optimal Subgroup Discovery at Every Support Threshold
- Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
- Optimistic Dual Averaging Unifies Modern Optimizers
- Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
- Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
- Optimized Forward-Backward Rematerialization for Memory-Efficient Pipeline Parallel Training
- Optimized Minimal 4D Gaussian Splatting for Efficient Dynamic Scene Representation
- Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
- Optimizer-Induced Mode Connectivity: From AdamW to Muon
- Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
- Optimizing Analytic Constants via AI-Guided Lean Proof Refinement
- Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
- Optimizing Retraining Schedules via Learning Curves
- Optimizing Social Utility in Sequential Experiments
- Optimizing the Envy Cycle Elimination Algorithm
- OptiWorld: Optimal Control for Video World Generation under Physical Constraints
- Oracle-Robust Online Alignment for Large Language Models
- Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising
- OrangeTree: A Linear and Tree-based Time Series Forecasting Model Supporting Multiple Input and Output Lengths
- ORBIT: A Framework for Multi-Agent Security Evaluations
- OrbitLoRA: Learning Rotation-Aware Low-Data Adaptation of Vision Foundation Models
- ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
- ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
- ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering
- OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control
- Order-based structure learning for zero-inflated count data under data heterogeneity
- Ordered Policy Optimization
- Order-Marginalized Scoring for Masked Diffusion Models
- Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection
- Order-Optimal Sample Complexity for Distribution Learning via Flow Matching
- Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
- Ordinary Least Squares as an Attention Mechanism
- Origami as a Real-Image Benchmark for Procedural State-Transition Reasoning
- Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
- OroPrecipBench: a km-scale benchmark for spatial precipitation downscaling over complex terrain
- Orthogonal Origin Parking: Decoupling Lorentz Manifolds for Robust OOD Generalization
- Orthogonal Sparse Subgraph Alignment for Structure-Function Coupling in Brain Networks
- Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
- Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments
- OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
- Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
- Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
- OS-Omni: A Cross-Platform Benchmark for Generalist Computer-Using Agents
- OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
- OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing
- OTel: Open Telco AI Datasets, Benchmarks, and Models
- OTformer: Non-Stationarity-Aware Adaptive Optimal Transport Attention for Time Series Forecasting
- OTIS: Learning High-Quality Time Series Features With Tiny Encoders
- OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies
- OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
- Otter Weather: Skillful and computationally-efficient medium-range weather forecasting
- Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
- Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
- Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
- Outlier-Robust Multi-Output Gaussian Processes
- Out-of-Distribution Detection in Continual Learning
- Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
- Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
- Overcoming Kernel Redundancy for Scaling Logic Gate Networks
- Overcoming Rank Collapse in Feedback Alignment
- Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
- Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness
- OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
- Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
- Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
- OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
- OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
- P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
- P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
- PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
- PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
- PACE: A Proxy for Agentic Capability Evaluation
- PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models
- PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
- PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
- PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
- PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
- PACE: Progress Actively-internalized Conditioning Execution for Long-horizon Manipulation
- PACE: Two-Timescale Self-Evolution for Small Language Model Agents
- PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
- Pacing Branch Parallelism in LLM Serving
- PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
- PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
- PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
- PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
- PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes
- Paint Anything: Toward Any-Color Controllable Image Generation and Editing
- PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
- PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
- Pairwise AUC Optimization Needs Corrective Power: A Unified View
- Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design
- Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
- Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting
- PaLoRA: Paced Low-Rank Adaptation for Continual Learning
- PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
- PANDA: Prior-guided Attentional Dual-path Architecture
- Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
- Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
- PanoHK360: A Large-Scale 8K Urban Panoramic Dataset and Benchmark for Depth Estimation
- Panoptic Saliency Ranking
- Panoptic Scene Program Diffusion Transformer
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling
- PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World
- PaperLens: How Predictable Is Paper Acceptance?
- PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
- Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
- Paradoxes of Game Theoretic Equilibria and Price of Anarchy
- Paradoxical noise preference in RNNs
- ParaLin: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure
- Parallel Broyden methods for efficiently evaluating nonlinear state space models
- Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
- Parallel Fixed-Point Spiking Neurons for Efficient Training of Spiking Neural Networks
- Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
- Parallel-in-Time Variational Inference for Latent Stochastic Differential Equations
- ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?
- Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
- Parameter Exploration for RLVR via Variational Learning
- Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses
- Parameterized Stripe Attention for Efficient Video Generation
- Parameter symmetries determine representational geometry in overparameterized nonlinear networks
- Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation
- ParaPC-FM: Accelerating Parallel Sampling via Principled Initialization
- Parasite Features: Causal Abstraction Through Spurious Pathways
- ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
- PARE: Pruning and Adaptive Routing for Efficient Video Generation
- Pareto DNN Verification: Fast for Most Queries
- ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
- Pareto Preference Optimization for Structure- and Stability-Aware RNA Inverse Folding
- ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
- PARI: Policy-Driven Active Residual Intervention for Weakly Supervised Point Cloud Segmentation
- Partially Performative Prediction
- Participatory ML for Social Harm Should be Constructed, Validated and Reasoned Through First-Person Accounts
- Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
- Partition Tree: Conditional Density Estimation over General Outcome Spaces
- PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
- Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation
- Past, Future, All at Once: Breaking Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
- Patch4Patch: Restoring Structural Connectivity in Patch-based Vision Encoders
- PatchBench: Measuring Collateral Damage in Activation Patching
- Patch Hierarchical Attention Transformers for Efficient Particle Jet Tagging
- Patching Up Circuit Learning on Images
- PatchKV: Weight Space Compensation of KV Cache
- PATCH: Learnable Tile-Level Hybrid Sparsity for LLMs
- Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
- PatchScout: Thematic Web Data Collection via Information Foraging
- PATH: A Dual Perspective for High-quality Text-attributed Graph Learning
- Path Dependence under Adaptive AI Delegation
- Path-Guided Flow Matching for Dataset Distillation
- Path-independent Flow Matching for Multi-parameter Generative Dynamics
- PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide VQA
- PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
- Pathway-Aligned Regulator Tokens for Interpretable Spatial Gene Expression Prediction from Histologyatial Transcriptomics Prediction from Histology
- Pathways of Visual Information Flow in Vision-Language Models
- Pattern-Based Matrix Analysis Under Permutations
- PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
- Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
- PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
- PaxBench: A Multimodal Sequence Benchmark for Protein Abundance Prediction
- Payoff-Aware Prediction of Population Game Dynamics
- Payoff-Only Learning in Games via Best-Response Differential Inclusions
- PBT-Bench: Benchmarking AI Agents on Property-Based Testing
- PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design
- PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification
- PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion
- PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models
- PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
- pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
- PDE-PFN: Prior-Data Fitted Neural PDE Solver
- PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
- PDF-HR: Pose Distance Fields for Humanoid Robots
- PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction
- P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
- PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language
- PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
- PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion Sampling
- Peer Review of Applied Machine Learning Papers Must Include Code Execution
- Peer review should constrain evaluative authority
- PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
- Penalize to Verify: A Multi-Domain Benchmark for Trustworthy LLM Evaluation
- Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
- PENEX: AdaBoost-Inspired Neural Network Regularization
- PepDDG: Peptide–Protein Binding ΔΔ𝐺 Prediction via Information Channel Decomposition
- PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction
- Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
- Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation
- PercepCap: Video Captioner with Structured Spatio-Temporal Perception
- Perception for Action in Latent World Models
- Perception, Not Reasoning, Limits Visual Theory of Mind
- Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
- Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
- Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
- Performance Estimation Problems: Computer-Aided and AI-Assisted Analysis and Design of First-Order Optimization Methods
- Performative Prediction with Selective Labels
- Periodic Complex Stochastic Processes for Retrieving Atomic Structures of Unknown Matters
- Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks
- Permanent and Transient Representations for Continual Reinforcement Learning
- PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
- Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
- PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
- Permutation-Invariant Spectral Learning via Dyson Diffusion
- Permutation Sensitivity in t-SVD-based Multi-view Clustering
- Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation
- PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation
- Persistent Planar Memory for Video World Models
- Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
- Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts
- Personalized, Aligned, Long-Term Memory for AI Systems (PALM) Workshop
- Personalized and Collaborative Online LQR via Thompson Sampling
- Personalized LLM Alignment Should Be Counterfactually Verifiable
- Personalized Safety in Federated Fine-Tuning of Large Language Models
- Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-Horizon Agents
- Personal Visual Memory from Explicit and Implicit Evidence
- PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
- Persona-Model Collapse in Emergent Misalignment
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models
- Persuasive Prediction via Decision Calibration
- Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy
- PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
- Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding
- PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations
- Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
- PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction
- PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
- PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection
- PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation
- PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression
- PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
- Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Sciences
- Phantom Transfer: Data Poisoning can Survive Data-Level Defences
- Phase-Adaptive Fusion: Spatio-Temporal Modulation for VLA Models
- PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling
- Phase-DGS: Phase-Guided Dynamic Gaussian Splatting from Unsynchronized Multi-view Video
- Phase Kernel Lifts Capacity of Dense Associative Memory
- PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
- Phases of Muon: When Muon Eclipses SignSGD
- Phase Space Attention: A Hairer Lift Resolves the Single-Layer Induction Obstruction
- Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
- Phase Transitions in Heavy-Tailed Mean Estimation under $\ell_p$ Norms
- Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
- Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFE
- PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
- PHIONet: Port Hamiltonian Inertial Odometry Network
- PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
- PHOEBI: An Open-World Benchmark for Bacterial Identification in Phase-Contrast Microscopy
- PhotoFlow: Agentic 3D Virtual Photography Missions
- PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA
- PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos
- PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
- PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
- PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
- PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing
- PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
- PhysEval: Quantifying the Gap Between Video Generation and World Physical Laws
- PhysEval.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models
- PhysFlow: Physics-Intrinsic Velocity Regularization for Motion-Intensive Video Generation
- PhysFormer: Learning to Simulate Mechanics in World Space
- PhysGraphNet: Physical-State Scene Graphs via Latent Graph Reasoning and Counterfactual Supervision
- PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates
- Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
- Physical Understanding for Decision-Making: Bridging Foundation Models and Reliable Agents
- Physical World Model
- PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
- Physics-Conditioned Video Diffusion with Kinematic Priors for Fusion Capsule Polishing
- Physics-Constrained Generative World Model for Off-Road Terrain via Post-hoc Projection
- Physics-Informed Functional Tucker Method with RKHS Factors for Sparse Spatiotemporal Reconstruction
- Physics-Informed Optimal Control by Control-Only Supervision with Error Guarantees on Value and Policy
- Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
- Physics Unrolled Neural Operator for Wireless Field Modeling
- PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks
- PhysRemover: A Unified Framework for Physically Realistic Object Removal
- PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation
- PhysTC: A Physics-Enhanced Dataset and Architecture for High-Precision Tropical Cyclone Forecasting
- PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
- PhyTS: A Benchmark for Scientific Time Series
- PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
- PICID: A Modular Evaluation Infrastructure for Reproducible PHM Across Tasks and Domains
- PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
- PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
- PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios
- PI-EDG: Physics-Informed Full-Space Electron Density Generation from Molecular Geometry
- PIGRAM: An Interpretable Patch--Motif Interaction Grammar for Protein--Nucleic-Acid Recognition
- PINNBench: A Benchmark and Evaluation Study of Training Policy Selection in Hybrid PINN-Operator Solvers
- PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks
- Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Reranking
- Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
- PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training
- PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
- PISCO: Precise Video Instance Insertion with Sparse Control
- PISG: Constraint-Aligned Signal Amplification for Diffusion-Based Combinatorial Optimization
- PIS: Pose-Interpolation Smoothness for Skinning Weight Refinement
- PitchBench: Measuring Pitch Hearing in Audio-Language Models
- PithTrain: A Compact and Agent-Native MoE Training System
- PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal
- PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding
- PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining
- PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
- PixelDiT2: Representation-Grounded Pixel Diffusion Transformers
- PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
- Pixels over Symbols: Sensory Realism Improves Behavioral Alignment in Models of Cognition
- Pixel-space Autoregressive Image Synthesis via Spectrum Serialization and Flow-based Refinement
- Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
- PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
- PLACE: Patch-Level Agnostic Concept Extraction
- Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing Actions
- Plan4D: Generative Plannable 4D Worlds
- PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
- Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation
- Planning Persuasion, Not Utterances: Profile-Conditioned Open-Loop Search for Dialogue Strategy
- PlasticMem: Adding Temporal Reasoning to Diffusions for Consistent Long Video Generation
- Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
- Platonic Task Arithmetic
- PLATO: Pointer Learner for Agent and Task Openness
- Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
- Plausible Biomolecular Structure Prediction via Physics-informed Reinforcement Learning
- Playing Markov Games Without Observing Payoffs
- Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
- PLLS-CP: Unsupervised Hallucination Detection with Layer Selection and Cross-Domain Conformal Guarantees
- Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
- Pluralistic AI Alignment Requires Inference-Time Multi-Objective Control
- PM1: A Multimodal Foundation Model for Genomes, Phenotypes, and Images at Biobank Scale
- PM-LoRA: Scalable Continual Learning via Progressive Merging of Low Rank Adapters
- PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization
- PocketVE: Stable and Controllable Structure-Based Drug Design with Variance-Exploding Diffusion
- PoEM: Predicting New RL Outcomes from Existing Policies
- POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
- Point4D: Long-range 4D Motion Reconstruction
- Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
- Point Clustering Encoders
- PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
- Pointillism: Probing-Based Model Compatibility for Robust Collaborative Machine Learning
- Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units
- Point Tracking Improves World Action Models
- Pointwise Lipschitz Continuous Graph Algorithms
- PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
- POISE: Instance-Specific Prompt Tuning under Latent Mixture Target Distributions
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
- Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders
- POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
- PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation
- Polar Transformers: $SO(2)^K$-Equivariant Angular Attention for Cryo-EM Image-Set Processing
- Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
- Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
- Policy Gradient Algorithms in Average-Reward Multichain MDPs
- Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
- Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
- Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
- Policy Regret Minimization in Partially Observable Markov Games
- Political Neutrality as Balanced Approval: A Large-Scale Human Evaluation of AI Responses
- PolyMind: Exploring Width Scaling for Reflective Reasoning in Language Agents
- Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences
- Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals
- PolySplat: Workload-Regime-Aware Rasterization for 3D Gaussian Splatting
- PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery
- PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs
- POME: Post Optimization Model Edit via Muon-Style Projection
- Pooling Versus Ensembling for Ridge Regression Under Covariate Shift
- PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
- POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
- Population-Aligned Persona Generation for LLM-based Social Simulation
- PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning
- PORT: Preference Optimization via Robust Token-Level Reweighting
- PortPy: A Benchmark for AI and Optimization in Cancer Radiotherapy Planning
- PoSafeNet: Structured Safety Learning via Compositional Projection
- Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation
- PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
- Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
- PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar Geometry
- Position: Adopt Constraints Over Fixed Penalties in Deep Learning
- Position: AI-Agent Pricing Should Become More Outcome-Dependent: An Economic Perspective
- Position: AI Development Should Prioritize Cognitive Security
- Position: AI Efficiency Gains Must Be Quantitatively Evaluated Against Rebound Effects
- Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
- Positional Encoding Is All You Need For Scalable Equivariance Constraint Relaxation
- Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases
- Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
- Position: Anthropomorphic Language in AI Discourse Can Be Constructive
- Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
- Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
- Position: Fair Representations Cannot Hold What They Promise
- Position: Let’s Strengthen Verifiability if We Can’t Enforce Reproducibility
- Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
- Position: LLM Privacy Requires a Lifecycle-Wide Approach
- Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
- Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
- Position: Machine Learning Models for Reaction Transition States Deserve Better
- Position: Neurosymbolic AI is a strong technical foundation for trustworthy, deployable AI by design
- Position: Next-Generation Game Engines Should Be Built on Interactive Generative Video
- Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
- Position: Robust Reasoning Requires Internal Time, Not Scale Alone
- Position: Semantic Uncertainty Measures Disagreement, Not Reliability
- Position: Telic Errors Make VLMs Unreliable Annotators in Sensitive Contexts
- Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
- Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI
- Position Without Positional Embeddings: A Directional Mechanism in NoPE Transformers
- Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
- Post-ADC Inference: Valid Inference After Active Data Collection
- PosterDuet: Co-Evolving Design Generation and Reward Optimization for Product Poster Synthesis
- Posterior Alternative Calibration in Ambiguous Inverse Problems
- PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
- Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
- Posterior-First Neural PDE Simulation: Inferring Hidden Problem State from a Single Field
- Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
- Posterior Sampling-based Online Learning for Episodic POMDPs
- Posterior-Tracking for Best-Arm Identification in Bernoulli Bandits
- Post-hoc Selective Classification for Reliable Synthetic Image Detection
- Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics
- POST: Progressive Object-Slot Tokenization for Multimodal Large Language Models
- Post-Selection Distributional Model Evaluation
- Post-Selection-Safe Pessimistic Utilities for Offline Multi-Objective Reinforcement Learning
- Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers
- PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
- Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
- Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
- PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
- PPO in the Fisher-Rao geometry
- Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
- Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
- Practical Non-Stationary Graph Gaussian Processes
- Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
- Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
- PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
- Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer
- Precision-Aware Hopfield Retrieval: Unifying Population Codes and Memory Retrieval with Information Optimization
- Precision-Pyramid: Towards real-time neural decoding for fault-tolerant quantum computing
- PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
- Preconditioned Flow Matching
- Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging
- Predicting and improving test-time scaling laws via reward tail-guided search
- Predicting directional flexibility in proteins
- Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings
- Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
- Predicting Only from Selected Evidence: A Tempered Product-of-Experts Bottleneck for Auditable EEG Diagnosis
- Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
- Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
- Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery
- Predicting the Needle in a Petabyte Scale Haystack: Open-Vocabulary Event Anticipation in Satellite Imagery
- Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning
- Prediction-Augmented Trees for Reliable Statistical Inference
- Prediction-Intervention Games and Invariant Sets
- Prediction-only distillation with optimal mixing in ridge-regularized linear and logistic regression
- Prediction-Powered Active Testing
- Prediction-Powered Inference Across Many Tasks for AI Evaluations and Social Science Research
- Prediction Under Imperfect Compression: A Theory of Approximate MDL
- Predictive 4D Generation with Latent State Machines
- Predictive but Not Plannable: RC-aux for Latent World Models
- Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
- Predictive–Generative Drift Decomposition for Speech Enhancement and Separation
- Predictive Geometry of Hidden Trajectories in Transformers
- Predictively-Oriented Kalman Filtering
- Predictive Representation Learning for Partially Observed Neural Dynamics
- Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
- Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
- PreDiff: Sequential Recommendation by Denoising Preference Distributions
- Pref-DetectGPT: Unveiling Machine-Generated Text via Preference-Aware Curvature Measurement
- Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
- Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
- Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving
- Preferential dynamic modeling with forward-backward smoothing
- Prefill-Guided Trace Allocation for Sample-Efficient Test-Time Scaling
- Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
- Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation
- Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
- PreFT: Prefill-only finetuning for inference efficiency
- PREPING: Building Agent Memory without Tasks
- Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
- Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment
- Preserving Geometric Symmetry in Uncertainty Estimation for Molecular Forces
- Pretext Reasoning: Scaling the Building Blocks of Interleaved Multimodal Reasoning
- Pretraining Curricula Enable Selective Fine-tuning
- Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models
- Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
- Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory
- PriFT: Prior-Support Guided Token Reweighting for Supervised Fine-Tuning
- Primal-Dual Flow Matching for Sample-Wise Constrained Generation
- Primal-Dual Guided Decoding for Constrained Discrete Diffusion
- Primal-Dual Representation Learning for Low-Rank Constrained MDPs
- Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
- PRIME: A Modular Approach for Private Synthetic Data
- PRIME: Poincaré return induced measure for learning partially observed dynamical systems
- PRIM: Meta-Learned Bayesian Root Cause Analysis
- Principia: Relational Physics Tests for Video Models
- Principled Design of Diffusion-based Optimizers for Inverse Problems
- Principled Federated Random Forests for Heterogeneous Data
- Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
- Principles of Deep Representation Learning via Low-Dimensional Models
- Prior-Anchored Local Statistical Representation Rectification for Low-Light Image Enhancement
- Prior as Geometry, Not Generator: Weak-Diffusion Test-Time Reconstruction for Dynamic MRI
- Prior Text-Informed Gate Attention Framework for Multimodal Psychiatric Disorder Diagnosis
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
- PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning
- PRISM: Asymmetric Precision-Recall Optimization for Million-Scale Root Cause Analysis
- Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
- PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
- PRISM:Disentangling Preference Distributions for Generative Ranking
- PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
- Prism: Harmonizing Missing Modalities via Implicit Structural Alignment on Lightweight Pulse RWKV for Multimodal Crack Segmentation
- PRISM: Human Point Cloud Reconstruction via Skeleton-Guided Diffusion from MmWave Radar
- PRISMIC: Reconstructing User Preference via Intent Decomposition and Consolidation
- PRISM: Phenotype-Resolved Inference in Single-Cell Mixed Models via Latent Disease States and Contextualized Differential Expression
- PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
- PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA
- PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning
- PriSM: Prior-guided Shared-basis Mixture Personalization for LLMs under Sparse User Histories
- PRISM: Priority-Guided Scanning in the Wavelet Domain for UAV Maritime Small Object Detection
- PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
- PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization
- PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing
- PRISM: Spectral Pruning and Reconstruction for Parameter-Efficient Model Merging of MLLMs
- Privacy Amplification Persists under Unlimited Synthetic Data Release
- Privacy by Postprocessing the Discrete Laplace Mechanism
- Privacy Guarantees in Posterior Sampling under Contamination
- Privacy in the Era of Large Opaque Models: Theoretical, Legal, and Practical Perspectives
- Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning
- Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
- Privacy Risk Scales with Effective Dimension in Federated Learning
- PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
- Private Adaptive Covariance Estimation via Gaussian Graphical Models
- Privately Clipping Heavy-Tailed Data
- Privately Estimating Monotone Statistics in Polynomial Time
- Private Online Prediction from Experts with Small Losses
- Private Prediction via Shrinkage
- PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking
- PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
- ProactBench: Beyond What The User Asked For
- Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
- ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification
- Probabilistic Circuits for Irregular Multivariate Time Series Forecasting
- Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction
- Probabilistic Guarantees for Adversarial Linear Contextual Bandits
- Probabilistic Recursive Reasoning
- Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures
- Probabilistic Tiny Recursive Model
- Probability-Conserving Flow Guidance
- Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
- Probe-Guided Gradient Balancing for Multimodal Learning
- PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
- Probing for Representation Manifolds in Superposition
- Probing Persona-Dependent Preferences in Language Models
- Probing the Trajectories of Reasoning Traces in Large Language Models
- Probing Visual Planning in Image Editing Models
- Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback
- probly: Uncertainty-Aware Machine Learning
- ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking
- ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
- Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
- Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
- Process-Aware LNS for Large-Scale MILP via Context-Enhanced Fine-Tuned LLM-driven Selector
- Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
- ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
- ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
- ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
- ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
- ProEdit: Inversion-based Editing From Prompts Done Right
- PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
- Profit Maximization in Bilateral Trade against a Smooth Adversary
- ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images
- Program-as-Weights: A Programming Paradigm for Fuzzy Functions
- ProgramBench: Can Language Models Rebuild Programs From Scratch?
- Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference
- Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
- Progressive Layer-wise Supervision: Deep-to-Shallow Supervision Annealing for Efficient and Robust Speech Deepfake Detection
- Progressive Memory Transformer: Memory-Aware Attention for Time-Series
- Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models Adaptation
- Progressive Residual Warmup for Language Model Pretraining
- Progressive Risk Estimation for Accident Anticipation
- Progressive Signal Calibration for Medical Image Segmentation: Diagnosing and Correcting Structural Misalignment in Training Signals
- Projected Neural Additive Models as Universal Approximators
- Projection Learning: A Principled Way to Overcome Memorization in Distribution Learning
- ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
- PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling
- ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
- Prompt–Activation Duality: Improving Activation Steering via Attention-Level Interventions
- Prompt-Conditioned Semantic Bottleneck for Cross-Domain Face Attack Detection
- Prompt-Driven Exploration
- Prompt Ensemble Image Purification for Test-time Adversarial Robustness of CLIP
- Prompting Diffusion Models for Zero-Shot Instance Segmentation
- Prompt Optimization Makes Misalignment Legible
- Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
- Propagate to Discover: Graph-Structured Propagation for Generalized Category Discovery
- Propagation of Chaos in Contextual Flow Maps
- Proper Agnostic Learning of Functions of Halfspaces
- Proper Scoring Rules for Agentic Uncertainty Quantification
- Property-Guided LLM Program Synthesis for Planning
- ProPolar: Progressive Polar Decomposition for Implicit Neural Representations
- Proportionality in Ranking Compression
- Proposing Better Rollouts for On-Policy Distillation
- Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation
- ProQuant: Progressive Quantization-aware Training for Edge MLLMs
- ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
- Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
- Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction–Reality Gaps
- ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
- PROTEUS: A Self-Evolving Red Team with Surface Expansion for Agent Skill Ecosystems
- Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
- ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
- Prototype-Aligned Multi-View Graph Learning for EHR Prediction
- Prototypes of the Mind: A Unified Framework for Probing the Visual Brain
- Prototype Topology Consistency for Visible-Infrared Lifelong Person Re-Identification
- ProtoVis-Nav: Prototypical Visual Imagination for Visual-Spatial Aligned UAV Navigation
- Provable Explanations for Any-Order Neural Additive Models
- Provable Joint Decontamination for Benchmarking Multiple Large Language Models
- Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
- Provable Quantization with Randomized Hadamard Transform
- Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
- Provable Selective Auto-labeling with Reliability Guarantees
- Provable Speedups From Dynamic Population Sizes in Evolutionary Algorithms for Multiobjective Optimization
- Provable State Estimation with Recurrent Models
- Provable Test-Time Scaling for Beam Search in LLM Reasoning
- Provably Accurate Shapley Value Estimation in High Dimensions via Sparse Leverage Sampling
- Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
- Provably Efficient Representation Learning for Low-Rank CMDPs
- Provably Reliable Classifier Guidance via Cross-Entropy Control
- Provably Safe, Yet Performant Reinforcement Learning
- Proximal Difference-in-Differences for Long-Term Causal Learning under Confounding and Outcome Drift
- Proxy-Based Approximation of Shapley and Banzhaf Interactions
- ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
- ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer
- PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping
- PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation
- Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
- Prune, Don’t Rebuild: Efficiently Tuning $\alpha$-Reachable Graphs for Nearest Neighbor Search
- Prune to Protect: Faster Training and Enhanced Privacy by Dynamic Data Pruning
- Pruning and Distilling Mixture-of-Experts into Dense Language Models
- Prysma: Efficient Modality Adaptation for SLO-aware LLM-based Video Question Answering
- PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs
- PTA: From Pretrained Representations to Acting Agents -- Bridging Pretraining, Planning, and Test-Time Decision Making
- Publishing Below-Threshold Triangle Counts under Local Weight Differential Privacy
- PULSE: A Synchronized Five-Modality Dataset for Sensorimotor Coordination in Long-Horizon Daily Activities
- PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders
- PULSE: Probabilistic Uncertainty-Aware Longitudinal Simulation for EHR Trajectories
- Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models
- PuppetGait: Generalizing Gait Recognition via 3D Body-Aligned LVM Features
- Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
- Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
- PVFormer: Proper Velocity Transformer for Stable and Scalable Hyperbolic Representation Learning
- pyCD: A Unified Benchmark for Reliable Evaluation of Cognitive Diagnosis Models
- Pygmalion: Bridging Reconstruction and Generation in Sparse Voxel-based 3D Modeling
- Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
- Q-ARVD: Quantizing Autoregressive Video Diffusion Models
- QB-Highlights: Quality-Guided Budgeted Highlight Detection in Videos with Dense Query-Relevant Moments
- Q-CoMove: Differentiable Quantum Circuit Priors for Coordinated Motion in Multi-Component Embodied Systems
- QDMouse4M: A Multi-View 3D Mouse Spontaneous Behavior Dataset with Quantum-Dot Markers
- QEC Model Zoo: Democratizing AI-enhanced Quantum Error Correction
- Q-Focus: Let the Question Guide What to See in Long Videos
- QGround: Condition-Wise Evidence Aggregation for 3D Grounding with 2D VLMs
- QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem
- Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
- Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
- Q-Residual Physics: Hamiltonian-Structured Quantum Residual Learning for Embodied Dynamics
- Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection
- QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
- Quality-Diversity Optimization as Multi-Objective Optimization
- quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
- QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
- Quantifying and Optimizing Path Uncertainty in Masked Diffusion Models
- Quantifying Centrality for Complex Data
- Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
- Quantile Benchmarking Heterogeneous Web Corpora in Open LLM Pretraining
- Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
- Quantile Geometry Regularization for Distributional Reinforcement Learning
- Quantitative Assessment of Crystal Structure Prediction
- Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
- Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
- Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
- Quantum Best Arm Identification with Limited Round of Adaptivity: Lower Bounds and Algorithms
- Quantum Composite Hypothesis Testing with Small Error
- Quantum Safe Stochastic Linear Bandits
- Quantum Speedup of Multi-armed Bandits at Scale by Tackling Memory Decoherence
- Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
- Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions
- Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM Collaboration
- Query as a Resource: Activity-Cost Guided Remote Sensing Domain-Incremental Object Detection
- Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
- Query-Limited Community Recovery in Stochastic Block Models
- Query Lower Bounds for Approximating the Top Eigenvector of Asymmetric Matrices
- Query Lower Bounds for Diffusion Sampling
- QueryStop: Dynamic Stop Signals for Efficient Streaming Inference
- QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams
- Quest: Training Frontier Deep Research Agents with Fully Synthetic Tasks
- Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
- QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
- Q-ViK: Question-Guided Visual KV Cache Eviction for Large Vision-Language Models
- QWaveNet: Quantum-Enhanced Wavelet Network for Time Series Forecasting
- RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
- RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain
- RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
- RA-ClipScore: Making Generative Model Evaluation More Interpretable
- RadarFlowPose: Vision-Inspired Coarse-to-Fine Skeleton Refinement with Flow Matching
- RadarMAE: Injecting Physical Inductive Biases into Masked Autoencoders for Advanced Radar Object Detection
- RADAR: Relative Angular Divergence Across Representations
- RADAR: Routing Agents via Difficulty-Aware Recovery
- RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
- Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
- RADIUM: RadioActive Decay of Image-Underlaid Marks
- RadOmni: Advancing Foundation Model for Non-contrast CT with Omni Radiology Knowledge
- RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models
- RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
- RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
- RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-Tuning
- RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies
- RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
- RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
- RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification
- RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis
- RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State
- Random Attention Pattern Learning Enables Emergent Capabilities
- Random-Effects Centroids for Domain Generalization
- Random features for Grassmannian kernel approximation with bounded rank-one projections
- Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
- Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
- Random Neural Network Expressivity for Non-Linear Partial Differential Equations
- Random-Projection Tree Stein Variational Gradient Descent
- Random-Set Graph Neural Networks
- RankAlign: Unsupervised Vision-Language Representation Alignment via Rank Transformation
- Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment
- Rank-Constrained Adaptation for Reliable Real-World Performance
- RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
- Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
- Rank-Transformed Dissimilarity Profiles for High-Dimensional Classification
- RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache Compression
- RANSAC Scoring Done Right
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
- RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud
- RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
- RAPDrive: Shared-Latent Hybrid Decoding for Reasoning and Planning in Autonomous Driving
- RAPTOR: Ridge-Adaptive Logistic Probes
- Rare-Class Signal Suppression in Long-Tailed Multi-Expert Fine-Tuning
- Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
- Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
- Rare-Tail Statistics For Learning Biased Gaussian Halfspaces with Label Noise
- RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark Subsets
- Rate-Constrained Edge Metadata for Sender–Receiver Generative Video Super-Resolution
- Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
- Rational Tuning of LLM Cascades via Probabilistic Modeling
- RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers
- RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
- RAVEN-Bench: A Paired EO-IR Video QA Benchmark for Aerial Multimodal Understanding
- Raven: High-Recall Sequence Modeling via Sparse Memory Routing
- RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
- RaVF: Learning Radar Velocity Fields via Spatial-Doppler Guidance
- RAWild: Toward Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
- Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
- RayTun3R: Online Camera Adaptation in 3D Foundation Models
- RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
- RB-LDC: Redundancy-Balanced Latent Coding for Robust Diffusion
- RCSTAT: A Statistical Framework of Relative Contextualization in Transformers
- Reaching a Consensus in Predictive Loops
- REACT: A Lightweight Reliability-Aware Framework for Spatio-Temporal Out-of-Distribution Prediction
- REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers
- Readiness-Aware Sample Selection for Noisy Labels with Class Imbalance
- Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMs
- Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
- Reading, Not Thinking: Bridging the Modality Gap When Text Becomes Pixels
- Reading Positional Coupling in Transformers with Diffusion Scores
- Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
- Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning
- Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
- Read-Only Zero-Shot Classifier Expansion from Pairwise Semantics
- Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
- RealDev-QA: Trajectory-Level Diagnosis for Developer RAG Under Real-World Noises
- RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
- Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?
- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
- RealityTest: How People Probe AI Identity and Whether Models Disclose It
- ReaLM: A Unified Red-Teaming Benchmark for Physical-World VLMs
- REAL-MED: Benchmarking LLM Agents on Real-World Medical Tasks
- Real-Time Conversational Agents: Toward Natural Multimodal Interaction
- Real-Time Multimodal Conversational AI
- Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
- Real-World Dual-Pixel Raindrop Removal: A New Benchmark and Degradation-Adaptive RWKV Baseline
- Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
- Reasoning-Aware IRT: Explainable Evaluation of Test-Time Scaling in Reasoning Models
- Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation
- Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object Detection
- Reasoning Gestures: LLM-Inferred Communicative Functions for Co-Speech Gesture Generation
- Reasoning over Coupled Receptive Fields: Eliminating Subgraph Redundancy at Scale
- Reasoning Pathologies in Large Language Models: A Diagnostic Perspective
- Reasoning Poisoning: Utilizing Social-Engineering to Steer Chain-of-Thought
- ReasoningShield: Safety Moderation over Reasoning Traces of Large Reasoning Models
- Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
- Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models
- Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
- Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards
- Reasoning with Sampling: Cutting at Decision Points
- Reasoning with Undecoded Tokens in Diffusion Language Models
- Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs
- Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
- Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
- Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
- RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
- RECIPE: Learning to Rank Complete Precursor Sets for Inorganic Retrosynthesis
- RECIPE: Procedural Planning via Grounding in Instructional Video
- RecMem: Recurrent Memory Compression for Long-Sequence Recommendation
- Re:Cognize - A Framework for Open-Set Sequential Character Re-Identification
- ReCoG: Relational Concept Graph for Training-Free Personalization
- Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models
- Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning
- Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
- Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
- Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
- Reconsidering Positional Supervision in Masked Diffusion Language Model Training
- Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
- Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
- ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
- RecoverBench: A Systematic Benchmark for Error Recovery in Robotic Manipulation
- Recovering Clean Evaluation Metrics from Contaminated Benchmarks
- Recovering Evolving User Preference State via Adaptive Interaction-aware Representation Correction
- Recovering the Apresjan Hierarchy Using Linkage-Based Clustering
- ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
- Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
- Recreating Video Arenas via Automated Preference Scoring
- Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
- Recursive Language Models
- Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
- Recursive Multi-Agent Systems
- Recursive Semantic Divergence for LLM Agent Consistency
- REDACTED-Tunes: An Open 1.4M-Track Dataset and Perceptual Benchmark for AI-Generated Music
- Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
- Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data
- Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
- RedVLA: Physical Red Teaming for Vision-Language-Action Models
- ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
- Re-evaluating Confidence Remasking in Masked Diffusion Language Models
- Re-evaluating Continual Learning with Few-Shot Adaptation
- Re-examining Low Rank adaptation for private LLM fine-tuning
- Refactoring Code Through Library Design
- RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
- Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons
- Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection
- Refinement as a Service: Algorithmic Predictor Refinement
- RefineTok: Scale-Wise Tokenization for Progressive Visual Refinement
- Refining Compositional Diffusion for Reliable Long-Horizon Planning
- ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
- Reflected Schrödinger Bridge Matching
- Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
- Reflection with Action-Induced Visual Differences for Desktop GUI Agents
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
- ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
- ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections
- REFLEX: Reflective Evolution from LLM Experience
- REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
- REFORM-3D: A Representation-Centric Evaluation Framework for 3D Medical Vision Foundation Models
- Reformulate LLM Reinforcement Learning for Stable Training under Black-box Discrepancy
- Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
- Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution
- ReFPO: Reflow Regularization for Flow Matching Policy Gradients
- ReFree-S2V: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
- REGATE: Confidence-Calibrated Integration of Temporally-Aligned Exogenous Texts for Dynamic Graphs
- ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
- ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation
- ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization
- RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
- Region-Normalized DPO for Medical Image Segmentation
- Register Anything Model for Generalizable and Robust Point Cloud Registration
- Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration.
- Regret Minimization in Single-Dimensional Contract-Design with Binary Actions
- Regret-Optimal Wasserstein-Robust Regression
- Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
- ReGuidance: Diffusion Steering with Strong Latent Initializations Solves Hard Inverse Problems
- Regularization Paths for Continuous DAG Learning
- Regularized Large Neighborhood Search
- Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning
- Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow Models
- Reinforced Evidence-Aware Long Video Understanding
- Reinforced Fast Weights via Next-Sequence Prediction
- Reinforcement Learning Agents Are Swimmers
- Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images
- Reinforcement Learning for Code Optimization
- Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
- Reinforcement Learning for Experimental Sciences: Bridging the Simulation-to-Reality Gap
- Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
- Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines
- Reinforcement Learning for View-Adaptive Distillation in 3D Gaussian Compression
- Reinforcement Learning from Rich Feedback with Distributional DAgger
- Reinforcement Learning-Guided Symbolic Execution for Efficient and Exploitable Smart Contract Analysis
- Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
- Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation
- Reinforcement World Model Learning for LLM-based Agents
- Reinforcing Multimodal Reasoning Against Visual Degradation
- Reinforcing VLAs in Task-Agnostic World Models
- REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
- REINS: Learning Inertia-Induced Geometry for Physics-Consistent Motion Representation in Clinical Gait Phenotyping
- Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
- RelAgent: LLM Agents as Data Scientists for Relational Learning
- Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation
- Relation-Aware Graph Foundation Model
- RelationVGGT : Visual Geometry Transformers for 3D Spatial Relation Segmentation
- Relative Energy Barriers for Copyright-Aware Language Model Adaptation
- RelaVPR: Relation-Based Knowledge Distillation for Efficient Visual Place Recognition
- Relaxation-Aligned State Control for Test-Time Scaling in Generative Combinatorial Optimization
- Relaxed On-Policy Distillation: Selective Credit Allocation for Scaling Reasoning Efficiently
- Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
- Relevance Is Not Necessity: Selecting the Necessary API Set for Tool-Using LLMs
- RelFlexformer: Efficient Attention Transformers for Integrable Relative Positional Encodings
- RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding
- Reliability-Budgeted Edge–Cloud Adaptation for Continual Multimodal Dehazing on UAV
- Reliability-Coupled Manifold-Aware Diffusion for Missing-Modality Inference
- Reliable Abstention under Adversarial Injections: Lower Bounds and New Upper Bounds
- Reliable Chain-of-Thought via Prefix Consistency
- Reliable Clustering and Quantization via Distortion-Constrained Optimal Transport
- Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration
- ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
- Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies
- Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
- Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees
- Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
- Remote Photoplethysmography Based on a Skin Reflection Exponential Model
- Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation
- Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
- Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
- Rep2Text: Decoding Full Text from a Single LLM Token Representation
- RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities
- RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space
- RePiD: Efficient Recursive Pixel-Space Diffusion via Hierarchical Patch Denoising
- Replay-buffer engineering for noise-robust quantum circuit optimization
- Replicability is Asymptotically Free in Multi-armed Bandits
- Replicable Constrained Bandits
- Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment
- RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
- RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
- Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
- RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation
- RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
- RepoZero: Can LLMs Generate a Code Repository from Scratch?
- Representation Forcing for Bottleneck-Free Unified Multimodal Models
- Representation Fréchet Loss for Visual Generation
- Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
- Representation Preconditioning for Efficient Diffusion Model Training
- Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
- Representations for the Physical Sciences
- Representing Part-Whole Hierarchy with Nested Neuronal Coherence
- Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
- Requential Coding: Measuring Model Compressibility by Coding Data Instead of Parameters
- Reranking with Intra-modal Visual Association for Text-to-Image Person Re-Identification
- ReSAM: Representation-Level Safety Margin Alignment for Vision–Language Models
- RESBev: Making BEV Perception More Robust
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
- RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
- RescueBench: Can Embodied Agents Save Lives in the Wild?
- ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
- ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
- Reset Dependence Is Embodied: Training Protocol Changes Which Morphologies Appear Optimal
- ResFusion: Medical Image Fusion Driven by Implicit-Forward Diffusion and Time-aware Joint Optimization
- Residual-Autoregressive Context for 3D Gaussian Splatting Compression
- Residual Calibration via Local Feature-Space Refinement
- Residual Expertise Is Not Decision Value
- Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
- Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
- Resilient Byzantine Agreement with Predictions
- Resilient Latent Readouts for Long-Context Question Answering
- Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data
- RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
- ResKV: Residual-based Channel-wise Unstructured Pruning for KV Cache Compression
- ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction
- Resolution-Aware Structural Density Peak Clustering
- Resolvent Ellipsoid for Minty Set Inclusions
- Resolving AdaBoost Cycling with LLMs: A Computer-Assisted Counterexample
- Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
- Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting
- Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data
- Response Time Enhances Alignment with Heterogeneous Preferences
- Responsible Communication of Machine Learning Research in Biomedicine
- Restoring the RNA-Ligand Interaction Manifold via Topology-Preserving Contrastive Learning under Epistemic Uncertainty
- ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search
- Rest-Tuning: Data-Efficient Adaptation of EEG Foundation Models to Individuals via Resting-State Signals
- Retain-Neutral Surrogates for Min-Max Unlearning
- Rethink Action Chunking in VLA Through Human Motor Control
- Rethinking Attention in Depth for Operator Learning
- Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
- Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching
- Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
- Rethinking Contrastive Targets in Radiology Language-Image Pretraining
- Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response
- Rethinking Cross-Layer Information Routing in Diffusion Transformer
- Rethinking CT Synthesis through Semantics-Structure Alignment
- Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
- Rethinking Diffusion Decoding via Structural Commitment
- Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language Models
- Rethinking Expressivity and Efficiency in Test-Time Training
- Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions
- Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation
- Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective
- Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
- Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm
- Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
- Rethinking Knowledge Distillation for Diffusion Language Models
- Rethinking Language Model Scaling under Transferable Hypersphere Optimization
- Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model
- Rethinking Layer-wise Model Merging through Chain of Merges
- Rethinking Learning from Label Proportions via Moment Matching
- Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
- Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
- Rethinking LoRA Initialization for Robust Asymmetric Learning Rates
- Rethinking Memorization–Generalization Trade-Off in Generative Models
- Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
- Rethinking Neural Nonlinearity as Gating
- Rethinking On-Policy Self-Distillation for Thinking Models
- Rethinking Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient Coordination
- Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models
- Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
- Rethinking Projector Training in Multimodal LLMs
- Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
- Rethinking Radar 3D Perception: Representation Learning from Raw Spectra
- Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
- Rethinking Reward Models for Multi-Domain Test-Time Scaling
- Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
- Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
- Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
- Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
- Rethinking Sequential Locate-Then-Edit: Optimality and Stability
- Rethinking Softmax Attention: Polynomial Activations for Transformers
- Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
- Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?
- Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
- Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection
- Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
- Rethinking Time Series Tokenization from a Frequency Perspective
- Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement
- Rethinking Vector Field Learning for Generative Segmentation
- Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
- Rethinking Visual Reasoning in Text-to-Image Reward Modeling
- Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
- ReToken: One Token to Improve Vision–Language Models for Visual Retrieval
- RETR: A Structure-Preserving RGB-Event Transformer for Robust 3D Lane Detection
- Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
- Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
- Retrieval from Within: An Intrinsic Capability of Attention-Based Models
- Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
- Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
- Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
- Retrieve-then-Rerank Inference for Vocabulary-Based End-to-End Driving
- Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
- Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
- Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle
- Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
- Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking
- Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
- REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
- Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks
- Reversing the Roles of Signal and Noise: Modeling Noise in Astronomical Images without Paired Data
- Revisiting Activation Steering Through an Optimization Lens
- Revisiting Autoregressive GCNs for Vehicle Routing Problems
- Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
- Revisiting Decentralized Online Convex Optimization with Compressed Communication
- Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
- Revisiting Diffusion Model Predictions Through Dimensionality
- Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
- Revisiting Gradient Ascent: Machine Unlearning from a Geometric Perspective for Source-Free Scenarios
- Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
- Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
- Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
- Revisiting the Adam–SGD Gap Beyond Single Factors
- Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models
- Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures
- Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
- Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective
- Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
- Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection
- ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion
- Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
- Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning
- Reward-Conditioned Reinforcement Learning
- Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower
- RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs
- Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
- Reward Hacking in Rubric-Based Reinforcement Learning
- Reward Inflation: A Healthy Stimulus for Reinforcement Learning
- Reward Is Not a Universal Interface for Generative Reinforcement Learning
- Reward Modeling for Multi-Agent Orchestration
- Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
- Reward Shaping to Improve Language Model Query Generation
- Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation
- RGF: Recursive Generative Framework for the Edge-Cut Separable Problems
- R-GRec: Relation-Guided Generative Recommendation via Collaborative Graph Supervision
- RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding
- RiboC2F: Pose-First Coarse-to-Fine Flow Matching for Protein-Conditioned RNA Co-Design
- RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
- Richer or More Gates? Fan-In Trade-offs in Learnable Logic Circuits
- Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
- Riemannian Admissibility Flow for Offline-to-Online Safe Reinforcement Learning
- Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
- Riemannian Lyapunov Framework: Optimization as Closed-Loop Control on Riemannian Manifolds
- Riemannian Optimization for Low-Rank Adaptation via Desingularization
- Riemannian Ordinary Least Squares
- RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
- Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
- Right Results, Wrong Reasons: Auditing Behavioral Reliance in Motion Forecasting
- RigidFormer: Learning Rigid Dynamics using Transformers
- RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning
- RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video
- RigRecon: Efficient Rig-Aware Street Reconstruction via Dual-Path Spatio-Temporal Interaction
- RILA: A Radar-Native Structured Interface from Sparse mmWave Point Clouds to Large Language Models
- RipBench: A Unified Benchmark for Multi-Level Rip Current Detection, Classification and Segmentation
- Ripple in Still Water: Zero-Shot Clustering in Heterogeneous Federated Learning with Wavelet Scattering Transform
- RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation
- RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
- RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization
- RISE-Video: Can Video Generators Decode Implicit World Rules?
- Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
- Risk-Aware Action Repetition via Expected Skip Evaluation
- Risk-Calibrated Context Selection for Healthcare Multi-Agent Handoff
- Risk-Controlled Post-Processing of Decision Policies
- Risk-guided Estimation-aware Acceptance for Learning with Synthetic Data
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction
- Risks Create a Jagged Frontier of LLM Productivity Gains Across Computer Occupations
- Risk-Sensitive Deep Optimal Stopping
- RIVET: Regex-to-Indexable Keys via Neural Translation for Interactive LIMIT-k Retrieval
- RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
- RL Excursions during Pre-training: How early is too early for on-policy learning?
- RL-Guided Contraction of Symbolic Tensor Networks for Quantum Circuit Equivalence
- RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
- RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
- RnR: a meta-solver for causal discovery in undersampled time series data
- RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
- ROAD: Rule-Grounded Context-Aware Open-World Driver Anomaly Detection
- ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games
- RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
- RoboExo: Structure-Guided Wrist-to-Exocentric Video Generation for Scalable Robot Learning
- RoboPAD: Post-Training Adaptation of Robot Foundation Models
- RoboProcessBench: Benchmarking Process-Aware Understanding in Visual-Language Robotic Manipulation
- Robot Demonstration Videos Should Include Transparency Disclosures
- Robot Learning with World Models: Capabilities, Frontiers, and Challenges
- RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
- Robust Amortized Simulation-Based Inference via Learned Error Models
- Robust and Efficient Backdoor Mitigation for ML Models via Tolerant Property Testing
- Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration
- Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling
- Robust and Hard-to-Remove GNN Watermarking via Topological Invariant Perception
- Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication
- Robust Approximate Nearest Neighbor Search for Any Dataset
- Robust-by-Design Distributional Learning from Contaminated Samples
- Robust Concept Unlearning in Diffusion Models via Directional Stability Regularization
- Robust Conditional Conformal Prediction via Branched Normalizing Flow
- Robust Diffusion Models via Divergence-Induced Weighted Denoising
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions
- Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
- Robust Flow Matching under Target Corruption and Label Noise
- RobustGenBench: A Benchmark for Robust Generalization to Adversarial and Common Perturbations, with Applications to Vision and Vision-Enabled Large Language Models
- Robust Graph Diffusion Model
- Robust Hopfield Decision Transformer
- Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures
- Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
- Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
- Robust Latent Space Bayesian Optimization with Marginalized Kernel
- Robust Multi-view Clustering against Imperfect Information
- Robust Nash Alignment under Preference Uncertainty
- Robust Noisy Inductive Matrix Completion with Local Linear Convergence
- Robust Offline Reinforcement Learning against Out-of-Distribution Dynamics in Autonomous Driving
- Robust PAC Learning of Concurrent Stochastic Games
- Robust Policy Optimization to Prevent Catastrophic Forgetting
- RobustPruner: Decoupled Relevance and Uncertainty for Efficient Visual Token Pruning in MLLMs
- Robust Residual Correction via Selective Deployment for Time Series Forecasting
- Robust Reversible Recovery for Adversarially Protected JPEG Images
- Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts
- Robust Statistical Estimators with Bounded Empirical Sensitivity
- Robust Stream Classification using Time Neutralising Decision Trees
- RobustStress: Stress-Testing AI-Generated Text Detectors under Gradual Perturbations
- Robust Surrogate Modeling for Explainable Graph Neural Networks
- Robust Task-Aware State Estimation from Pre-trained Perception
- ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression
- ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
- ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
- Roll2Depth: Zero-Shot Metric Depth Estimation Exploiting Camera's Rolling Shutter Effect
- Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
- RoLL: Robust Low-Rank Learning via Nesterov Momentum
- ROLLVERIFY: BRIDGING EFFICIENCY AND ACCURACY IN LONG-TAIL ROLLOUT REINFORCEMENT LEARNING
- RoMo Hands: A Large Scale Richly Organized Text to Hand Motion Dataset
- Root Cause Analysis of Measurement and Mechanistic Anomalies
- Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness
- RoPE Is Not a Proper Relative Position Embedding
- RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
- RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning
- ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models
- Rosetta: Composable Native Multimodal Pretraining
- RoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning
- ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
- Rotation-Invariant Vector Normalization for Molecular Force Learning
- Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
- RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism
- RotVLA: Rotational Latent Action for Vision-Language-Action Model
- Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection
- Route-Consistent Adaptation for Stable Quantization of Mixture-of-Experts Models with Theoretical Guarantees
- Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts
- Routing as a Singular Reparameterization: A Closed-Form Pushforward Prior and Exact Bayesian Complexity in a Minimal Proxy
- RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks?
- Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
- Row-Private Symmetric Cone Programming: Scale-Efficient Algorithm and Lower Bound
- RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
- RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers
- RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
- RRL-HOI: Reflective Reinforcement Learning for Open-Vocabulary HOI Detection
- RSPO: Reasoning-Supervised Policy Optimization for Long-Tail Autonomous Driving
- RSPReg: Reliability-aware Structural Prototype Learning for Point Cloud Registration
- RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
- RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking
- RSSA: Robust Semantic and Spatial Aligner for Collaborative Perception
- RTCBench: Evaluating Tool Use of Large Language Models Beyond Oracle Access
- RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
- Rubato: Signature Attention for Irregular Multivariate Time Series Forecasting
- Rubato: Transcribing Piano Music with Timestamps
- RubiConv - Efficient Boundary-Respecting Convolutions
- Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics
- RUBRIC-MME: Real-User Behavior-grounded Rubric for Multimodal Interaction Capability Evaluation
- RuleSmith: Multi-Agent LLMs for Automated Game Balancing
- Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup
- Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
- Runtime Verification of Multiple Natural Language Criteria for Agent Governance
- RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities
- RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models
- RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation
- RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
- RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control
- RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis
- RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
- S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks
- S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation
- S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation
- S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
- S²MoE: Shared-Subspace Mixture of Sparse Experts
- s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
- S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
- S3Former: Sequential, Structural, and Statistical Fusion for Continuous-Time Dynamic Graphs
- SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
- SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
- Saddle-to-Saddle Dynamics in Self-Supervised Shortcut Learning
- Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents
- Safe Active Learning with Future Viability Guarantees in Time-Series Models
- SAFE-DRIFT: Data Selection for Supervised Fine-tuning with Controllable Off-Target Drifts
- SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMs
- Safe Evolution with Circuit Anchors
- Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
- SAFE-FEC: Semantically Constrained Adversarial Frontier Evolution for Factual Error Correction
- Safe Few-Step Generation via Velocity Editing
- Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
- Safeguarding Mutual Correction in Source-Free Domain Adaptation via Cut Statistics
- SAFE-Hair: Scalp-Anchored Fields for Exportable Single-View Hair Reconstruction
- Safe in Its Own Words: Self-Guided Safety Alignment for Multimodal Reasoning Models
- Safe Linear Bandits with Unknown Safety Gaps
- Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance
- Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
- Safe-PG-LQR: Provably Safe, Convergent and Optimal Model-Free Linear Quadratic Regulator with Hard Constraints
- SafePro: Generation of Safe and Functional Proteins via Cross-Task Conflict-Aware Alignment
- Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
- SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
- Safety-Aware Latent Space Reasoning in Large Language Models
- Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
- Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
- SAFTAC: Simulation-Augmented Fine-Tuning of Open-Source LLMs for Analog Circuit Design
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- SAGE: Evidence-First Biomarker Discovery through Multi-Agent Reasoning
- SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
- SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
- SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
- SAGE: Semantic-Agnostic Image Embedding for Generalized AI-Generated Image Detection
- SAGE: Semantically Disentangled Representation Learning through Latent Geometry Constraint and Large Language Model
- SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation
- SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation
- SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning
- SALART-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images
- Saliency-Aware Multi-Route Thinking: Grounding and Reasoning on Vision-Language Agents
- SALT: When More Rollouts Don’t Help in Group-Based Policy Optimization and How to Make Them Matter
- Salvation Lies Within: Proactive Prefix Re-forming for LLM-based Tagging
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
- SamaDICE: Safe Multi-Agent Reinforcement Learning with Stationary Distribution Correction Estimation
- SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product
- SAMAT: A Stereotype-Aware Multimodal Transformer for Interpretable Misogynistic Meme Detection
- Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
- Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy
- Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
- SAME: Stability-Aware Embedding Extraction in Mixture-of-Experts Language Models
- Same Words, Different Judgments: How Preferences Vary Across Modalities
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology
- Sample Complexity of Linear Regression under Random-Location Coordinate Corruptions
- Sample complexity of stochastic optimization with integer variables
- Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
- Sample-Efficient Optimization over Generative Priors via Coarse Learnability
- Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds
- Sample Size Design for Bounds on Discrete Probabilities of Causation
- Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
- Sampling-Based Safe Reinforcement Learning
- Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
- Sampling Is Not Curiosity: Why LLM Agents Should Investigate
- SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
- Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
- SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis
- Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
- SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
- SAPO: Step-Level Skill-Augmented Policy Optimization for Multi-Turn LLM Agents
- SARA: Step-Adaptive Rank Adjustment for Diffusion Inference Acceleration
- SarcBench: A Bilingual Benchmark for Contextual Sarcasm Understanding, Response, and Generation
- SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
- SASA: Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
- SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
- SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery
- SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards
- SAVE: Sparsity-Aware Influence Estimation for Vocabulary-Expanded LLMs
- SAX: Advancing Video Diffusion Models for Sequential Action Execution
- SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?
- Say the Same, Act Differently: Text-Orthogonal Action Subspaces in Reasoning Vision-Language-Action Models
- SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
- SC$^3$: A Multi-Solvent Solubility Challenge and Benchmark
- Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction
- Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
- Scalable Derivative Gaussian Processes via Exact Gradient Reduction
- Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
- Scalable Fair Learning via Cramér-von Mises Regularization
- Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
- Scalable Minimal-Change Learning for Controllable Image Editing
- Scalable Multi-Agent Contrastive Reinforcement Learning
- Scalable Neural Safety Certification via Monotonicity
- Scalable Supervised Optimal Transport of Gaussian Mixture Models
- Scalable Token-Level Hallucination Detection in Large Language Models
- Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
- ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
- SCALECUA : Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
- Scale-Invariant Empirical-Bayes Laplace Approximation for ReLU Networks
- Scale-mixture Langevin sampling in the subspaces of recurrent cortical circuit dynamics
- Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale
- Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models
- Scaling Arbitrary Architectures and Optimizers with Automatic Parameterization
- Scaling Causal Reasoning with Increasingly Complex Causal Simulators
- Scaling Full Conformal Image Classifiers
- Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
- Scaling Genomic Language Modeling with Unified Corpus and Evaluation in Bacteria
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
- Scaling Laws for Multimodal Data Mixtures
- Scaling Laws for SAE Training Data
- Scaling Laws for Synthetic Pretraining in Radio-Map Prediction
- Scaling Limits of Long-Context Transformers
- Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
- Scaling Multi-Teacher Distillation for Digital Pathology
- Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining
- Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations
- Scaling Point-in-Time Language Models: Economic Evaluation of Embeddings
- Scaling Reward Modeling without Human Supervision
- Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet
- Scaling Whole-Body Loco-Manipulation through Compositional Data Synthesis
- ScAn-Bench: Evaluating Scaling Analysis Methodology
- Scattered by Design: Why Per-Output Pruning Resists Structured Compression
- SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers
- SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
- Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing
- SceneAligner: 3D-Grounded Floorplan Localization in the Wild
- SceneBind: Binding What and Where Across Vision, Audio, and Language
- SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
- Scenes as Objects, Not Primitives : Instance-Structured 3D Tokenization from Unposed Views
- SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding
- SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation
- SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition
- SchedDiff: Diffusion-Based Priority Refinement for Job Shop Scheduling
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema
- SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
- Scheming Is a Symptom: Alignment Research Should Probe Reflexive Fragility
- SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review
- SCHTs: A Semi-Structured Dynamic Sparse Training Framework for Hardware-Efficient Deep Learning
- SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
- SCION: Scene Composition via Instanced Neural Primitives
- SciReason: A Controllable Benchmark for Scientific Reasoning in LLMs
- SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
- scMAF: Single-Cell Multi-Omics Clustering via Adaptive Modality Fusion
- SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
- ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
- SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
- Score-based Variational Inference via Quantum Maximally Mixed States
- SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objectives
- SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts
- ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
- ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation
- Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
- Screening Lipid Nanoparticles through Structure-Ratio Alignment
- ScreenSearch: Uncertainty-Aware OS Exploration
- ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening
- scShapeBench: Discovering geometry from high dimensional scRNAseq data
- SCTI: Self-Calibrated Trident Identification of Black-Box LLM Watermarks
- scTrilemma: Balancing Identity, Invariance, and Reconstruction in Single-Cell Representation Learning
- SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
- SDAE: Semantic-Diversity-Aware Exploration for Efficient Reinforcement Learning in Large Language Models
- SDFlow: Similarity-Driven Flow Matching for Time Series Generation
- SDHilb: Schrödinger Dynamics-Guided Neural Network with Adaptive Multi-Scale Hilbert Transform for Time Series Forecasting
- SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation
- SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning
- SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
- SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
- Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
- SeaPilot: Mobile Agent with Self-refining Environment Alignment
- Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
- Search-Augmented Masked Diffusion Models for Constrained Generation
- Search, Edit, and Fold: LLM-Guided MSA Optimization for Protein Conformation Prediction
- Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
- Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
- Search-Tree Scaling in Parallel Monte Carlo Tree Search
- SearchV: Evolutionary Fine-Grained Visual-Token Skipping for Efficient Vision-Language Models
- SEAR: Sample Efficient Action Chunking Reinforcement Learning
- Second-Order Complexity of Neural ODE Inference
- Second-Order Complexity Theory for Neural Networks
- Second-Order Complexity Theory for Risk, Explanation, and Calibration in Machine Learning
- Second Workshop on MLxOR: Mathematical Foundations and Operational Integration of Machine Learning for Uncertainty-Aware Decision-Making
- SecureClaw: Clawing Back Control of LLM Agents
- Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
- Securing AI Agents with Information-Flow Control
- S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs
- SEED: Self-Speculative Decoding via Implicit Encoder–Decoder
- Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
- Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
- Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes
- Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation
- Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning
- Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
- Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning
- Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation
- Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation
- Seeing the World through Any Eyes
- Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models
- Seeing Together, Acting Apart: Shared Environmental Understanding for Multi-Robot Navigation
- Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
- See it to Place it: Evolving Macro Placements with Vision Language Models
- Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
- SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
- Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery
- See, Read, Compare: Candidate-Aware Verification for Agent Test-Time Scaling
- SeeSE3: The Emergence of 3D Space in Vision Features
- See to Believe: Segmentation by Reasoning with Visual Evidence
- Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
- SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
- Segment and Select: Vision-Language Segmentation in 3D Scenarios
- Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
- SEISMOS: A Statistical Signal Detection Framework for Semantic Chunking
- Selected-Tail Reliability in Verifier-Guided Best-of-$N$ Inference
- Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation
- Selective Answering for Medical VQA via Parallel Independent Claim Verification
- Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making
- Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
- Selective Off-Policy Reference Tuning with Plan Guidance
- Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
- Selective Safety Steering via Value-Filtered Decoding
- Selectivity and Shape in the Design of Forward-Forward Goodness Functions
- Selectivity Makes State-Space Models Universal Sequence Approximators
- Select Smarter, Not More? Prompt-Aware Evaluation Scheduling with Submodular Guarantees
- Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
- Self-Adjoint Flow Policy Optimization
- Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling
- Self-Cleaning Diffusion Models
- Self-Compacting Language Model Agents
- Self-Consuming Generative Models with Co-Evolving Human Preferences
- Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization
- SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
- Self-Distillation of Hidden Layers for Masked Self-Supervised Representation Learning
- Self-Distilled RLVR
- Self Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale
- Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
- Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
- Self-Evolving Agents Should Build Internal and External Models of the World
- Self-Evolving Diversity-Driven Search for Robust AI Systems
- SelfGuard: Self-Supervised Deviation Modeling for Multi-Modal Jailbreak Detection
- Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
- Self-Improving World Modelling with Latent Actions
- Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery
- Self-Programmed Execution for Language-Model Agents
- Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment
- Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
- Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
- Self-Supervised Doppler-Guided RF Odometry
- Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
- Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
- Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
- Self-Supervised Reconstruction Knockoffs for Calibrated Unsupervised Feature Selection
- Self-Trained Verification for Training- and Test-Time Self-Improvement
- Self-Tuning Graph Filters via State-Dependent Operator Composition
- Selling Information While Being an Interested Party
- Semantically Complementary Spectral Views Learning for Graph-Level Anomaly Detection
- Semantic-Bridge Federated Learning: Bridging CLIP Semantics for Heterogeneous FL
- Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
- Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models
- SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
- SemanticDLM+: Improving Diffusion LLMs through Bias-variance Trade-off in Transition Kernel Design
- Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-Spoofing
- Semantic-level Exploration for Multi-Agent Reinforcement Learning
- Semantic-Level Invariant Representation Learning for Cross-Hospital Clinical EEG Modeling
- Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
- Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
- Semantic Priors Meet Statistical Evidence: Robust Forests for Few-Shot Tabular Learning
- Semantic Residual: A Paired-Oracle Decomposition of LLM Multi-Agent Systems under Lossy Channels
- Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
- Semantic Search over 9 Million Mathematical Theorems
- Semantic-Statistical Prior Banks for Federated Low-Shot Learning under Non-IID Clients
- Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation
- SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
- Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity
- Semiparametric Efficient Tests for Interpretable Distributional Treatment Effects
- SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
- SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
- SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph Encoding
- Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
- SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
- Separating Common and Unique Directions for Model Merging
- SePO: Self-Evolving Prompt Agent for System Prompt Optimization
- SeqDiCO: Sequence-oriented Diffusion for Scale-Generalizable Neural Combinatorial Optimization
- Seq-LoRA: Sequential Bayesian Low-Rank Adaptation for Large Language Models
- Sequence-to-Sequence Modeling with Camera-Induced Priors for Multi-View Stereo
- Sequential Behavioral Watermarking for LLM Agents
- Sequential Membership Inference Attacks
- Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
- Sequential Probability Assignment against Smoothed Adversaries with Unknown Base Measure
- Sequential Solution Concepts in Cooperative Games with Generalized Characteristic Functions
- Serialization Tax in Shared-Latent Exchangeable Decisions
- SetAD: Semi-Supervised Anomaly Learning in Contextual Sets
- SETA: Scaling Environments for Terminal Agents
- SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
- Settling Pure Differentially Private Covariance Estimation
- Settling the Sample Complexity of Deterministic Agnostic PAC Learning
- Severity-Controlled Prediction Sets for Medication Recommendation
- SF-DST: Adapting Vision-Language Models for Anomaly Detection via Asymmetric Modulation and A-LoRA
- SFPR: Structural Fingerprinting for LiDAR-to-OpenStreetMap Place Recognition
- SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
- SGD at the Edge of Stability: The Stochastic Sharpness Gap
- SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws
- SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
- SGEvolve: Semantic Gradient Guidance for LLM-Driven Evolutionary Search
- SGNNBench: A Holistic Evaluation of Spiking Graph Neural Networks on Large-scale Graphs
- SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs
- ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language Models
- ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
- ShadowTransfer: A Geographic Transfer Benchmark for Overhead Shadow Detection
- Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
- Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
- Shared-Noise Mechanisms for Verifiable Differentially Private Counting
- Shared Truth: Emergent Truth Properties in Large Language Models via Heterogeneous Injection-based Transfer
- Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
- Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization
- Sharper Regret Bounds for Shampoo
- Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
- Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation
- Sharpness of Minima in Deep Matrix Factorization
- Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks
- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
- Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
- SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining
- Shellsort as Multi-Scale Relaxation: Learning Spectrum-Matched Gap Schedules
- She Performs Your Voice: A Unified Speech and Dance Motion Model
- Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
- Shift-Aware Identity-Guided Latent Refinement for Referring Audio–Visual Segmentation
- Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
- ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
- ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents
- Short-Context Dominance: How Much Local Context Natural Language Actually Needs?
- Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
- Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
- SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
- SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural Network
- SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
- SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
- SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
- SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study
- SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models
- SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
- Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
- SignalBench: Comparing Dense Feedback Methods for Long-Horizon Agents
- Signature Approach for Contextual Bandits with Nonlinear and Path-dependent Rewards
- Signature-Kernel Evaluation Metrics for Robust Probabilistic and Tail-Event Forecasting
- Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
- Signed-Permutation Coordinate Transport for RMSNorm Transformers
- Signed Rectified Flow: Negativity Controlled Generation
- SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation
- SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir Generation
- SiliconBench: Speed, Memory, and Fidelity for LLM Inference on Apple Silicon
- SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
- Sim2Science: ML with Imperfect Scientific Models
- SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity
- SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
- Similarity-Constrained Reweighting for Complex Query Answering on Knowledge Graphs
- Simmer: A Scalable Pretraining Recipe for Video-Text Encoders
- Simple Baselines are Competitive with Code Evolution
- SimpleEvol: Efficient Intelligence Conversion via Less Human Prior in Automated Heuristic Design
- Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
- Simple KNN-Based Outlier Detection Achieves Robust Clustering
- Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
- Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics
- SimplexUQ: An Evaluation Framework and Benchmark for Conformal Uncertainty on Simplex-Valued Predictions
- Simple yet Effective Budget-Feasible Procurement Auctions for Submodular Welfare Maximization
- Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
- Simplicity is Enough: ReAct Agents for Prompt Optimization
- Simplified Reversible Residual Networks
- Simplifying Transformer-Based U-Net Neural Physics Simulators
- SimpliHuMoN: Simplifying Human Motion Prediction
- SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization
- SimSD: Simple Speculative Decoding in Diffusion Language Models
- Simulating Human Memory with Language Models
- Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
- Simulation-aided Reinforcement Learning with Control Variates
- Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
- Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
- Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
- Simultaneous Gradient Learning in First-Price Auctions
- Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems
- SimVLA: Attributing Gains in VLA Models Through Controlled Ablation
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
- SING-CH: Task-Scale-Agnostic Lifelong Cross-Modal Hashing on Statistical Manifolds
- Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-Spoofing
- Single Shot HDR Recovery via a Video Diffusion Prior
- Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
- Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
- SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards
- SitCom: Scaling Egocentric Multi-Party Spoken Dialogue for Situated Communication Assistance
- SituRecBench: A Benchmark for Situated Recommendation in 3D Interactive Environments
- Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
- Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
- Skill-Adaptive Noise Scheduling for Diffusion Policies
- SkillCIR: Intent-Guided Skill Composition for Training-Free Composed Image Retrieval
- Skill-Coupled Policy Optimization with Calibrated Group-Wise Advantage Estimation
- SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
- SkillGen: Verified Inference-Time Agent Skill Synthesis
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- Skill-Level Effects in Behavioral Cloning: When Low-Skill Data Improves Performance
- SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- SkillOrchestra: Learning to Route Agents via Skill Transfer
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
- Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization
- SkipSR: Faster Super-Resolution with Token Skipping
- Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates
- SkiP: When to Skip and When to Refine for Efficient Robot Manipulation
- SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
- SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
- SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
- Sliced Inner Product Gromov–Wasserstein Distances
- Sliced Wasserstein Meets Quantum Optics: Provable Wavefunctions Tomography with Scarce Noisy Measurements
- SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
- SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization
- Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation
- SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
- SLiDE: Structured Linear Dynamics for Forecasting with Exogenous Inputs
- SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth Pruning
- SLM-Agents: 1st Workshop on SLMs for Agentic Systems
- SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
- SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
- SLOT-IR: Learning Disentangled Slot Representations for Infrared Spectral Unmixing
- Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
- Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
- SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data
- SLVMBench: Skill Learning from Video Memory
- SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
- Small Model Portfolios for Many Deployment Profiles: Submodular Coverage under Bundled Constraints
- Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
- SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
- SMASH: Probing Speech Recognition Robustness via Semantically Targeted Bit Flips
- SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery
- SMI: Semantic Medical ID for Hierarchy-Aware Concept Representation
- SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
- SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
- sMMC-22M: A Context-Aware Dataset and Benchmark for Single-Cell Spatial Transcriptomics
- SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
- SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization
- Smoothed Elicitation Complexity for Approximate $\Gamma$-calibration of Discrete Classification Tasks
- Smoothed Score Queries and the Complexity of Sampling
- Smooth Flow Matching for Synthesizing Functional Data
- Smooth Partial Lotteries for Stable Randomized Selection
- Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions
- SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
- SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
- SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
- SO(3)-Equivariant Learning on CAD Boundary Representations
- SOAP-Bubbles: Effective and Scalable Variational Learning with Structured Covariances
- SOAR: Regression-based LiDAR Relocalization for UAVs
- SOAR: Semantic Organ-Aware Pretraining for 3D CT Image Understanding
- Sobolev Regularized MMD Gradient Flow
- SoccerNarrate: Event-Grounded Streaming Soccer Commentary with Macro-Window Preference Alignment
- SocialAgent: Second Workshop on Large Language Models for Social Reasoning and Simulation
- Social Choice Foundations for Simulation-Augmented Generation
- SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
- Social Interaction Breaks Replicate Independence in Controlled-Clone LLM Agents
- SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
- SODA: Selective Optimization with Deferred BN Alignment for Efficient Dataset Distillation
- SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
- Soft Contamination Means Benchmarks Test Shallow Generalization
- Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
- Soft geometric inductive bias for object centric dynamics
- Soft-Radial Projection for Constrained End-to-End Learning
- Soft Token Alignment for Cross-Lingual Reasoning
- SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
- SOLAR: AI-Powered Speed-of-Light Performance Analysis
- Solaris: Building a Multiplayer Video World Model in Minecraft
- SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
- SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
- Solver-as-Teacher: Solver-Guided On-Policy Post-Training Framework for PDE Foundation Models
- Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
- Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
- Solving Stochastic Control under Multiplicative and Internal Noise via Constrained Optimization
- SolvMix: Learning Formulation-State Landscapes for Liquid Electrolyte Conductivity Prediction
- Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models
- SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection
- Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
- Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
- Sound Verification of Deployed Neural Networks
- SourceBench: Can AI Answers Reference Quality Web Sources?
- Source-Causal Control of Historical Context in Longitudinal Radiology Report Generation
- SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models
- SP$^3$: Spherical Priors for Plug-and-Play Restoration
- Space-Aware World Models: Spatial Persistence Through Factored Scene Representations
- Space Group Conditional Flow Matching
- Space-Optimal Streaming Algorithms via Efficient Encodings
- SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
- SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers
- SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide Shots
- SPANUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
- SPA-Q: Structure-Preserving Adaptive Post-Training Quantization for Monocular Depth Estimation
- SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
- Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
- Spark: Path-Aware Experiential Self-Evolution for VLMs Spatiotemporal Reasoning
- Sparse All-Layer Connector for Domain Generalised Semantic Segmentation
- Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
- Sparse Attention as Compact Kernel Regression
- Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
- Sparse blind deconvolution via thresholded Wirtinger flow
- Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
- Sparse Expansion Utility: Identifying and Routing to Pivotal Steps in LLM Reasoning Chains
- Sparse Fine-Tuning for Parameter-Efficient Adversarial Training
- Sparse Internal Control of Language Models
- Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
- Sparse Layers are Critical to Scaling Looped Language Models
- Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge
- Sparsely Supervised Diffusion
- Sparsely Wired Mortal LLM Inference
- Sparse Multimodal Switching State-Space Models for Regime-Dependent Neural Connectivity under Partial Observations
- Sparse Planning in Visual World Models via Cost Gradients
- Sparse Repair in Reasoning Traces: A Structural View of Test-Time Inference
- Sparse Reward Subsystem in Large Language Models
- Sparse Sum-of-Squares Layers for Certified Learning
- Sparse Updates Generalize Better Than Optimization: Stability Analysis for Randomized Subspace Descent
- Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
- Sparsifying Correlation Clustering: Edge Coresets, Triangle Witnesses, and Observation Lower Bounds
- Sparsity for Free: A Budget-Induced Equilibrium in Joint Topology–Parameter Search
- SpatialBench: Is Your Spatial Foundation Model an All-Round Player
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
- SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting
- SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
- Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
- Spatially Feasible 3D Indoor Scene Generation via Interaction-Oriented Human Proxy
- Spatially-Grounded Long Video Generation with Self Geometry Forcing
- Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
- Spatial-temporal Attributes Enhanced Prompt Weighting and Fusion for Video Recognition
- SpatialVAM: Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy
- SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning
- SPDEBench: An Extensive Benchmark for Learning Stochastic PDEs
- Speak Early: Speculative Speech Generation for Low-Latency SpeechLLMs
- Speakeasy: Auditing Cheap Signals in Peer Prediction
- SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
- SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
- SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
- SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
- SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
- Specialist Mediators: Causal Localization of Dense Fine-Tuning
- Specialists Hold, Generalists Discount: Asymmetric Equilibrium in LLM Routing Auctions
- Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo
- SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
- SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
- Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
- Spectral-Aligned Pruning for Universal Error-Correcting Code Transformers
- Spectral Alignment in Forward–Backward Representations via Temporal Abstraction
- Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization
- Spectral Asymptotics of Neural Network Jacobians: Convergency, Universality, and Phase Transition
- Spectral Degeneration of Softmax Attention under Isotropic Score Geometry
- Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting
- Spectral Estimation with Deformed Decompression
- Spectral Feedback for Test-Time Alignment of Protein Diffusion Models
- Spectral Geometry of Attention: From Information Routing to Uncertainty
- Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
- Spectral Identifiability for World Models: Polynomial Projectors, Resolvent Stability, and a Krylov Bottleneck
- Spectral Insights from the Unconstrained Feature Model for Neural Multi-Output Regression
- SpectralKV: Redundancy-Aware KV Cache Compression via Spectral Coreset Selection
- Spectrally Decomposed Equivariant Graph Neural Networks for Interatomic Potentials
- Spectrally Parameterized Neural Inverse Reconstruction
- Spectral Measures of Mamba Conductances Predict and Shape Effective Receptive Fields
- Spectral Progressive Diffusion for Efficient Image and Video Generation
- Spectral Quantum Memory for Implicit Neural Representations
- Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
- Spectral Re-Basin for Linear Mode Connectivity
- Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards
- Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting
- Spectral-Spatial Interpretation
- Spectral-Sphere-Constrained Hyper-Connections
- Spectral Stratification of Semantic Abstraction in Vision-Language Models
- Spectral Transformer Neural Processes
- Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model
- Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
- Speculative Decoding Is Per-Token, Not Path
- Speculative Self-Distillation enables Efficient Knowledge Internalization
- Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer
- Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
- Speed Predictions for Online Energy-Efficient Scheduling
- Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent Reasoning
- SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
- SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding
- SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere
- SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
- SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
- Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian Splatting
- Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
- Spherical Flows for Sampling Categorical Data
- Spherical Interpolation for Backward-Compatible Multimodal Representations
- SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
- SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
- Spikes as Detectors: Phase-Conditioned Spiking Dynamics for Time-Series Anomaly Detection
- Spike-SFT: Selective Parameter Enhancement and Fusion for Efficient Spiking Neural Networks
- SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
- SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting
- Spike-to-Field Mechanisms of Turbulence-Like Dynamics in Spatial Spiking Neural Networks
- SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays
- Spiking neural network initialization for scale-invariant maximization of entropy
- Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF
- Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks
- SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents
- SPIRIT: Speed-Driven Online Adaptation for Self-Speculative Decoding
- Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
- SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
- SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants
- Split and Bridge: Multimodal Generation via Diffusion Bridging
- Split-and-scale Latent 3D Representations
- Split-RL: Local Conflict Resolution in Reinforcement Learning
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
- Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting
- SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
- Sponsored Questions and How to Auction Them
- spora: A Unified Multimodal Dataset for Spatial Proteomics
- Sport Is The Next Grand Challenge For Artificial Intelligence: Toward A Science Of Human Physical Skill
- SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
- SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers
- SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation
- SPRM: From Cooperative Games to Marginal-Contribution Process Reward Modeling
- S&P: Towards Scalable and Powerful Graph Learning with Hierarchical Structural Acquisition
- SQUEEZE: Preserving Homeomorphism and Smooth in Higher-Dimensional Flows
- Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
- SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction
- SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios
- SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
- SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
- SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
- SS3D: End2End Self-Supervised 3D from Web Videos
- SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks
- SSD: Shell-Guided Spherical Diffusion for Molecular Geometry Generation
- SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
- Stability and Diversity of Networked Self-Consuming Generative Ecosystems
- Stability and Generalization in Looped Transformers
- Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch
- Stability-Constrained Regime-Aware Forecasting for Heterogeneous Panel Time Series
- Stability-Enhanced Federated Learning with Accelerated Gradient
- Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis
- Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
- Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal
- Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
- Stabilizing Few-Shot Object Detection with Language-Conditioned Probabilistic Prototypes
- Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- Stabilizing Off-policy LLM Optimization with Prefix Importance Ratio
- Stabilizing Policy Optimization via Logits Convexity
- Stabilizing RL+Search for Imperfect-Information Extensive-Form Games
- Stabilizing the Dynamic Low-Rank Training
- Stable3R: Streaming 3D Reconstruction with Stable Geometric References
- STABLE: A Continual Learning Optimizer with Adaptive Drift Control
- Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts
- Stable and Granular Policy Optimization for Generative Recommendation
- Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs
- StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
- Stable GFlowNets with Probabilistic Guarantees
- StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
- Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators
- Stable Max Coverage Under a Cardinality Constraint
- Stable Partial Order Constraints for Temporal Causal Structure Learning
- Stable Resolution-Invariant Emulation in Entropically Controlled Kinetic Methods
- StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
- stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
- STAC-R: Subspace-Tracked Activation Compression with Residuals
- StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching
- Stage-Aware Dual Alignment for Covariate Shift in Graph Domain Adaptation
- Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning
- Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
- StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
- StakeBench: Evaluating Language Understanding Grounded in Market Commitment
- StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
- Standardization of Post-Publication Code Verification is Possible with the Support of the Community
- Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
- STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
- STAR: Boosting Time Series Foundation Models for Anomaly Detection Through State-Aware Adapter
- StarCraft Motion: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios
- STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
- STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
- STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision
- StaRPO: Stability-Augmented Reinforcement Policy Optimization
- StarWM: Self-Supervised Trained Attention Routing for Robust World Models
- State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods
- State Augmented Flows
- State Copying Crowds Out Reasoning: Mechanistic Evidence for Delta Planning in Autoregressive Models
- State Evolution Awareness for Category-agnostic 3D Point Cloud Tracking
- StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
- State of Thought Enables Endogenous Reasoning
- State-Resolving Attention for Length-Extrapolating Transformers
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
- Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models
- Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding
- Static-to-Dynamic: Animating Still Mattes via Generative Motion for Video Matting
- Statistical Complexity of Soft Bellman Residual Minimization
- Statistical Convergence of Spherical First Hitting Diffusion Models
- Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
- Statistical field theory for Markov decision processes under uncertainty
- Statistical Inference in Causal Partial Identification under Smooth Densities
- Statistical Limits of Affine Equivariant Estimation
- Statistical Matching via Schr\"odinger Bridge beyond Conditional Independence
- Statistical Mixing Guarantees for Contractive Echo State Networks
- Statistical Query Lower Bounds for Smoothed Agnostic Learning
- StatLUT: Statistical Feature-Driven Multimodal 3D LUT Generation for Photorealistic Style Transfer
- Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
- ST-Bridge: Bridging Sketch and Text with Large Language Models for Coarse-to-Fine Image Retrieval
- STDec: Spatio-Temporal Stability Guided Decoding for dLLMs
- ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
- SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization
- Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
- Stealthy World Model Manipulation via Data Poisoning
- Steer2Edit: From Activation Steering to Component-Level Editing
- SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting
- Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
- Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
- Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
- Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
- Steering Optimisation Trajectories in Diffusion Representation Learning
- Steering Vectors as a Training Signal in LLM Post-Training
- Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
- STEER: Route-Aware Adaptive Reasoning for Autonomous Driving
- Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
- SteerVTE: Seamless Video Text Editing with Style and Glyph Control
- Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
- Stein Transport for Generative Modeling
- StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
- STEMFly: Enhancing UAV Vision-Language Navigation via Sensor Grounding, Temporal Diversity and Episodic Memory
- StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
- Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
- StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
- Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
- STEP: Learning STructured Embeddings for Progressive Time Series
- Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
- Step-wise Rubric Rewards for LLM Reasoning
- StereoPep: Do Molecular Models Understand Stereochemistry? A Benchmark on Synthetic Diastereomeric Peptides
- StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting
- StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
- StiCAS: Compositional Activation Steering via Stiefel Manifold Coordinate Transport
- Sticky Jump Diffusions: A Unifying Framework for Discrete, Continuous, and Hybrid Diffusion
- STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
- StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
- Stitched Value Model for Diffusion Alignment
- Stochastic Approximation Approach for Decentralized Optimization on Time Varying Random Networks
- Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
- Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability
- Stochastic Heat Diffusion Models
- Stochastic Interpolants via Conditional Dependent Coupling
- Stochastic Matching Bandits with Rare Optimization Updates
- Stochastic Matching via Local Sparsification
- Stochastic Optimization with Random Search
- Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise
- StomataBench: Measuring Taxonomic Generalization in Stomatal Detection
- Stop Calling It Reinforcement Learning in Language Models Without Clear Improvement Claims: Decision-Process Cards as a Reporting Standard
- Stop Mechanizing Reform Heuristics as Scientific Quality Filters in AI Review
- Stop or Restart? Principled Inference Control for Large Reasoning Models via the Pandora's Box
- Stop Quantum Machine Learning; do AI-for-Quantum instead
- Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels
- Stop Using Plausibility as the Criterion for Explainable AI
- StoSplat: Ray-Aligned Stochastic Preconditioning for Feed-Forward 3D Gaussian Splatting
- STParOpt: An End-to-End Framework for Execution-Aware Parallelism Inference and Optimized CUDA Migration
- STRABLE: Benchmarking Tabular Machine Learning with Strings
- STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
- Stranger Things: When Objects Appear Without Their Typical Neighbours
- StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- Strategic Causal Policy Learning: Welfare, Safety, and Fairness Thresholds
- Strategic Decision Focused Learning
- Strategic Decision Support for AI Agents
- Strategic Evaluation: Incentivizing AI Capability Coverage with Private Benchmarks
- Strategic Feature Selection and Regularization
- Strategic PAC Learnability via Geometric Definability
- Strategist: Designing Agentic Reasoning at Scale
- StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
- Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
- StreamMind: Dynamic Streaming Cognition for Online Video Understanding
- StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
- StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
- StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
- STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
- Strengthening LLMs for Tabular Prediction with Structural Priors
- Strengthen Out-of-Distribution Detection via Adaptive Mahalanobis Gap
- Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
- Stress-Testing Neural Network Verifiers with Provably Robust Instances
- STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts
- STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
- Stroke-Audited Quadratic Bezier Splatting with Structural Initialization for Efficient Painting Rendering
- Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
- Strongly Adaptive Online Learning with Time-Varying Movement Cost
- (Strongly) Replicable Distribution Testers imply High Probability Distribution Testers
- Strong Post-Training from Permissive, Reasoning-Dominant, Web-Scale Pretraining
- Strong Stochastic Flow Maps
- Strong Teacher Not Needed? On Distillation in LLM Pretraining
- StructBridge: Structure-Grounded 3D Indoor Object Generation via 3D Latent Diffusion Bridge and Normal Refinement
- StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
- Structural Blindness in Latent Data Assimilation: Representation Geometry Misleads Sensor Design
- Structural Causal Bottleneck Models
- Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning
- Structurally Separated DAG Learning with Multi-Scale Normalized Closure
- Structural Rationale Distillation via Reasoning Space Compression
- Structural Self-Teaching for Compositional Generation in Unified Multimodal Models
- Structural Support Certificates for Mechanistic Hypothesis Selection
- Structure-Adaptive Estimation of Heterogeneous Treatment Effects with Kernel Methods
- Structure-agnostic Causal Representation Learning
- Structure-aware Reinforcement Learning for Protein Directed Evolution
- Structured Coupling for Flow Matching
- Structured Human-Like Agentic Flow for RTL Design
- Structured Masked Diffusion for Joint Multiuser Decoding
- Structured Sparse Memory for Recurrent Reasoning
- Structured State-Space Regularization for Generation-Friendly Image Tokenization
- Structured Transforms for Low-Overhead Quantization of Language Models
- Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding
- Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
- Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
- Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness Prediction
- Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis
- Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration
- Structure, Subspace and System: Push the Real Limit of Extremely Low-Bit Quantization for MoE-LLMs
- Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy
- Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
- StylePlan: Style-Conditioned Intent Planning for Zero-Shot Coordination
- StyleRoute: Diffusion Style Transfer via Regional Routing and Conflict-aware Projection
- StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
- Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
- Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment
- Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference
- Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
- Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
- Subliminal Learning Is Steering Vector Distillation
- Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation
- Sublinear Time Quantum Sensitivity Sampling
- Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters
- Submodular Benchmark Selection
- Submodular Clustering beyond $1-1/e$
- Submodular Multi-Agent Reinforcement Learning for Effective Online Distributed Task Allocation
- Subprocess-Constrained Markov Decision Processes
- Subset-Conditioned Boundary Compensation for Missing-Modality Multimodal Classification
- Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning
- Substrata: Know What You Don't Know
- SudoBench: A Contextual Authorization Benchmark for LLM Agents
- SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
- Super-Level-Set Regression: Conditional Quantiles via Volume Minimization
- Superplatforms Are Strategically Compelled to Counteract AI Agents
- SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy
- SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation
- Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
- Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing
- Sup-Norm Error under Proportional Asymptotics: Phase Transitions under Linear Regression
- Support Before Frequency in Discrete Diffusion
- Support Mismatch as a Benchmark Failure Mode for In-Context Prediction
- Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery
- Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
- SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
- SurGe: Improved Surface Geometry in Point Maps
- SurgReasoner: Surgical Reasoning Segmentation with Dynamic Difficulty-Aware Reinforcement Learning
- SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics
- Surjective Pseudo-Invertible Neural Networks
- Surprise, Episodic Context, and Catastrophic Forgetting in LLM Fine-Tuning: An Empirical Study
- Surprises in Proper Positive-Only Learning
- Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch
- Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
- SurvCancel: A Longitudinal Dataset and Benchmark for Dynamic Order Cancellation Prediction in On-Demand Ride-Sharing Systems
- SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
- Survival Transformers for Longitudinal Data Analysis: Application to Atrial Fibrillation Risk from ECG
- Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
- Susceptibilities for Neural Networks Learning from Physical Data
- Sustainability in the Loop: AI Model Development Should Be Multi-Objective
- SVDP: Training-Free Contextual Sparsity Predictors for Fast LLM Inference
- SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D Classification
- SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
- Swarm Shepherd: Securing Multi-Agent Ecosystems Against Persistent Latent Compromise
- SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
- SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
- SWE-Crafter: Scaling Executable Multilingual Software Engineering Data with Meta-Skill Agents
- SWE-Git-Bench: A Focused Worktree-Level Benchmark for Real Merge Conflict Resolution
- SWE-GPU-Bench: Can Language Models Solve Real-World GPU Software Engineering Tasks?
- SWE-Marathon: Can AI Agents Autonomously Complete Ultra-Long-Horizon Software Work?
- SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization
- SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
- SwiftFlow: An Efficient One-Step Policy Learning via Improved Mean Flow for Robotic Manipulation
- Swift Sampling: Selecting Temporal Surprises via Taylor Series
- SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
- Swimba: Switch Mamba Model Scales State Space Models
- SwitchLingua V2: Agent-Driven Code-Switching via Digital Clones
- Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
- SymDrift: One-Shot Generative Modeling under Symmetries
- Symmetric Interventions for Eliciting Model Intent
- Symmetry and Geometry in Neural Representations NeurIPS Workshops 2026
- Symmetry-Guaranteed Prediction of High-Order Tensor Properties for Crystalline Materials via Irreducible Decomposition
- Symmetry Guarantees Statistic Recovery in Variational Inference
- SympFNO: Structure-Preserving Fourier Neural Operators for Physical Surrogate Modeling
- Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
- Symplectic Normal Coordinates Flow for Generative Modeling of Hamiltonian Systems
- Symplectic Parallel Scan: A Neural Hamiltonian Framework for Accelerated Scientific Simulation
- Symplectic Reck: In-Situ Learning of Gaussian Quantum Operations
- Synaptic Strength Controls Trainability and Structural Stability in Rank-Deficient RNNs
- SynBench: A Benchmark for Differentially Private Text Generation
- SyncLight: Single-Edit Multi-View Relighting
- SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
- SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
- SynerVLA: Exploiting Embodied Execution Phases for On-Device Dual-System VLA Acceleration
- SynGeo: Synergizing Seeing and Proving through Revisable Geometric States
- SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting
- SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
- SynMQG: Disentanglement and Mutual-Information Optimization for Synergistic Multi-modal Question Generation
- Synsema: Syntax-Guided Learning of Semantically Valid Programs
- SynTeX-FL: Cross-Modal Text Transfer in Federated Learning for Medical Visual Question Answering
- Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
- Synthetic Anchor-Assisted Prototype Alignment for Heterogeneous Federated Learning
- Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
- Synthetic Tasks for Training AutoResearch
- Synthetic Web: Benchmarking Language Agents under Adversarial Search Ranking
- Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs
- SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
- SynthHair: Leveraging MetaHumans for a High-Quality 4K Hair Matting Dataset
- Synthon Contrastive Learning for Synthesizable 3D Molecule Generation
- Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models
- Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
- T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
- T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval
- T3-S2S: Training-free Triplet Tuning for Sketch to Scene Generation
- TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning
- TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering
- TabDLM: Free-Form Tabular Data Generation via Joint Numerical–Language Diffusion
- TabK: Amortized Bayesian Estimation of the Number of Clusters in Tabular Data
- TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
- Tabular Foundation Model for Generative Modelling
- TabWorld: A World-Modeling Foundation Model for Tabular Generation
- Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
- TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
- Tactile MNIST: Benchmarking Active Tactile Perception
- TAC: Timestamped Audio Captioning
- TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs
- TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
- Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
- TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery
- TailAdapt: Heavy-Tailed Sparse Variational Adaptation for Long-Tailed Class Incremental Learning
- Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
- TailCon: Mitigating Tail Signal Erosion through Memory Consolidation for Long-Tailed Recognition
- Tail Cues, Principal Corrections: Plug-and-Play Rectification for Open-Set Test-Time Adaptation
- TailDiff: Elicitable Tail-Guided Diffusion for Risk-Sensitive Generation
- TailFix: Mitigating Error Accumulation and Correcting Tail Deterioration in Long-Horizon Forecasting
- TailGuard: Subgroup Tail Coverage Theory for Safe LLM Alignment
- Tail-Risk-Aware Stackelberg Learning
- Tail Wags the Model: Generalization and Membership Privacy Trade-offs of Sharpness-Aware Minimization
- Take It or Leave It: Intent-Controlled Partial Optimal Transport
- Taking Low-Rank LLM Compression a Step Further: A Global Perspective with Fused Inference
- Taking the Road Less Scheduled with Adaptive Polyak Steps
- TALES: Text-Adventure Learning Environment Suite
- Talk Less, Work More: Communication-Efficient Decentralized Stochastic Approximation
- TALK: One-Shot Batch Design for Protein Variant Effect Prediction
- TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
- TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant
- Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
- Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge
- Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation
- Taming the Tails: Why Distributionally Robust Optimization Needs New Theory for Imbalanced Regression
- TanGCE: Manifold-Aware Concept Erasure
- Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence
- TANGO: RNA Topology and Geometry Co-Design
- Tapes Together Strong: The Co-evolution of Computation and Cooperation
- TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
- Target-Aligned Reinforcement Learning
- Target-Aware Nuisance Shaping for Object Detection
- Target-Budget Best-Function Identification for Scaling-Law-Guided Model Selection
- Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling
- Targeted Synthetic Control Method
- TargetSage: Identifying Therapeutic Target Genes with Interpretable and Robust LLM Reasoning
- TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
- Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning
- Task-Driven Bayesian Experimental Design Yields Singly Intractable Objectives for Joint Policy Training
- TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
- Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
- Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents
- Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
- TasteBench: multimodal benchmark for sensory prediction, from molecules to sustainable foods
- Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
- TaxaAdapter: Scaling Fine-grained Species Image Generation To the Tree of Life
- Tcell: Mitigating Harmful Fine-tuning for Large Language Models via Gradient Alignment
- TDBench: Benchmarking Vision Language Models on Top-Down Image Understanding
- Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies
- Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
- Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
- Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
- Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving
- Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
- TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization
- TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios
- Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
- Temperature Guidance For Robust Reward Conditioning In Diffusion Planning
- Temperature-Regulated Stochastic Sampling for Diffusion-Based High-Quality Molecular Generation
- Tempered Guided Diffusion
- TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model
- TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
- Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models
- Temporal Backtracking Search for Test-time Generative Video Reasoning
- Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics
- Temporal Concentration from Rollout Errors: Implicit Preference Optimization For Text-to-Video Diffusion
- Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning
- Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
- Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models
- Temporal Pair Consistency for Flow Matching
- Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
- Temporal-Scale Sensitivity in Time-Series Tokenization and Scale-Robust Token Estimation by Gated Sum
- Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design
- Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs
- Temporal Smoothness Constraints on Efficient Neurobiological Codes Imply Temporal Specialization
- TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
- TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
- TENG-BC: Time-Evolving Natural Gradient for High-Accuracy Neural PDE Solvers with General Boundary Conditions
- TensorCommitments: A Lightweight Verifiable Inference for Large Language Models
- Tensorion: A Tensor-Aware Generalization of the Muon Optimizer
- Terminal Failure Is Not Computational Failure: A Pre-Collapse Readout Regime in Nonlinear Dynamical Learners
- TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
- TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
- TerraMesh-Masks: Open‑Vocabulary Segmentation for Earth Observation
- TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
- TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents
- Tessellations of Semi-Discrete Flow Matching
- Tesserae and MoDiCo: A Billion-Fragment Dataset and Multi-Branch Architecture for File Fragment Classification
- Testable and Actionable Calibration for Full Swap Regret
- Testable Learning of General Halfspaces under Massart Noise
- Testing and Estimation of Contextual Generalized Thurstone Models
- Test-Time Adaptation via Self-Reinforced Optimal Transport for Zero-Shot OOD Detection with Vision–Language Models
- Test-Time Compute Games
- Test-Time Conditioning with Representation-Aligned Visual Features
- Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
- Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
- Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling
- Test-Time Graph Recalibration: Enhancing Robust Zero-Shot Inference for Graph Foundation Models
- Test-Time Learning with an Evolving Library
- Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
- Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
- Test-Time Prompt-Agnostic Decomposition
- Test-time Risk Adaptation with Mixture of Agents
- Test-time Scaling for Diffusion Language Models with Frequency-Aware Remasking
- Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
- Test-time Scaling of Diffusions with Flow Maps
- Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
- Test Time Search Requires Training for Diversity
- Test-Time Sequential Steering of Diffusion Models via Preconditioned Crank-Nicolson
- Test-Time Speculation
- Test time training enhances in-context learning of nonlinear functions
- Tethered Predictive-Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems
- Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning
- Text-Based AI Tools for Research Integrity Must Be Audited on Linguistic Fairness Before Deployment
- TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
- TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
- Text-side fragility in contrastive vision-language retrieval
- Text-to-CAD Evaluation with CADTests
- \texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
- Text-Vision Co-Instructed Image Editing
- TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization
- TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
- TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation
- TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
- The $1/\mathcal{W}$ Law: Context Length is the Dominant Energy Lever in LLM Inference Fleets
- The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
- The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted For
- The Agentic Web: Networked, Continually-Adapting Agent Ecosystems
- The AI Observatory: A Public Measure of Real-World AI Use
- The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning
- The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network
- The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
- The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
- The Alignment Illusion in Multimodal Large Language Models
- The Alignment Tax Concentrates in Output Projections
- The Alternation Depth Principle for Neural Operator Design
- The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
- The BabyVLM Workshop: Toward Developmentally Plausible Multimodal Systems
- The balance between feature learning and collapse in generative dynamical systems
- The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife
- The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
- The Bayesian Learning Rule Beyond KL Geometry
- The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities
- The Benefits of Temporal Correlations: SGD Efficiently Learns k-Juntas from Random Walks
- The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
- The Block Catastrophe of Marginal Calibration in Certified Requirements Traceability
- The Butterfly Effect in Reasoning: Branch-Structured Distributional Memory for Stochastic Agents
- The BV4 Benchmark for Unsupervised Anomaly Detection in High-Dimensional Spectral Data Streams
- The Capability Frontier of GRPO
- The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
- The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
- The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
- The Complexity Kink: LLM Rubric Instruments for Causal Inference on Code Generation Reliability
- The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
- The Confusion is Real: GRAPHIC – A Network Science Approach to Confusion Matrices in Deep Learning
- The Constitutional Coverage Trilemma in AI Governance
- The Cost of Absolute Position: A Spread-Expressivity Tradeoff for Additive Positional Encodings
- The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
- The Cost of Symmetry: Universality and Hardness for Permutation-Invariant Neural Networks
- The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
- The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation
- The Dead Salmons of AI Interpretability: The Need for a Statistical Inference Perspective
- The Denoising Wrapper: A Modular Post-Processing Framework for Noisy First-Order Optimizers
- The Design Space of Tri-Modal Masked Diffusion Models
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
- The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
- The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection
- The End Justifies the Mean: Linear Ranking Rules for Proportional Sequential Decisions
- The Era of Agentic Organization: Learning to Organize with Language Models
- The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
- The Fault in Our Metrics: Revisiting Generative Model Evaluation with Chamfer Distance
- The Foundation Model Transparency Index
- The Fractured Interlingua: Geometric Bottlenecks in Cross-Lingual Knowledge Editing
- The Future of Facts: Tracing the Factual Generation-Verification Gap
- The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
- The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
- The Geometry of Agent Skills: Non-Commutative Composition in Representation Space
- The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
- The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
- The Geometry of Generative Latents: Navigability and Invertibility
- The Geometry of Linear Program Compression: An Exact Characterization and Learning Algorithm
- The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
- The Graph Concept Bottleneck: Decoding Combinatorial Reasoning in GNNs for Interpretability
- The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
- The Heavy Hitter Oracle: Enhancing Frequency Estimation in Skewed Data Streams
- The Heel of RLVR: Benchmark Glory Should Not Outpace Honest Measurement
- The Hidden Power of Scaling Factor in LoRA Optimization
- The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics
- The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
- THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout
- The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy
- The Illusion of Forgetting: Rank Leakage in Knowledge Editing and Its Mitigation
- The Illusion of Multi-Agent Advantage
- The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective
- The Internal Growth Function: A More General PAC Framework for Scenario Decision Making
- The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
- The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
- The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at Scale
- The Key to Going Linear: Analysis-Driven Transformer Linearization
- The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
- The Laplacian Keyboard: Beyond the Linear Span
- The limbic navigation system as a hierarchical RNN
- The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
- The Locality Cost of Semantic Patch Self-Distillation
- The Long-Run Distribution of Regularized Learning in Non-Concave Games: A Large Deviations Approach
- The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
- The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric
- The Marauder’s Map: Bézier Manifolds Reveal Hidden Surfaces for Model Merging and Ensembling
- The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation
- The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
- The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
- The Minimax Rate of Online Isotonic Regression on Product Orders
- The Minimax Rate of Second-Order Calibration
- The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
- The Missing Corpus: Infinite Ground Truth for File-Grounded LLM Evaluation
- The Missing Positional Story in LLMs: A Case Study of Shift-Invariant Attention
- The Multi-Block DC Function Class: Theory, Algorithms, and Applications
- The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature Learning
- The Narrative Gap: Can LLMs help us Navigate Diverse Narratives Across Languages?
- The Neural Race Model
- The Optimal Control Foundation of Early Exits – Turnpikes and ResNets
- The Optimization Prior: Instilling depth for shallow networks, detail for coarse networks
- Theoretical guarantees for Banded Approximations of Gaussian Processes
- Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
- Theoretical Limits of Language Model Alignment
- Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learning
- Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
- Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
- Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
- Theory-Scale Auto-Formalization of Logics for Computer Science
- The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
- The Panel Complexity of Sortition: Is 12 Angry Men Enough?
- The parameters in weight-sparse transformers are interpretable
- The Pareto Frontier of Randomized Learning-Augmented Online Bidding
- The Path Not Taken: RLVR Learns Off the Principals
- The PFAD Not Taken: Measuring Polysemanticity via Feature Affine Decomposition
- The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
- The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training
- The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
- The Pok\'emon Theorem and other Fairness Impossibility Results
- The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm
- The Power of a Random Sample in Online Algorithms
- The Power of Menus in Dynamic Pricing: Near Optimal Regret and Equivalence Results
- The Power of Second Order Methods for Sequence Preconditioning
- The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
- The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning
- The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
- The Price of Locality: Why Forward-Forward Underperforms Backpropagation?
- The Principles of Diffusion Models: Toward Fast and Scalable Diffusion LLMs
- The Quantization Benefits of Residual-Free Transformers
- The Query Complexity of Local Search in Rounds on General Graphs
- The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative Guidance
- TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
- The Rate-Distortion-Polysemanticity Tradeoff in SAEs
- There are Levels to It: Red Teaming LLMs with Hierarchical Reinforcement Learning
- The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
- The Reciprocity Gradient
- The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction
- The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.
- The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
- The risk of KV cache compression
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
- The road reaches every place, the short cut only one: Self-Adversarial Shortcut Mitigation for AI-Generated Image Detection
- The Ruler and the Judge: Benchmark-Conditional Evaluation of LLM-as-a-Judge
- The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
- The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
- The Scaling Laws of Skills in LLM Agent Systems
- The Scaling Paradox of Tool-Calling LLM Agents Under Realistic MCP Faults
- The Score Kalman Filter
- The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
- The Shape of a Program: Path Signatures for Trace-to-Program Induction
- The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
- The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
- The Sign Code: The Hidden Binary Nature of Deep Networks
- The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility
- The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability
- The Sparsity Whisperer
- The Spectral Amplitude Principle for Dynamics of Quantum Neural Networks
- The Stability of Data Exchange in Competitive Markets
- The Stability of Online Algorithms in Performative Prediction
- The State-Prediction Separation Hypothesis
- The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix
- The Subjectivity of Monoculture
- The sublevel Flood bifiltration: towards scalable 2-parameter persistent homology
- The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
- The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
- The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
- The Symmetries of Three-Layer ReLU Networks
- The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval
- The Third Workshop on Agents in the Wild: Safety, Security, and Beyond
- The Third Workshop on GenAI for Health: Agentic Systems, Clinical Trust, and Future Potential
- The Third Workshop on Long-Context Foundation Models
- The two clocks and the innovation window: When and how generative models learn rules
- The Type Theory of Stationary MDPs: Rare Events and Uncertainty Quantification
- The Unembedding Bottleneck: A Mechanistic Analysis of Single Digit Counting in LLMs
- The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
- The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
- The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
- The VLM as Sensor: Bayesian Active Search for Long Video Understanding
- The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
- The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
- The Window for Preventive Action Before AI Saturates Most Cognitive Benchmarks is Closing
- The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models
- They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
- The Z-Gromov-Wasserstein Distance
- Think2SQL: Blueprinting Reward Density and Advantage Scaling for Effective Text-to-SQL Reasoning
- Think about how AIs think about themselves
- Think Before You Generate: Active Panoramic Exploration for Text-to-3D Scenes
- Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving
- Thinking in Boxes: 3D Editing in Real Images Made Easy
- Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
- Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
- Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
- Thinking with Imitation: Adaptive Reinforcement-Imitation Learning for Tool-Augmented Scientific Reasoning
- Thinking with Visual Primitives
- ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
- Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models
- ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
- Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
- Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
- Thompson Sampling using Prior-fitted Diffusion Transformers
- ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets
- Three Geometric Lenses on Graph Machine Learning
- TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption
- TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback
- TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics
- TIDE: Every Layer Knows the Token Beneath the Context
- TIDES: Implicit Time-Awareness in Selective State Space Models
- TIDE: Trajectory-Aware Watermark Propagation for Text-to-Image Diffusion Models
- TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
- TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
- TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
- Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials
- Tight Gap-Dependent Regret Bounds and Problem-Independent Bounds for Cost-aware Cascading Bandits
- Tight Generalization Bounds for Noiseless Inverse Optimization
- Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring
- Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
- TILT: Target-induced loss tilting under covariate shift
- TIMA: Test-Time Internalization for Agentic Memory
- TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
- TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
- Time-Frequency Decoupled Cross-Scale Partial Optimal Transport for Time Series Domain Adaptation
- Time–Frequency Non-Stationary Modeling for Multivariate Time Series Forecasting
- TimeOperator: A Function-to-Function Approach to Time Series Modeling
- Time-Sensitive Anytime-Valid Testing
- Time series analysis with Gumbel dynamics
- Time Series Foundation Models in Practice: From Forecasting to Classification and EEG Analysis
- TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
- Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks
- TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding
- TimeWarp: Evaluating Web Agents by Revisiting the Past
- Timing Is All You Need: SpikeCore, Learnable Delays, and Gain Control for Neuromorphic Classification
- Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
- Tio: Language Models with Parallel Streams of Thoughts, Inputs and Outputs
- TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
- TKCAM: Text and Keyframe to Camera Trajectory Generation
- TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
- To Align or Not To Align: Check Your COMPASS Before You Train
- To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
- To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
- To discretize continually: Mean shift interacting particle systems for Bayesian inference
- Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
- TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection
- Token-Conditional Expert Dropout: Implicit Regularization for Stable MoE Pretraining
- Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
- Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
- Tokenization and Architecture Jointly Allocate Component Roles in Time Series Transformers
- Tokenizer Choice Shapes Generalization in State-Centric Learning for Planning
- Tokenizer-Generator Coupling in Medical Image Generation
- TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality
- TokenRouter: Efficient Serving System for Token-Level LLM Routing
- Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation
- TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
- Token Time Continuous Diffusion for Language Modeling
- Token-to-Token Alignment of Text Embeddings for Semantic Blending
- ToLD: Efficient Time Series Forecasting via Tokenized Truncated Latent Diffusion
- ToMAToMP: Robust and Multi-Parameter Topological Clustering
- TOM-Pruning: Target-aware Output Manifold for LLM Pruning
- Too Aligned to be Real: Detecting AI-Generated Images via Cross-modal Alignment Shift
- Too Early for AI-Assisted Peer Review: A Systematic Account of the Limits and Opportunities of Automating Human Judgment
- ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
- Tool-Integrated Reasoning via Hierarchical Multi-Agent Reinforcement Learning
- Tool-IQA: Augmenting Image Quality Assessment with Simple Tools
- Tools as Continuous Flow for Evolving Agentic Reasoning
- ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
- Tool Verification for Test-Time Reinforcement Learning
- Too Smart to Teach: The Articulability Ceiling in Language Models
- Top-$k$ Identification with Correlated Biased LLM Judges via Anchor Leverage
- ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
- Topic-Aware Contextual Cascading Bandits
- TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
- TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
- TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
- Topological Invariance and Breakdown in Learning Dynamics
- Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction
- Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings
- Topology-Aware Optimal Transport for Source-Free Test-Time Adaptation in Anomaly Segmentation
- Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning
- Topology-Reinforced Swin Transformer for Medical Image Analysis
- TopoPrune: Robust Data Pruning via Unified Latent Space Topology
- TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation
- TopoRefine: Topology-Aware Correspondence and Residual Refinement for Training-Free Subject-Consistent Generation
- TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design
- TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
- TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
- TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting
- To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
- ToS: Tree-of-Skill Reinforcement Learning driven by Behavior Tree for Long-Horizon Manipulation
- Total Variation Distance Estimation in Autoregressive Models
- Total Variation Rates for Riemannian Flow Matching
- To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation
- To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
- Touch-R1: Reinforcing Touch Reasoning in MLLMs
- Toward a theory of Evaluability
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning
- Toward Better Geometric Representations for Molecule Generative Models
- Toward Cognitive Supersensing in Multimodal Large Language Models
- Toward Efficient Reasoning of Large Language Models via Latent Concept-Pyramid Modeling
- Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
- Toward Executable Multi-framework Front-end Code Generation with Self-Correction
- Toward in Silico Strain Evaluation: A Multimodal Surrogate for Fermentation Dynamics with Metabolic Graph Pretraining
- Toward Interactive Understanding of Code APIs
- Toward Minimal-dimensional Convex Calibrated Surrogate Losses for Classification with Rejection
- Toward Multimodal Sheet Music Recognition and Understanding
- Toward Online Robust Zero-Sum Markov Games with Function Approximation
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
- Towards Anytime-Valid Statistical Watermarking
- Towards a Unified Model for Flexible Job Shop Scheduling Problems
- Towards a Universal Causal Reasoner
- Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning
- Towards Characterizing Scientific Image Utility and Upgradability
- Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion
- Towards Complementary Keypoint Detection via Mixture of Detectors
- Towards Convergence of PPO: An Approximate Descent Approach
- Towards Differentially Private Reinforcement Learning with General Function Approximation
- Towards Direct Evaluation of Harness Optimizers via Priority Ranking
- Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
- Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
- Toward Semantically-Consistent Tuning-Free Customization for Rectified Flow Transformers
- Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
- Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning
- Towards Fair Graph Generation Without Sensitive Attribute
- Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
- Towards Financial World Modeling
- Towards Generalist Graph-Level Anomaly Detection
- Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling
- Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values
- Towards Generalizable Partially Relevant Video Retrieval
- Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
- Towards Hyperparameter Transfer for Differentially Private Optimization
- Towards Identifiable Latent Additive Noise Models
- Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
- Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
- Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
- Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs
- Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
- Towards more general control of diffusion models using Jeffrey Guidance
- Towards Multi-Human-Value Alignment via Value Localization in LLMs
- Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
- Towards Optimal Pre-training Data Mixtures for Empowering Reinforcement Learning in LLMs
- Towards Optimism-Pessimism Trade-off in Model-based Offline-to-Online Reinforcement Learning
- Towards Precise Knowledge Distillation for Large Language Models via Knowledge Probing
- Towards Principled Efficient Rollout Allocation in Test-Time Training
- Towards Principled Fine-Grained MoE Expert Pruning via Pseudo-Boolean Approximation
- Towards Principled Task Grouping for Multi-Task Learning
- Towards Realistic Conversational Multimodal Instruction Following
- Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
- Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
- Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
- Towards Reliable LLM Evaluation: Correcting the Winner’s Curse in Adaptive Benchmarking
- Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics
- Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images
- Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling
- Towards Scalable Egocentric HOI for Humanoids: Benchmarking Whole-Body Dexterous Interaction with Tactile Prediction
- Towards Self-Supervised, Generalizable and Decomposable 4D Driving Scene Reconstruction
- Towards Settling the Complexity of Non-Euclidean Parallel Convex Optimization
- Towards The Science of Multi-Agent Communication
- Towards Trustworthy Agentic AI: Interpretability, Safety, and Steering
- Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour
- Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
- Towards Understanding Self-Pretraining for Sequence Classification
- Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
- Towards Unified Dynamic Face Landmark Detection
- Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways
- Towards Universal Black-box Attacks on Graph Neural Networks
- Towards Visual Query Segmentation in the Wild
- Toward the Goldilocks Blind Compression of Quantum States
- TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
- TPRL: Adaptive Visual Token Pruning in LVLMs via Language-Guided Reinforcement Learning
- TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
- TraceDx: Criticality-Weighted Atomic Facts as a Training Signal for Sequential Clinical Diagnosis
- TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
- TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
- TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
- TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
- TraceSim: A Generative Simulator and Benchmark for Joint scRNA-seq and Lineage Tracing
- TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
- TRACE: Tourism Recommendation with Accountable Citation Evidence
- TRACE: Trajectory-Aware Conceps for Explainable Video Understanding
- TraceTriage: A Benchmark for Cost-Aware Stop-or-Continue Decisions in Delayed-Outcome Workflows
- Tracing Actual Causes with Counterfactual Witness Maps
- Tracing Agentic Failure from the Flow of Success
- TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics
- Tracing Moral Foundations in Large Language Models
- Tracing Persona Vectors Through LLM Pretraining
- Tracing Psychometric Inference in Large Language Models
- Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
- Track4D: Representing Dense 3D Tracking for Video Diffusion Models
- TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
- TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos
- TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens
- TrAction: Action Recognition with Sparse Trajectories
- Trading Sensing for Structure: Sparse IMU-EMG Fingertip Force Estimation via Neuro-inspired Structured Modeling
- Traffic STGNNs across Sensor, City, and Time Shifts: Routing Concentration Tracks Sensitivity to Sensor Dropout
- Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
- Trainable Topology Supervision under Structurally Unreliable Pseudo Supervision
- Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
- Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
- Training Agent to Scale Inference-Time Reasoning
- Training a Predictive Coding Network on ImageNet using Equilibrium Propagation
- Training-Based Backdoors Are Not Cryptographic
- Training Data Attribution in Diffusion Models via Mirrored Unlearning and Noise-Consistent Skew
- Training Deliberative Monitors for Black-Box Scheming Detection
- Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models
- Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction
- Training-Free Active Test-Time Adaptation for Vision-Language Models
- Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
- Training-Free Dynamic Upcycling of Expert Language Models
- Training-Free Entangler Selection for Quantum Neural Networks via Hilbert–Schmidt Geometry
- Training-free Focus-Ambient Retention for Memory-Efficient Video Large Language Models
- Training-Free Generative Sampling via Moment-Matched Score Smoothing
- Training-Free Open World Object Detection
- Training-free Spatially Grounded Geometric Shape Encoding
- Training-Free Task Vectors for LLM Behavioral Control
- Training Generalizable Collaborative Agents via Strategic Risk Aversion
- Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
- Training Language Models to Explain Their Own Computations
- Training Language Models via Neural Cellular Automata
- Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
- Training ML Models with Predictable Failures
- Training on Documents About Monitoring Leads to CoT Obfuscation
- Training Optimal Large Diffusion Language Models
- Training Quality Determines Efficiency Boundaries in Test-Time Reasoning
- Training Transformers for KV-Cache Compressibility
- Training Vision Transformers to Focus: Emergence of Attention Head Specialization
- Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
- Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex
- Train on the Sphere, Deploy on the Hill: Closed-Form-Anchored Surrogates for Real-Terrain Boundary-Integral Equations
- Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
- Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
- Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning
- Trajectory-Consistent Dropout for Uncertainty Decomposition in Hamiltonian Neural Networks
- Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
- Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video Generation
- Trajectory-Matching Meta Pseudo-Labeling for Semi-Supervised Learning
- Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
- TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
- TrajLift: Encoding Verbal Memory Dynamics via Heat Diffusion on Semantic Hierarchies
- TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
- TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
- Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
- Transcoder Adapters for Reasoning-Model Diffing
- Transductive Generalization for GNNs via Optimal Transport
- Transferability for General Reasoning: An Automated Curriculum for Multi-Domain LLM RL
- Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
- Transferable, Time-Parallel Graph Dynamics via Space-Time Factorization
- Transfer Entropy as a Measure of Information Flow in VLMs and LLMs
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
- Transfer Learning Through Conditional Quantile Matching
- Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
- Transformers Can Learn Multiclass Classification In-Context: Isotropy Governs Generalization
- Transformers Converge to Invariant Algorithmic Cores
- Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
- Transformers Linearly Represent Highly Structured World Models
- Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
- Transformers Provably Learn Graph Search: Training Dynamics and the Exponential Power of Depth
- Transforming Image Editors into Video Editors
- Transition-Aware Credit Assignment in Agentic Learning for LLM Reasoning
- Transitioning from Pre-training to Post-training
- TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
- TransMem: Transition-Aware Retrieval for Evolving Personal Memory
- TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
- Transolver-GMsFEM: A Hybrid Framework for High-Contrast Multiscale PDEs on Irregular Grids
- Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse
- Transporting the Past: An Optimal Transport View of Backtracking Counterfactuals
- Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
- Traversal-Invariant Positional Encoding for Serialized Graphs
- TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
- Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
- Treat Domain-Specific Languages as Design Variables in LLM Agents
- Treating Hyperparameters as Interventions: Task-Invariant Representation Learning for Transferable HPO
- TReDS: Trajectory-Grounded Requirement-Capability Modeling for Training Distribution Shaping in Tool-Interactive Tasks
- Tree-Ensemble Repair through Constrained Optimization
- TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding
- Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits
- TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision
- TreePII: Efficient Computation of Higher-Order Probabilistic Interaction Indices in Tree Ensembles
- Tree Rotary Positional Encoding for Extreme Length Extrapolation from Scratch
- Tree Search With Predictions
- Tree-Sliced Orlicz Integral Probability Metric
- Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
- Tree Training: Efficient LLM Training on Tree-Structured Trajectories
- TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference
- Trellis4D: Complex 4D Mesh Generation
- T-ReX: Learning Tile-Reuse Indexes for Structured Model Compression
- TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models
- TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
- TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions
- TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
- TriBet: Relative E-values for Online Machine-generated Text Detection
- TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG
- Trie-Aware Transformers for Generative Recommendation
- Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
- TRIM: A Theory of Retrieval with Incremental Memory -- Defect, Benefit, and Critical Horizon
- Trimming the Long-Tail of Visual World Modeling Evaluation
- TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation
- Tri-Prompting: Controllable Video Generation with Scene, Subject, and Motion Prompts
- TriPrompt: Progressive Local Prompting for Few-shot Out-of-Distribution Detection
- TriSearch: Learning to Optimize Triangulations via Bistellar Flips
- TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
- TriTD: Tri-Partite Trajectory–Distribution Distillation for Real-Time Autoregressive Video Generation
- TritonTune: LLM-Guided Multi-Agent Optimization of GPU Kernel Configurations
- Trivialized Generative Models on Lie Groups
- TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
- Tropical Boundary Complexity of Deep ReLU Networks
- Tropical Gaussian Anticoncentration: Settling Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games
- TropNNC: Structured Neural Network Compression Using Tropical Geometry
- TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
- Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification
- Truncated Riemannian (1+1)-ES for Black-Box Optimization with Intrinsic Dimension Guarantees
- TrunkFish: Making Model Width Incrementally Refinable
- Trust, but Don’t Verify: Epistemic Blind Spots in LLM Source Evaluation
- TrustFlow: Adaptive Trust Calibration for Language Model Guided Reinforcement Learning
- Trust Guided Decision Transformer
- TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation
- Trust Region Continual Learning as an Implicit Meta-Learner
- Trust Region Policy Distillation
- Trust Region Q Adjoint Matching
- Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
- Trust What Matters: Language-Conditioned Evidence Routing for Video-IMU Action Question Answering
- Trustworthy AI for Good (AI4GOOD) Workshop
- Trustworthy AI Must Account for Interactions
- Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching
- Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
- Truth as a Compression Artifact in Language Model Training
- Truthful Calibration Errors for Multi-Class Prediction
- TSB-SEG: A Systematic Time-Series Segmentation Benchmark
- TSFM Meets LLM: Context as Covariate
- TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
- TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking
- TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
- TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models
- TTCS: Test-Time Curriculum Synthesis for Self-Evolving
- TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
- TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
- Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
- Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
- Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP
- Tuning the Tuner
- TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
- TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates
- TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving
- TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
- TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
- Twisted Schrödinger Bridge Matching
- Two-Clustering Regime of Token Dynamics in Causal Attention
- Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning
- Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
- Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
- Two is better than one: designing heterogeneous scales in binary rating systems
- Two Layers of Attention Stability: A Koopman-Operator Analysis of Linear and Softmax Attention
- Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
- Two Phase Rapid Simulation Based Inference with Differentiable Simulators
- Two-Sided Learning in Matching Markets with Interviews
- Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
- Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
- Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
- U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
- UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
- UECO: A Unified Encoder with Structure-Aware Attention Mixture via Iterative Edge Evolving for Neural Combinatorial Optimization
- UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
- UGGRH: Unsupervised Generative Completion and Graph-attention Refinement for Incomplete Cross-modal Hashing
- UGM: Unified Multi-scale Genomic Event Modeling with Site-level Joint Prediction
- UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
- UltraDiff:Transferring High-Fidelity Priors to Compressed Latent Spaces for High-resolution Image Generation
- Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task
- Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
- UltraFlash: Accelerating Megapixel Visual Synthesis
- Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
- UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction
- UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
- Umbilic Multinomial Logistic Regression
- U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition
- U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting
- Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching
- Unbiased First-Order Randomized Smoothing for Differentiable Simulation
- Unbounded Streaming Text-To-Speech with Prefixed Sliding Window Attention
- UncertainGen: Scalable Uncertainty-Aware Representation Learning of DNA Sequences
- Uncertainty as an Underconstrained Axis in Lossy Compression
- Uncertainty-Aware Fuzzy Graph Contrastive Learning
- Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
- Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision
- Uncertainty Aware SURE Transfer Learning for Classification Problems
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
- Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback
- Uncertainty Quantification for Large Language Diffusion Models
- Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
- Uncertainty Quantification: From Detecting LLM Hallucinations to Strengthening Reasoning and AI Agents
- Uncertainty Quantification of Least Squares Estimator for Generalized Orthogonal Procrustes Problems
- Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
- Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem
- Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
- Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy
- Uncovering the latent structure of interwoven population and temporal codes
- Underlying Functional Structure of Reinforcement Learning
- Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
- Understanding and Mitigating Structural Forgetting in Fine-Tuned Time Series Foundation Models
- Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
- Understanding axial attention in TSFMs through single location regression
- Understanding Circulant Permutation to Extend the CMinHash Estimator
- Understanding diffusion models requires rethinking (again) generalization
- Understanding Double Descent through Universal Compression
- Understanding Generalization Requires Universal Induction
- Understanding Generalization through Decision Pattern Shift
- Understanding Goal Generalisation in Sequential Reinforcement Learning
- Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization
- Understanding Graph Self-Supervised Pre-training under Distribution Shifts: A Scaling Law Perspective
- Understanding Layer Patching in Model Size Interpolation
- Understanding Model Reprogramming: A Reachability and Relabeling Perspective
- Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
- Understanding Multi-View Transformers
- Understanding Private Evolution as Learning-Augmented Clustering
- Understanding Randomization in Greedy Model Search
- Understanding Reasoning from Pretraining to Post-Training: Chess as a Controlled Testbed
- Understanding Sample Efficiency in Predictive Coding
- Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
- Understanding the Challenges in Iterative Generative Optimization with LLMs
- Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups
- Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
- Understanding the Curse of Unrolling
- Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis
- Understanding the Effects of Neuron Dominance in Deep Reinforcement Learning
- Understanding the Interplay between Memorization and Learning in Large Language Models
- Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
- Understanding the Surprising Generalization Properties of Tabular Foundation Models
- UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
- Uni-Cheb: A Basis-Agnostic Learnable Chebyshev Filter for Multimodal Spectral Modulation
- UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
- UNICOM: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video
- UniCustom: Unified Visual Conditioning for Multi-reference Image Generation
- UniDBO: A Unified Dual-Branch One-Step Denoising Framework for Autonomous Driving Scenario Generation
- UniDG: Universal Defect Generation via Defect-Context Editing
- Unified Approach for Weakly Supervised Multicalibration
- Unified Forensic Preference Learning for Generalizable Synthetic Image Detection
- Unified Generative-Predictive Modeling for 4D Scene Understanding
- Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
- Unified Loss-Aware Density Control for 3D Gaussian Splatting
- Unified Noise Steering for Efficient Human-Guided VLA Adaptation
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models
- Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
- Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
- UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
- UniFlowDock: Flexible Docking with Complete Equivariant Velocity Fields
- Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
- Uniform-in-Time Weak Propagation of Chaos in Shallow Neural Networks
- UniForm: Segment-Aware GRPO for Joint Punctuation Restoration and Inverse Text Normalization
- Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA
- Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
- UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation
- Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
- Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
- Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
- Unifying Partner and Environment Diversity to Improve Human-AI Coordination
- Unifying Reasoning and Planning through Energy Minimization
- Unifying Sparsity and Discreteness: One-Shot Pruning for Quantized LLMs via Discrete Optimization
- UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
- UniMoE-World: A Unified Mixture-of-Experts Architecture for Scalable Multi-Control Video Generation World Modeling
- UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
- UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation
- UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
- UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
- UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks
- UniSHARP: Universal Sharp Monocular View Synthesis
- Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning
- UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
- UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
- Universal Adaptive Proximal Gradient Methods via Gradient Mapping Accumulation
- Universal and Efficient Computation with 2D Attention
- Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees
- Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities
- Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
- Universal Time Series Generation with Neural Controlled Differential Equations
- UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
- UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
- UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
- UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
- UniVR: Thinking in Visual Space for Unified Visual Reasoning
- Unlearning Diffusion Policies via Relative Fisher Forgetting
- UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?
- Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
- Unleashing the Power of Intrinsic-Entropy-Driven Exploration for Off-Policy Generative RL
- Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification
- Unlocking Any-Order Generation in Pretrained Autoregressive Image Models
- Unlocking Compositional Generalization in Continual Few-Shot Learning
- Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling
- Unlocking LLM Creativity in Science through Analogical Reasoning
- Unlocking the Duality between Flow and Field Matching
- Unlocking Volition: Proactive Intention Decoding via Interpretable Graph Learning of Multi-Region ECoG
- Unpacking the Evaluators: How Configuration Shapes the Evaluation of Alignment in Explainable AI
- Unpaired Canonical Correlation Analysis
- Unrestrained Simplex Denoising for Discrete Data. A Generative Method Applied to Graphs.
- Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics
- Unsupervised Concept Discovery with Dirichlet Concept Diffusion Models
- Unsupervised Domain Adaptation for Semantic Segmentation Based on Instance Spatial Geometry
- Unsupervised Physics Informed Decomposition of Incomplete Time-Resolved Spectroscopy
- Unsupervised Unlearnable Segmentation via Semantic Structure Disruption
- Untrusted Content Masking for Web Agents with Security Guarantees
- Unveiling Entropy-Performance Decoupling in Agentic RL for Tool-Integrated Reasoning
- Unveiling Fine-Grained Visual Traces: Evaluating MultiModal Interleaved Reasoning Chains in Multimodal STEM Tasks
- Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
- Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
- Unveiling the Value of Motion for Cinematic Camera Trajectories
- UpSafe℃: Upcycling for Controllable Safety in Large Language Models
- Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
- URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets
- Urgency-Aware Autoregressive VLMs for Unanticipated Healthcare Occurrences
- URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
- USAD: Uncertainty-aware Statistical Adversarial Detection
- Useful Memories Become Faulty When Continuously Updated by LLMs
- User Embeddings are Superpositions of Interpretable Behavioral Modes
- Utility-Constrained Policy Optimization
- Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution
- UtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models
- UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression
- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
- V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception
- V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
- V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion
- VAANI: Capturing the language landscape for an inclusive digital India
- VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
- Validating Causal Abstraction Metrics on Simulated Complex Systems
- Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
- VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V Inference
- Value-Aware Stochastic KV Cache Eviction for Reasoning Models
- Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models
- Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
- Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
- Values Are Not Single Labels: Distributional Value Profiling Across Groups and Contexts
- Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
- ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
- VAMIRec: Value-Aware Memory Intervention for Continual Recommendation
- Variable-Length Generative Protein Design via Generalized Poisson Flow
- Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
- Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
- Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards
- Variance Reduction for Expectations with Diffusion Teachers
- Variational Active Flow Matching for Discrete Online Black-Box Optimization
- Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy Evaluation
- Variational Consequence-Driven Offline Reinforcement Learning
- Variational Cover Modification Steganography
- Variational Inference via Entropic Transport Descent
- Variational Monte Carlo for Quantum Excited States via Nested Low-Rank Approximation
- Variational Trajectory Optimization of Anisotropic Diffusion Schedules
- Variational Wasserstein Model on Riemannian Manifolds for Image Segmentation
- VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
- VASR: Variance-Aware Systematic Resampling for Diffusion Models
- V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
- VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
- VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals
- VDE: Verifiable Dynamic Evaluation of Mathematical Reasoning via Typed Bipartite Graphs
- VecDBLens: A Modular Framework for Diagnosing Vector Databases Retrieval Pipelines
- VecUQ-OT: Aggregating Uncertainty Measures via Multivariate Ranks
- VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design
- Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching
- Velocity-Space 3D Asset Editing
- Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection
- VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
- Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
- Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays
- Verification-Aware Training for Speculative Decoding
- Verification-Guided Abstraction Generation with Large Language Models for Generalized Planning
- Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance
- Verifier-Backed Hard Problem Generation for Mathematical Reasoning
- Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models
- Verifiers in the Loop: Decoding Time Verification for Code Translation
- Verify0: Can AI Agents Build Formally Verified Software Repositories?
- Verifying Agents in Rubric-Graded Environments
- Verifying Neural Networks with Reinforcement Learning
- VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
- VerifyThisBench: Joint Evaluation of Code, Specifications, and Proof
- Verigrad: Verification-Driven Multi-Agent GPU Kernel Generation for High-Order MLIP Derivatives
- VeriGraph: Towards Verifiable Data-Analytic Agents
- VeriScope: Measuring Verification-Ready Verilog Artifacts
- Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
- VERITAS: Veracity-Enhanced Robust Identification of LLM-generated Text Against Style-shifts
- VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
- VeriVul: A Verification-Guided Framework for Generating Realistic Vulnerability Benchmarks
- VeriWorld: A Verifiable Visual SWE-Bench for Spatial Reasoning in 3D Environments
- Vermeer: Autoregressive generative modeling of microscopy predicts protein localization
- VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
- VeruSAGE-Bench: A Benchmark Suite for Rust System Verification
- Very Fast Bayesian Additive Regression Trees on GPU
- VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
- VESTA: Visual Exploration with Statistical Tool Agents
- VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection
- VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
- vExpert: Virtualizing Expert Storage for Adaptive Load Balancing in Distributed MoE Inference
- VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
- VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
- V-GIFT: Boosting Visual Instruction Tuning with Self-Supervised Guidance
- VI-Bench: Benchmarking Prompt Inversion from AIGC Videos
- Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence
- VicEdit: Learning to Edit Videos from Visual In-Context Examples
- ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
- ViCoR: Estimating Visual Necessity via Counterfactual Residuals for Multimodal Medical Data Selection
- VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
- VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
- Video-FLAIR: Not Whether to Reason, But How
- Video Forensic Self-Descriptions: Leveraging Temporally Distributed Forensic Microstructures for Zero-Shot Detection of AI-Generated Videos
- Video Generation Research Needs a Legally Sustainable Data Infrastructure
- VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Tokens
- VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
- Video-Mirai: Autoregressive Video Diffusion Models Need Foresight
- VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
- Video Models Can Reason with Verifiable Rewards
- VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
- VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel
- VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
- VideoSTF: Stress-Testing Output Repetition in Video Large Language Models
- Video Stitching from Multiple Moving Cameras
- Video-Zero: Self-Evolution Video Understanding
- VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models
- ViDiC: Video Difference Captioning
- VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks
- VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
- View Confidence Perception-Driven Incremental Prediction for Incomplete Multi-view Multi-label Learning
- ViewRec3D: Learning to Recommend 3D Viewpoints for AI Photography
- ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
- View-Spectral Reconciliation Learning for Text-based Multispectral Aerial–Ground Person Re-Identification
- VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
- VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
- VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
- ViLo: LiDAR Localization with Vision-Language Priors
- ViMU: Benchmarking Video Metaphorical Understanding
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
- VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning
- VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology
- ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins
- Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along
- Virtual-Flow: Virtual Microphone-based Speech Enhancement via Unsupervised Flow Matching
- Virtual Head Attention
- Virtual Task Prompting for Multi-Task Scene Understanding
- VISD: Enhancing Video Reasoning via Structured Self-Distillation
- VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual Instructions
- VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
- VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
- Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
- VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
- VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization
- Vision-Language Grounding as Bidirectional Concept Correspondence
- Vision-Language Models Should Commit to a Cézannian Specification
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
- Vision Token Pruning via Query-Vision Interaction Decomposition
- Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
- VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
- VISTA: Support-Anchored Value Targeting for Fast Flow-Based Vision-Language-Action Policies
- Visual-Advantage On-Policy Distillation for Vision-Language Models
- Visual Anchoring for Scenario-Guided Forecasting
- Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
- Visual-ERM: Reward Modeling for Visual Equivalence
- Visual Expert Skipping for MoE-MLLMs via K-Armed Bandit based Expert Estimation
- Visual Grounding First, Multimodal In-context Learning Follows
- Visual Harness: Grounding Multimodal Reasoning in Physics Engines
- Visual Instruction Tuning Aligns Modalities through Abstraction
- Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
- Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
- Visual Reinforcement Fine-Tuning via Bootstrapped Medical Reasoning
- Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI Benchmark
- Visual Text Compression as Measure Transport
- Visual-to-Executable Procedural Reconstruction of Buildings.
- VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs
- ViT-AdaLA: Adapting Vision Transformers with Linear Attention
- ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
- Viverra: Text-to-Code with Guarantees
- VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
- VLAN: Vision-Language Accessible Navigation
- VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
- VL-DocIR: A Benchmark for Vision-Based Long Document Retrieval
- VLM$^3$: Vision Language Models Are Native 3D Learners
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
- VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
- VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
- VLS: A Vision-Language-Shape Model for Open-Vocabulary Partonomic 3D Reconstruction
- VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph
- V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
- VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing
- VocalGrad: Evaluating Acoustic Perception in Audio Language Models
- Voice "Cloning" Is Actually Style Transfer
- VOID: Backdoor Injection through Knowledge Vacuity in Federated Unlearning
- Volatility-Whitened Probabilistic Residual Modeling for Long-Term Time Series Forecasting
- VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation
- VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
- VoluCore: Spanning Teacher Representations with Volumetric Coresets for Data-Efficient LLM Distillation
- Voronoi-Markov chain and spatial entropy for point pattern analysis
- Vortex: Efficient and Programmable Sparse Attention Serving
- Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding
- VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
- VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
- VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness
- VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on
- VTV-FM: Flow Matching through Variational Terminal-Velocity Closure
- VUM: Visual Unified Models for Image Generation and Perception
- VVTRec: Radio Interferometric Reconstruction through Visual and Textual Modality Enrichment
- Walking the Hypercube: Unbiased Quantum Partition Functions Without the Matrix
- Walking Through 3D Spaces: Spatial Routing for Referring 3D Gaussian Splatting Segmentation
- WASD: Wasserstein-based Knowledge Distillation for Large Language Models
- WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound Learning
- Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
- Wasserstein residuals: Learning Gradient Flows from Population Dynamics
- Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning
- WaterDescatterGS: Diverse Underwater 3D Scene Reconstruction Using Gaussian Splatting
- WATERFALL: Workflow for Adaptive Training with Evolutionary Reward Formulation and Automated Learning Loops
- Watermarking as a Learned Intrinsic Property of Diffusion Models
- Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
- Watermarking Should Be Treated as a Monitoring Primitive
- Watermarking Without Standards Is Not AI Governance
- WavCIL: Wavelet Coefficient-Domain Invariant Learning for Dynamic Graph OOD Generalization
- Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
- WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
- Wavelet Flow Matching for Multi-Scale Physics Emulation
- WaveletLoRA: Frequency-Aware Content-Style Decomposition for Personalized Image Generation
- WaveMamba: Wave-Inspired Cross-Modal Fusion for Robust event-image Semantic Segmentation
- WaveSem: Frequency-Adaptive Tokenization for Disentangling Semantics and Noise in Genomics
- WavFlow: Flowing Through Waveforms for Audio Generation
- WavNAF: Learning Wave Propagation Priors for Neural Acoustic Fields
- WAXAL: A Large-Scale Multilingual African Language Speech Corpus
- Wayfinder: Adaptive Resource Routing from Agent Citations
- WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark
- Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
- Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
- WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents
- WebNavigator: Global Web Navigation via Interaction Graph Retrieval
- WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime Environments
- WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos
- Weighted Conformal Clustering
- Weighted Sampling for Online Causal Discovery
- Weight Space Learning needs to unify benchmarking! A taxonomy of evaluation practices
- Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors
- Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs
- Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
- Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
- We Need to Improve Benchmarks in AI for Mathematics
- We Need to Rethink Benchmarking in Anomaly Detection
- We Should Distinguish Unlearning From Untraining
- What are Key Factors for Updates in RL for LLM Reasoning?
- What Arranges Features in Activation Space? Non-Classical Predictive Geometry in Next-Token Predictors
- What Can Labels Alone Audit and Edit in Frozen Representations?
- What Claims Do LLM Benchmark Scores Support?
- What Cohort INRs Encode, and Where to Freeze Them
- What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
- What DNA Foundation Models Learn Beyond Sequence Composition
- What Do Audio Models Really Hear? Layer Selection and Mechanistic Structure in Sound Representations
- What do EEG Foundation Models Capture from Human Brain Signals?
- What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach
- What Does an Observability Forecasting Foundation Model Know?
- What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
- What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
- What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment
- What Do SAE Features Encode? Evidence from Human Neural Activity
- What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
- What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
- What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
- What Gets Measured Gets Managed: Sign-aware Recommendation Needs Sign-aware Evaluation
- What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation
- "What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
- What Is Worth Representing? Representational Empowerment for Continual Model Construction
- What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
- What Kind of Diffusion Models Do We Need in Online Reinforcement Learning?
- What Makes a Good Path? Factoring Manifold Support and Path Geometry
- What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
- What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
- What MLLMs Learn about When they Learn about Multimodal Reasoning
- What Probing Reveals about Autonomous Driving: Better Predictions Lead to Better Planning
- What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting
- What’s Holding Back Latent Visual Reasoning?
- What Should a Streaming Video Model Remember?
- What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions
- What should post-training optimize? A test-time scaling law perspective
- What Should Remain After Forgetting? Rethinking LLM Unlearning as Predictive Posterior Correction
- What’s in a Smoothness Constant? Tight Rates for Local SGD with Bounded Second-order Heterogeneity
- What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation
- What Sound Tells You About the Room
- What Stops SGD on LLM Pre-Training: The Need for Large Learning Rate and How to Achieve it
- What Survival Benchmarks Don’t Tell You: Impact of Model Selection and Dataset Regimes
- What the Geometry of Good Models Tells Us
- What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
- What to Forget in Unlearning? Forget Set Curation for Language Models
- What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models
- What to Predict for Efficient Scheduling on Parallel Machines
- What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents
- What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation
- What Was That Again? Certified Robustness for Automatic Speech Recognition
- What, Where, and Boundary: Hierarchical Cognitive Decomposition for Echocardiography Video Segmentation
- When Actions Matter: Causal Affordances for Long-Horizon Credit Assignment in World Models
- When Alignment Fails: Stabilizing Cross-Dynamics RL with Prototype Trust Regions
- When All Paths Lead to Dead End: Deadlock-Depth-guided Monte Carlo Tree Search for Reentrant Blocking Hybrid Flow Shops
- When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
- When and How to Canonize: a Generalization Perspective
- When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA
- When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
- When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
- When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
- When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
- When Are Compositional Problems Learnable from Verifiable Rewards?
- When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
- When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition
- When Are Semivalue-Based Decisions Identifiable? Robust Data Selection under Utility Ambiguity
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
- When Attention Collapses: Residual Evidence Modeling for Compositional Inference
- When Attribution Patching Lies: Diagnosis and a Second-Order Correction
- When a Window Is Not an Action: Selective Phase-Script Deliberation for Sliding-Window Human Activity Recognition
- When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering
- When Can Digital Personas Reliably Approximate Human Survey Findings?
- When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
- When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
- When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
- When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
- When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
- When Do Cosine Prototypes Mislead? A Whitening-Aware Benchmark for Frozen-Feature Image Classification
- When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers
- When Does Flow Matching Help Deterministic Multimodal Prediction: A Spatial Transcriptomics Study
- When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG
- When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
- When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward Design
- When does LeJEPA learn a World Model?
- When Does Non-Uniform Replay Matter in Reinforcement Learning?
- When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
- When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation
- When Does Structure Help? Statistical Tradeoffs for Structured Reverse Processes in Diffusion Large Language Models
- When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation
- When does the noise schedule matter? A spectral classification of diffusion training objectives
- When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
- When Do Learned State Representations Break Sensitivity Analysis?
- When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
- When do Prophets Profit in Prediction Markets?
- When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
- When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
- When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice
- When Everyone Can Submit: Designing Contests with Transparent Pre-Selection
- When evolution cheats: Frozen-weights Baselines reveal static-solvers interference in evolved plastic spiking neural networks
- When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines
- When Form Changes but Logic Doesn’t: Building Logic-invariant LLMs through Structures
- When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents
- When Graph Anomalies Learn to Hide: Test-Time Cloaking in Graph-Level Anomaly Detection
- When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
- When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring
- When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
- When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion
- When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
- When is Warmstarting Effective for Scaling Language Models?
- When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
- When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution
- When Less is More: The LLM Scaling Paradox in Context Compression
- When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets
- When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement
- When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity
- When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting
- When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale
- When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
- When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
- When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation
- When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
- When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
- When Prompt Internalization Breaks: Continuous Experience Internalization in Large Language Models
- When Prompts Override Vision: Instruction-Induced Hallucinations in LVLMs
- When Reasoning Meets Its Laws
- When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
- When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
- When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
- When Scores Conflict with Preferences: Calibrated Drift Control for Heterogeneous DPO
- When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
- When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
- When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
- When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
- When Streaming Fails: Dynamic Algorithms for Unconstrained Submodular Maximization
- When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
- When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
- When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
- When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
- When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
- When to Adopt Model Updates
- When to Align, When to Predict: A Phase Diagram for Multimodal Learning
- When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
- When to Trust a PFN: Detecting Harmful Shift in Tabular Foundation Models
- When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift
- When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation
- When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation
- When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
- When, Where, What: Structural Guarantees for Travel Time Prediction on Temporal Graphs
- Where and When Identity Forms: Identity-Vital Attention Redistribution for Training-Free Subject-Driven Generation
- Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering
- Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
- Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
- Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
- Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic Grokking
- Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition
- Where Should Society Draw the Line? A Social Choice Approach to Collective Consent
- Where Tabular Foundation Models Falter on Genetic Data: Datasets That Expose and Provide a Path to Address the Gap
- Where to Approximate in Neurosymbolic Inference?
- Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
- Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition
- Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
- Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback
- Where You Backpropagate Matters: Token Hypothesis for Memory-Efficient Fine-Tuning
- Which Pairs Should We Compare for DPO?
- Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
- Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs
- Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
- Who caused $Y$? Local identifiability for learning causal parents
- Whole-Body Compliant Control via Learned Force-Regulation Modules
- Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
- Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs
- Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
- Who Verifies the Agents? Toward Reliable Agent Development
- Who Watches the Watchers? Semantically-Constrained Reinforcement Learning for Red-Teaming Provenance Intrusion Detectors
- Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
- Who, Where, and What? Forensic Localization in LLM-Based Multi-Agent Systems
- Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS Research
- Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
- Why Cancer cfDNA Models Fail on Chronic Disease: A Geometric Information-Theoretic Bound and Its Architectural Implications
- Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
- Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
- Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive Reasoning
- Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning
- Why DiT Models Underperform as Representation Learners without Long Skip Connections
- Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
- Why Do Time Series Models Need Long Context Windows?
- Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
- Why Heavy-Tailed Weights Predict Model Quality
- Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
- Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
- Why Latent Actions Fail, and How to Prevent It
- Why Learning Rediscovers the Closed-Form Diagonal Regularizer
- Why Muon Outperforms Adam: A Curvature Perspective
- Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
- Why Routers Freeze: Infinite Width Learning Dynamics for Mixture of Experts
- Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models
- Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
- Why Transformer-Based Language Models Need Explicit Mechanisms of Cognitive Control
- Why Transformers Struggle with Distribution-Independent In-Context Learning
- WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
- WILD: Widely Linear Conditioning for Time Series Forecasting
- Winfree Oscillatory Neural Network
- Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
- Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers
- WiREBench: Evaluating AI Agents' Capabilities in Reverse-Engineering Black-Box Applications in the Real World
- WirelessMathBench-XL: A Contamination-Audited Benchmark for Wireless Mathematical Reasoning
- Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks
- Witness Overlap: Directional Provenance Inside Open-Weight Model Families
- WORD: Diffusion-Based Posterior Inference for Online Goal Recognition
- WordEval: Evaluating Word-Native Operation Fidelity in Document Editing
- Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
- Words That Make Language Models Perceive
- Working with AI: Measuring the Applicability of Generative AI to Occupations
- Workshop for Autonomous Machine Learning Research
- Workshop on Evaluation of Interactive Agents
- Workshop on Resource-Aware Agentic AI
- Workshop on the Linguistic Principles for Foundation Models
- Workshop on Towards Test-Time Continual Learning Agents
- Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
- WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
- World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
- WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis
- WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation
- WorldForge: Forging Unified World Modeling into Video Generation
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
- WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction
- World-Model-Inspired Flicker State Modeling for Burst Flicker Removal
- World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
- World Models as Group Actions
- World Models for High-Stakes Health: Reliable Clinical Trial Simulation and Intervention-Aware Reasoning
- World Models in Physical AI
- World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
- WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification
- WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
- WorldSpeech: A Multilingual Speech Corpus from Around the World
- WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
- World Tracing: Pixel-Aligned Geometry Beyond the Visible
- World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems
- WorldVLA: A Unified Vision-Language-Action and World Model
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
- Worst-Case Regret Bounds for Combinatorial Bandits with Ranking Feedback
- WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching
- WsiSSM: A Weakly Supervised Subset-Matching Framework for Unified Classification and Segmentation of Histopathology Whole Slide Images
- WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps
- WURI: Watching Unfolding Risk in Agent Interactions
- X2HDR: HDR Image Generation in a Perceptually Uniform Space
- XAI4science: Knowledge Discovery and Trust through Interpretable Foundation Models
- X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation
- XBRIDGE: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
- XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
- xHC: Expanded Hyper-Connections
- XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding
- XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
- XMNoise2Clean: Cross-Modal Denoising Under Sparse Data
- X-Palm: Paired Multispectral-to-Smartphone Dataset for Cross-Domain Palmprint Authentication
- XTC: Head-Aware Sampling by Excluding Top Choices
- XTraj: A Coarse-to-Fine Autoregressive Framework for Transferable Trajectory Generation
- xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs
- xWhy: Causal Learning from Explanations
- You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace Expansion
- You Can’t Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
- You Don’t Need Aligned Representations: Knowledge Distillation via Random Prototype Spaces
- Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems
- You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
- Your Benchmark Is an Empirical Measure Over Difficulty
- Your Embedding Model Is SMARTer Than You Think
- Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
- Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States
- Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
- Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics
- Your Teacher Can’t Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
- Z0-Inf: Zeroth Order Approximation for Data Influence
- Z-AXIS: From Deterministic Ground to Agentic Depth for Enterprise Evaluation
- Z-Cache: Accelerating Diffusion Transformers via Self-Reflection
- ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
- ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations
- Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise Likelihood
- Zero-Shot Coordination among LLM Agents
- Zero-Shot Instruction Following in RL via Structured LTL Representations
- Zero-Shot Quantization via Weight-Space Arithmetic
- Zeroth-Order Sharpness-Aware Learning with Exponential Tilting
- Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
- Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints
- ZetaEvolve: Learning to Search through History-Conditioned Potential Value
- ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
- ZO-F2: Low-variance Fisher preconditioner via bilinear estimation for zeroth-order optimization
- μLM: Rethinking Sub-100M Language Models through Memory-First Design
Successful Page Load