NeurIPS 2026 Schedule

Filter Events

SUN 6 DEC

11 a.m.

Expo Talk Panel:

When Models Optimize: From Automated Red Teaming to Reward Hacking

(ends 12:00 PM)

Expo Talk Panel:

AI That Optimizes AI: Agentic Kernel and Model Optimization in Production

(ends 12:00 PM)

Expo Talk Panel:

CEO Bench: Evaluating frontier agents on real company work

(ends 12:00 PM)

Expo Talk Panel:

Training Data Expires Faster Than Ever: Five Shifts in How Frontier Models Learn, 2024–2027

(ends 12:00 PM)

Expo Talk Panel:

The Model Is Not the Agent: Building Better Agents from Experience, Systems, and Evaluation

(ends 12:00 PM)

Expo Talk Panel:

Any GPU, Any Cloud: Training on a Planetary Fleet

(ends 12:00 PM)

noon

Expo Demonstration:

When Agents Cannot Guess: Grounded Financial Research Under Regulatory Constraints

(ends 2:00 PM)

Expo Demonstration:

Closing the Agent Learning Loop: Strands, Amazon Bedrock AgentCore, and Feedback-Aware Post-Training

(ends 2:00 PM)

Expo Demonstration:

Mirror: Start an Agent Session Anywhere, Never Lose It

(ends 2:00 PM)

Expo Demonstration:

From Flat Pixels to Editable Layers: A Live Image-to-Layers System at Production Scale

(ends 2:00 PM)

Expo Demonstration:

Beyond “The Robot Moved”: Building VLA Systems That Detect Failure and Recover

(ends 2:00 PM)

Expo Demonstration:

QuLM-ST: Real-Time Speech Translation on Smart Glasses

(ends 2:00 PM)

Expo Talk Panel:

Continual Learning in Non-Stationary Environments

(ends 1:00 PM)

Expo Talk Panel:

Causal Inference has Entered its Foundation Model Era – What Industry Needs to Know

(ends 1:00 PM)

Expo Talk Panel:

A Training-Free Framework for Spatially Grounded 2D Shape and 3D Object Encoding

(ends 1:00 PM)

Expo Talk Panel:

Tabular Foundation Models Have Taken the Lead: What Changed This Year and How to Use TabPFN

(ends 1:00 PM)

Expo Talk Panel:

The Art & Science of Benchmarking Agents

(ends 1:00 PM)

Expo Talk Panel:

Scaling AI Safety & Security

(ends 1:00 PM)

Expo Demonstration:

Building Self-Improving User Simulators

(ends 2:00 PM)

Expo Demonstration:

Stump the Model: Become an AI Trainer in Five Minutes

(ends 2:00 PM)

Expo Demonstration:

Agent-driven training on Modal

(ends 2:00 PM)

Expo Demonstration:

Agent Harnesses in Practice: From Everyday Tasks to Autonomous Research Teams

(ends 2:00 PM)

Expo Demonstration:

Building High-throughput Top Performing Machine Translation System

(ends 2:00 PM)

Expo Demonstration:

CyberStrike: Evaluating whether frontier agents can complete real cybersecurity work

(ends 2:00 PM)

Expo Demonstration:

Inside the RL Stack: Training Open Models with Custom Rewards, Losses, and Code Sandboxes

(ends 2:00 PM)

Expo Demonstration:

LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks

(ends 2:00 PM)

Expo Demonstration:

Break the Guardrails: Can You Outsmart the Model?

(ends 2:00 PM)

Expo Demonstration:

Tangent: Autonomous Auto-Research Agent for ML Pipelines

(ends 2:00 PM)

1 p.m.

Expo Talk Panel:

Composing Modular Capabilities into One Deployable LLM

(ends 2:00 PM)

Expo Talk Panel:

Applying AI to Financial Markets: A Citadel and Citadel Securities Perspective

(ends 2:00 PM)

Expo Talk Panel:

Advancing the Frontiers of On-Device AI: Efficiency, Multimodality, and Emerging Models

(ends 2:00 PM)

Expo Talk Panel:

Constructing Data and Rule Ontologies for Enterprise Agents

(ends 2:00 PM)

Expo Talk Panel:

One Market, Many Clocks: Domain-Grounded Multimodal Learning in Quantitative Finance

(ends 2:00 PM)

Expo Talk Panel:

Fine-Tuning Small Models on Real Enterprise Tool Use: A Data and Evaluation Pipeline

(ends 2:00 PM)

2 p.m.

Expo Workshop:

Protective and Creative AI for Creators: Foundation Models, Protection Mechanisms, and Audio-Visual Generation

(ends 5:00 PM)

Expo Workshop:

Compute Efficiency & Scalable System Design (Smart Compute Allocation: High-Throughput, Low-Latency AI Across the Model Lifecycle)

(ends 5:00 PM)

Expo Workshop:

Forgetting on Purpose: A Hands-on Tutorial on LLM Unlearning

(ends 5:00 PM)

Expo Workshop:

RL in the wild: principles of post-training that work in the real world

(ends 5:00 PM)

Expo Workshop:

Priorities in AI Safety & Security

(ends 5:00 PM)

Expo Workshop:

From Proteins to Cell State: Toward World Models of Biology

(ends 5:00 PM)

5 p.m.

Expo Talk Panel:

Beyond Chat: Always-On Context Engines for Proactive AI Assistants

(ends 6:00 PM)

Expo Talk Panel:

Towards Foundational Robotics Models with 3D Reasoning

(ends 6:00 PM)

Expo Talk Panel:

Building Enterprise AI for Finance: Structured Models, Adaptive Memory, Trusted Agents, and Scalable Orchestration

(ends 6:00 PM)

Expo Talk Panel:

Breaking the Bottlenecks of Autoregressive LLM Inference

(ends 6:00 PM)

Expo Talk Panel:

Owning the Harness: Durable, Open Infrastructure for Long-Running Agents

(ends 6:00 PM)

Expo Talk Panel:

Can We Turn Images into Words—and Back Again? Holistic Visual Descriptions for Understanding and Generation

(ends 6:00 PM)

6 p.m.

Expo Talk Panel:

Adapting AI Research to Quantitative Finance

(ends 7:00 PM)

Expo Talk Panel:

Turning Academic AI Research into Trusted Real-World Impact

(ends 7:00 PM)

Expo Talk Panel:

Continual Reinforcement Learning for AI Shopping Assistants

(ends 7:00 PM)

Expo Talk Panel:

Agents in Production: Evals, Harnesses, and the Reinvention of Recommendation

(ends 7:00 PM)

Expo Talk Panel:

Environments Are the New Data: Building, Verifying, and Training Agents at Scale.

(ends 7:00 PM)

Expo Talk Panel:

From Research to Industry: Building Scalable Production Systems and Teams

(ends 7:00 PM)

MON 7 DEC

9 a.m.

Tutorial:

The Principles of Diffusion Models: Toward Fast and Scalable Diffusion LLMs

(ends 12:00 PM)

TUE 8 DEC

2:30 a.m.

Education Track:

Education Track

(ends 10:30 AM)

9 a.m.

Sydney Invited Talk:

Scaling Experience in the Wild: Building the Industrial Learning Loop

Tie-Yan Liu

(ends 10:00 AM)

10 a.m.

Sydney Poster Session 1 [10:00-1:00]

Posters 10:00-1:00

$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion

$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement

$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation

3D Fresnel Volumizing for Efficient Implicit Velocity Field Reconstruction

3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields

3D Skew Normal Splatting

3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model

A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark

Accelerating Rectified Flow Models via Trajectory-Aware Caching

Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses

Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries

Active Learning as Nullspace Regulation: A Spectral Representation Perspective

Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel

Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval

ActO: Extracting Action Representations from MLLM Embeddings for Video World Models

AdaMAP: Learning Adaptive Multi-Action Prediction with Grounded Dreaming Guidance

AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation

Adaptive auditing of AI systems with anytime-valid guarantees

Adaptive Feature Propagation for Attribute-Missing Graph Clustering

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

Adaptive Internal Readout for Native Multimodal Models

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

AdDirector: Anchored Guidance for Generating Camera-Controllable Advertisement Videos

Adversarial Attack and Defense for Machine Learning in Statistical Physics

AERO: Adaptive Ensemble-Disagreement Routing for Oracle Feedback in Sample-Efficient Online RLHF

AesGI-Bench: Benchmarking and Evaluating the Aesthetic Quality of AI-Generated Images via Large Multimodal Models

AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games

Agreement without Coverage: Conditional Agreement is Non-Identifying in Variable-Support Structured Extraction

AI Alignment Can Build Moral Autonomy

AIRA-Compose: Agentic Discovery of Neural Architectures

AirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting

A latent control model for realistic rodent motion

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

Aligned Delta-Triplane Transformers as Occupancy World Models

Aligning AI Teams

Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference

Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy

A Little Robustness Is All You Need: Leveraging Predictions for Contextual Optimization

A Locally Tokenized Generative Model for Robust Time-Series Watermarking

AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning

A Mechanistic Investigation of Theory of Mind in a Large Language Model

Amortized Optimal Transport from Sliced Potentials

A multi-scale information geometry reveals the structure of mutual information in neural populations

Anchoring Reasoning Distillation via Syntactic Constraints

AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence

APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents

AptaBench: A Benchmark for Aptamer-Small Molecule Binding

Architecture-Embedded Physics Priors for Mitigating Spectral Bias in Physics-Informed Neural Networks

A Regularization-Based Approach to Public Belief State Search for Adversarial Games

Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains

ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation

Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video

A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training

Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs

A Solvable Model of Chain-of-Thought in In-Context Learning

A Sparse Low-Rank Biclique Decomposition for Graphs

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

ASQ: Agent-guided Semantic-aware Quantization for Large Language Models

Asymmetric Generalization in Deep CTR Models: A Block-wise Diagnosis

Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning

AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism

At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections

A Theoretical Analysis of Test-Driven Code Generation

AtmoZero: Self-Play Post-Training for Caption-Free Weather Time-Series Captioning

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

Auditing Conformal Prediction for Language Models Under Inference-Time Model Shift

A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs

A Unified Neural Architecture for Variable-Wise Shape Constraints

A Unified Semismooth Newton Approach to Multitask and Multivariate Square-Root Lasso Problems

AVENUE: Audio-Video Editing Understanding and Evaluation

Backtracking with Linear-in-Depth Search-Space Growth: Width-Limited Tree Search for Large Language Models

Balancing Image Compression and Generation with Bootstrapped Tokenization

BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation

Bayesian Causal Stress Testing: Posterior Fragility of Treatment-Effect Conclusions

Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback

BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation

Behaving Better, Thinking Worse: Sycophancy Across Post-Training Stages

Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning

Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline

Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models

Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models

Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer

Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization

Beyond Contraction: Geometry-Faithful Supervised Dimensionality Reduction for Data Visualization

Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation

Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models

Beyond Hard Negatives: Grounded Positive Supervision for Compositional CLIP

Beyond Imputation: Mask-Adaptive Conformal Prediction via Tree Embeddings on General Missing Data Mechanisms

Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

Beyond Raw Observations: Distilling and Storing Invariant Driving Memories for Generalizable Autonomous Driving

Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

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 the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs

Beyond the Readout: Reservoir State Statistics for Model-Space Learning under Sparse Observations

BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots

Binding Visual Features Point by Point

BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments

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

BitShift-RoPE: Zero-FLOP Relative Positional Encoding for Spiking Neural Network Transformers

Black-box model classification under the discriminative factorization

BlendCast: Teaching Vision-Language Model to Anticipate Member Skill in Weather Ensembles

Bonobo: Efficient Library-Scale Generation for De Novo Antibody Design

BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability

Bound-Conditioned Latent Inference for Progressive Image Compression

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

Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories

Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning

Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

BReD: Block Replay Dithering for Stable Low-Bit EMA Optimizer States

BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization

Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding

BridgeMVS: Bridging Multi-View Stereo and Monodepth via Bidirectional Dynamic Fusion

Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling

Bridging the Simulation-to-Experiment Gap with Adversarial Distribution Alignment

BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization

BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation

C3H: Compression-to-Consensus Criteria Hijacking in Multimodal LLM Recommender Systems

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

Can Large Language Models Develop Gambling Addiction?

Can Model Merging Improve Aggregation in DiLoCo?

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

CASAM: Consistency-Anchored Sharpness-Aware Minimization for Improved Model Generalization

Castle-in-the-Air: Probing the Foundational Visual Deficits of MLLMs via Bottom-Up Cognitive Factors

Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production

Caterpillar GNN: Replacing Message Passing with Graph-Level Aggregation

CATS: Acceptance-Oriented Critical Token Adaptive Selection for Multimodal Speculative Decoding

CausalAffect: Causally Guided Learning of Psychology-Aligned Facial Affect Relations

Causal Bias Detection in Generative Artifical Intelligence

Causality can systematically address the monsters under the bench(marks)

CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery

ChainFlow-VLA: Causal Flow Planning with Vision-Language Models

Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator

Characterizing the Aesthetic Defaults of Generative Image Models

Characterizing Universal Object Representations Across Vision Models

ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing

Chebyshev Differential Flows for Shape Matching and Interpolation with Endpoint Guidance

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

Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples

Classification of high-dimensional data with spiked covariance matrix structure

ClawBenchPro: Benchmarking How Well Agent Harnesses Work

ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation

CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?

CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention

CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation

Collapse Hunter: Tackling the Dimensional Degeneration in Generative Ranking

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models

Complete or Sparse: A Tale of Two Identifiabilities

Complexity-guided Regularization for Generalizable Human Gaussian Splatting

Complexity of Differentially Private Selection via Federated APIs

Complex Optimization Modeling via Multiagent Fine-Tuning and Skill-Augmented Reasoning

Complex Schrödinger Bridges

Compressible Representations: Functional Spines in Deep Neural Networks

Computing All Optimal Partial $p$-Wasserstein Matchings on the Line

Conditioning Gaussian Processes on Almost Anything

Confidence-Based Diffusion Sampling with Geometric Readiness Awareness for Accelerated Structure-based Drug Design

Conformal Agent Error Attribution

Conformal Language Modeling via Posterior Sampling

Conformal Prediction for Time-Dependent PDEs

ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading

Consolidating Reasoning with Test-Time Learning

Consolidating Rewarded Perturbations for LLM Post-Training

Constrained Graph Clustering: A Spectral Algorithm with Generalized Eigenvectors

Constrained Look-ahead Guidance for Interference-Aware Flow Editing

Continuous Latent Diffusion Language Model

Continuous p-adic Optimization

Contractive Monoids: The Algebra Behind Stable Residual Propagation in Deep Graph Neural Networks

Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

Controlling Transient Amplification Improves Long-horizon Rollouts

Coordinating Hundreds of RL Agents through Scalable Inference-Time Search

CoQuant: Covariance-Aware Rotation for 2-bit KV Cache Quantization

Correctable Fork Tokens: Verifier-Anchored Selective Credit Assignment for Tool-Integrated RLVR

Correpondence Alignment For Improved Virtual Try-On

Cost-Aware Best-LLM Identification using Dueling Feedback

Counterfactual Instruction Grounding for Vision-Language-Action Models

CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation

CP-MLPs: A Tensor-Rank Theory of Tied and Untied MLP Blocks

CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

Cross-Architecture Transferability is Width-Confounded:Diagnosis and Subspace Correction

Cross-Foundation Complementary Learning Systems for Continual Test-Time Adaptation in Open-Vocabulary Semantic Segmentation

Cross-order Consensus Graph Matching

CrossSteer:Cross-Modal Safety Steering for Audio-Language Models

Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents

CT-Lesion: A Multi-Region CT Dataset for Co-existing Lesion Segmentation and Detection

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

Curvature-Guided Parameter Initialization for Multi-Task Learning

CutAttn: Discovering Cognitive Transition Layers for Efficient Long-Context Prefilling

CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language Models

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios

Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation

DACE RL for Compute Efficient Reinforcement Learning in Small Model Reasoning

DAGent: Evaluate-then-Grow Planning for Deep Research Agents

Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers

Data Density Scaling Laws for Image Self-Distillation

Deadline-Constrained Dynamic Workflow Scheduling Can be Cast as a Representation Learning Problem

Decentralized Coupled Representation Learning

Decomposing the modulation of interactions between neuronal populations

DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection

DeepfakeGenome: Toward Next-Generation Deepfake Attribution

Deep Probabilistic Supervision for Image Classification

Delayed homomorphic reinforcement learning for environments with delayed feedback

DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule

Demographic parity in regression and classification within the unawareness framework

Density-Ratio Losses for Post-Hoc Learning to Defer

Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View

Detection and Classification in Latent Spaces: High-Dimensional Analysis and Validation

Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding

Dexterous Skill Discovery via Topology-Aware Wasserstein Dependency

DGRAF: Observation-Quality-Aware Reinforcement Learning for Dynamic Reconfigurable Batteries

DiA: Directional Adapter

Diagnosing and Repairing Visual Collapse in Compact Medical Multimodal LLMs

Differentiable Exact Learning of Algorithms

Differentiating Network Design Objectives for Balancing Cost and Distance

DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

DiffRisk: Diffusion Representation Learning with Informative Missingness for Health Risk Prediction

Diffusion Masked Pretraining for Dynamic Point Cloud

Diffusion-Time Concept Manifolds: Sparse Autoencoder Groups for Interpreting Denoising Language Models

Diffusion Tree Search for Inference Time Adaptation of Material Foundation Models

Dimension Bounds for Contractive Reservoir Computing from Input Entropy

DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning

Direct Conditional Parameterization for N-Dimensional Splatting

Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning

Discovering Phase Space Structure in Learned Hamiltonian Systems

Discovering Unseen Degradations to Adapt Open-World Image Restoration

Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion

Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models

Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications

Distributionally Robust Algorithmic Recourse for Tree Ensembles

Distribution Corrected Decision Transformer for Offline Reinforcement Learning with Imbalanced Datasets

Diving-R1: Empowering Multimodal LLMs with Traceable Progressive Reasoning for Interpretable Diving Action Quality Assessment

DoAtlas-1: A Causal Compilation Paradigm for Clinical AI

Does Mixed Label Imbalance Matter to Minority Collapse in Imbalanced Learning?

Does This Gradient Spark Joy?

Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision

DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring

Do Image Editing Models Understand Lighting?

Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL

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

Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling

Drifting Fields are not Conservative

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation

Dual-Pathway Circuits of Object Hallucination in Vision-Language Models

DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards

DynaCell: an Evaluation Framework for Dynamic 3D Virtual Staining of Live Cells

Dynamic Latent Routing

Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology

Early Failure Detection and Intervention in Video Diffusion Models

EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function

EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG

Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching

Efficient Decoder Scaling Strategy for Constructive Neural Routing Solvers

Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion

Efficient Label Distribution Inference Attack and Defense on Classifier Weights in Federated Learning

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing

EIPO: Efficient Inter-Step Parallel Optimization

ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation

Elicited Adaptation: Auditable Localized Fairness via Pairwise Queries

ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation

Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations

Emergent Misalignment as Data-Mediated Transfer

Emergent Visual Thinking in Text-Only Reasoning through Multimodal Training

ENACT: Single-Image Human-Scene Interaction Motion from Language via Foundation-Model Orchestration

EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning

Enhancing Speech Large Language Models through Reinforced Behavior Alignment

Ensembling Language Models with Sequential Monte Carlo

EntiRE: Invariant Learning for Robust Concept Erasure in Text-to-Image Generative Models

EpicWorldModel: Exploration-driven Planning with Latent World Models

Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room

ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP

Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification

EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning

Even Sailors Need Calm Seas: Taming the Geometry of VLMs for Fast Adversarial Fine-Tuning

Event based Multi-Velocity-Scale Imaging

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

Exact Topological Compliance: Generating Persistence-Equivalent Graphs

Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models

Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding

ExperiGen: Agentic Hypothesis Discovery from Observational Data

Explainability matters: The effect of liability rules on the healthcare sector

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

Exploring the Epipolar Consistency for Light Field Deraining

Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes

FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

Fast-RL: Accelerating Reinforcement Learning for LongCoT Reasoning Models

Fault Tolerance in Transformers Favors Output Alignment over Hidden-State Consistency

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

Federated Distributionally Robust Neural Combinatorial Optimization with Convergence Guarantees

FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models

FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated Learning

FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning

FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine

FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory

Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

Finetuning with Sampling: Make SFT Generalize, Not Forget

Fingerprinting Inference Systems of Large Language Models

FireMPC: A Multi-Source Pan-Canadian Wildfire Benchmark Revealing Spatiotemporal Generalization Gaps

Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission

FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers.

FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention

FlashRelight: Portrait Video Relighting with Dynamic Lighting

FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps

Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

Flow Matching for Count Data

Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling

FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing

Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials

Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models

Focus on Where You Aggregate: Restricted SAM for Non-IID Federated Learning

FOGO: Forgetting-aware Orthogonalization Optimizer

Follow the Mean: Reference-Guided Flow Matching

Forgery Evidence Peaks Mid-Stack: Forensic Evidence Relay for Multimodal Forgery Detection

Forgetting to Improve: Principled Data Removal in Active Learning

FracTS: Hierarchical and Autoregressive Time Series Generation

FraudBench: A Legal Evaluation of AI Deception on Realistic Tasks

Fréchet Regression on the Bures-Wasserstein Manifold

FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated Videos

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

FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching

From Benchmark to Adoption: Coding Agent Evaluation Needs User-Level Harness

From Click Imitation to Transition Equivalence: Rethinking Supervision for GUI Agents

From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts

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 Pixels to Concepts: Do Segmentation Models Understand What They Segment?

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving

From Sample to Subset Construction: Coverage-Aware Curation of Robot Demonstrations

From SGD to Muon: Adaptive Optimization via Schatten-p Norms

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

Full-Sequence Masked Diffusion for Generative Recommendation

G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models

GARDO: Reinforcing Diffusion Models without Reward Hacking

GATE-AD: Graph Attention Network Encoding for Few-Shot Industrial Visual Anomaly Detection

Gaussian Mixture Models in Hilbert Spaces via Kernel Methods

GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs

Generative Scenario Rollouts for End-to-End Autonomous Driving

GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

GenZ: Hybrid statistical–foundational models for knowledge discovery from real-valued multidimensional targets

Geometric Latent Reasoning Induces Shorter Generations in LLMs

GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression

GEOPHYS: The Geometry of Physical Plausibility

Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images

GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning

Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction

GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection

GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations

Global convergence of adjoint-optimized neural PDEs

GLOVE: Global Verifier for LLM Memory-Environment Realignment

GlycoGen: Crystallizing Flows for De Novo Glycan Structure Prediction

GOLIATH: Gradient Inversion of Tabular Diffusion Models

G-PAC: Constructing Cohesive Pseudo-Features for Generalizable Physical Adversarial Camouflage

GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

Greedy Alignment Principle for Optimizer Selection

GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement

Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

Guiding Visual Autoregressive Models through Spectrum Weakening

HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation

HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models

HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning

HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields

HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search

Harnessing Agentic Evolution

Harnessing Streaming Video in the Wild

Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting

Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and Confidence

Heuresis: Evaluating Search Strategies for Autonomous Machine Learning Research Agents

Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence

Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning

HierSVA: A Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification

High-Fidelity Boltzmann Samplingvia Physical Prior Lifted Continuous GFlowNets

HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction

HoloCode: A Code-Centric Multi-Agent Framework for Image-to-3D Scene Generation

Horizon-Stream: Long-Horizon Attention for Streaming 3D Reconstruction

Horizontal Diffusion Models: Score-based Generative Modeling on Frame-Connection Geometry

How Complete Should a Reference Be? A Benchmark Audit for Fluorescence Spot Detection

How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies

How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?

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 to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

Human–AI Collaboration Requires a High-Order Dynamic Abstraction Substrate

Human-AI Teaming Through the Lens of Calibration

HuPER: A Human-Inspired Framework for Phonetic Perception

HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation

Hyperagents

Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning

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

Identification and Bounding of Joint Expectation over Potential Outcomes

ImageNet FID is a Pass Check, Not a Finish Line

Imagine Before You Draw: Visual Prompt Engineering for Image Generation

Imperfect World Models are Exploitable

Implicit Bias in State Space Models and Linear Autoregressive Training

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

Importance-Aware OBS Pruning for Diffusion Models

Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

Improving Generative Adversarial Networks with Self-Distillation

IMTS-Tokenizer: Time-Aware Tokenization for Irregular Multivariate Time Series Forecasting

Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training

Incorporating Neural Network Structure in the Bayesian Learning Rule

Incremental Multiple Oracle

Inference-time Alignment via Sparse Junction Steering

Inpainting physics: self-supervised learning for context-driven fluid simulation

InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse

Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

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

Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems

Internal Safety Collapse in Frontier Large Language Models

Intervene3D: Intervention-Based Controlled Inference for Multimodal Perception under Partial Observability

Introspective Coupling: LMs Learn to Explain Themselves Better Than Their Training Targets

Inverse Modeling of Neural Recordings via Differentiable Biophysical Simulation

INVITA-WheatFieldState: A Real-World Benchmark for Crop-State Estimation in Wheat Field Trials

Iris: Empowering Video MLLMs with High-Frequency Pose Priors via Spatiotemporal Binding

Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow Support

ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining

JailBound: A FOL-Guided Jailbreak Evaluation Framework for Revealing Safety Boundaries of LLMs

Joint Learning of Hierarchical Neural Options and Abstract World Model

JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors

Kernel-based guarantees for nonlinear parametric models in Bayesian optimization

Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification

Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking

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

Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting

KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG

kVNN: Learnable Volterra Network Kernels

L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks

L2P: Unlocking Latent Potential for Pixel Generation

LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving

Latent Process Generator Matching

Layer Precision Reduction for Deep Anomaly Detection

Layout Before Pixels: Topology-Anchored Transcriptome-to-Histology Generation

LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models

LeAct: Learning to Reason from Expert Actions

LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification

Learning a Trajectory-Geometric Condition from Reasoning for VLA Planning

Learning Causal Orderings for In-Context Tabular Prediction

Learning Dynamic Evidence Routes for Vision Transformer Probing

Learning Event-to-Field Operators Without Interpolation

Learning from Disagreement: Maximum Divergence Knowledge Distillation

Learning Global Temporal Dynamics in Sparse Networks via Cycle Counts

Learning Hierarchical Forward Processes For Discrete Diffusion Language Models

Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation

Learning in Causal Markov Games

Learning in Policy Transparency Games: Wedge Structure and Adaptive Certification

Learning Minimal Sufficient Evidence Graphs for GraphRAG via Nash-Guided Optimization

Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport

Learning Planning Budgets in Real-Time RL

Learning Robust Representations for Defending White-Box Adversarial Attacks in Continual Learning

Learning through Internalization

Learning to Deaggregate: Large-scale Trajectory Generation with Spatial Priors

Learning to Sample From Diffusion Models via Inverse Reinforcement Learning

Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual Representations

Learning to Solve Generative ODEs Beyond the Linear Span

Learning under Localized Minority Imbalance

Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics

Leech Lattice Vector Quantization for Efficient LLM Compression

LEGO: Sizing Rules for Budget-Aware Dense-to-MoE Conversion of Vision-Language Models

Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA

LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field Representations

Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling

LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance

Linear approximations to HMM filtering

Lipschitz Dueling Bandits over Continuous Action Spaces

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models

LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

LLM Rheology: Auditing Refusal Geometry in Aligned Language Models

Load Balancing Mixture of Experts with Similarity Preserving Routers

Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning

Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization

LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting

Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds

LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging

LOTION: Smoothing the Optimization Landscape for Quantized Training

Lower-Level Agnostic Bilevel Optimization

LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models

Machine Learning-Driven RAG System Design

MAEB: Massive Audio Embedding Benchmark

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction

MapPFN: Learning Causal Perturbation Maps in Context

MARBLE: an Agent Benchmark for Spatial Reasoning and Visual Abstraction

Masked Visual Actions for Unified World Modeling

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models

Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation

Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment

MaterialsPilot: An Execution-Feedback Framework for Generative Design of Complex Atomistic Architectures

MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models

MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving

MC-H: Multi-Granularity Clustering with Hyperspherical Determinantal Point Process

Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios

Measuring and Decomposing Mode Separation via the Canonical Diffusion

Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models

Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events

Mechanistic Interpretability Needs Philosophy

MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes

MedHorizon: Towards Long-context Medical Video Understanding in the Wild

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare

MedVTok: A General-Purpose Medical Visual Tokenizer

MemCode: Discrete Semantic Representations for Long-Term Agent Memory

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters

METRO: Metric-Enhanced Token Routing Operator

Metropolis-Adjusted Diffusion Models

MICA: Activation Checkpointing for Double-Backward Training of Machine Learning Interatomic Potentials

Microstructure Descriptor Fields as Supervision for Scientific Images

Mind the Gap: Dataset and Fine-grained Evaluation for Inline Audio Descriptions

MinerU2.5-Pro: Pushing the Limit of Document Parsing via a Calibrated Evaluation-Data Flywheel

Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport

Minimax Optimization without Spurious Solutions in Optimal Transport Learning

Minimax Rates and Spectral Distillation for Tree Ensembles

MIRAGE: Duality-Inspired MILP Augmentation for Representation Learning

MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?

MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series

Mitigating Reward Hacking via Task Representations

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing

MixScentNet: A Multiscale Graph-based Framework for Predicting Scent Mixture Perception

Mixture-Trained Merging for Unified Multi-Objective Models

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment

MLLM Makes Strong Backbone for Multi-Modal Object Detection

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models

Model Immunization Beyond Condition Numbers: The Importance of Plateau Regions

Model Incrimination: Investigating Whether Concerning Behavior Reﬂects Misalignment

MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs

MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening

MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning

Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism

Multi-Marginal Couplings for Metropolis--Hastings

Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity

Multiobjective Submodular Maximization with Concave Aggregation

Multi-Part Object Representations via Graph Structures and Co-Part Discovery

Multi-step Consistency Models: A Complete Error Theory and Optimal Step Selection

Multivariate Time Series Forecasting needs Cross Variable Loss

Muon Does Not Converge on Convex Lipschitz Functions

MUST: Stage-Adaptive Stability Control for Test-Time Scaling in Multimodal Reasoning

MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning

NarrativeBench: Benchmarking Multi-trait Automated Scoring and Feedback Efficacy of Large Language Models for Chinese Narrative Essays

Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret

NavOCR: A Dataset Generator for Navigation-Relevant Text Detection in Mobile Robots

Nearly-Optimal Algorithm for Adversarial Kernelized Bandits

Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians

Neural Backward Filtering Forward Guiding

Neural Bayesian Filtering

Neural networks are more modular than single neurons suggest

Neural Refraction Fields for Image Verification

Neural Scaling Laws in Particle Jets

Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference

Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models

Next-Token Prediction Enables Scalable Learning of Sleep Physiology

Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge Surrogates

Noisy2Latent: Nonparametric Deconvolution and Denoising via Maximum Mean Discrepancy

Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards

Non-Expanding Gated Continued Fraction Architecture for Feedforward Layers in Language Models

Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free Training

Normalized Friedkin–Johnsen Opinion Dynamics

Normalized SGD in the Convex Regime: First High-Probability Guarantees and Momentum Extension

Norm Anchors Make Model Edits Last

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness

Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models

Not Just Oversmoothing: Detecting Echo Chamber Effect in Graph Neural Networks

Nuwa: Evaluation-Grounded Agentic Construction of Time Series Forecasting Systems

Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly

OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation

OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

Offline Materials Optimization with CliqueFlowmer

OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning

One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception

One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms

Online Bayesian Recalibration of Brain–Computer Interfaces with Language Model Potentials

Online Minimum Description Length Passive-Aggressive Algorithms

Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points

On the Convergence of Multicalibration Gradient Boosting

On the Depth of Monotone ReLU Neural Networks and ICNNs

On the Effect of Token Correlations on Semantic Transfer in Transformers

On the Faithfulness of Visual Thinking: Measurement and Enhancement

On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

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 Price of Privacy for Language Identification and Generation

On the Relaxation of Conditional Independence Assumption for Image Segmentation

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning

On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences

OpenMHC: Accelerating the Science of Wearable Foundation Models

OpenView: Empowering MLLMs with Out-of-view VQA

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in Policy Optimization

Optimal Ansatz-free Hamiltonian Learning In Situ

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing

Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning

OrbitLoRA: Learning Rotation-Aware Low-Data Adaptation of Vision Foundation Models

OrchestraRL: Learning to Orchestrate LLM Agent Swarms with Entropy-Aware Communication Control

Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM

Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

OTIS: Learning High-Quality Time Series Features With Tiny Encoders

OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference

PACE: Pareto-Adaptive Compression for Efficient Native MLLMs

PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking

PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning

Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation

ParaLin: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure

Parameter Exploration for RLVR via Variational Learning

Parameterized Stripe Attention for Efficient Video Generation

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

PatchBench: Measuring Collateral Damage in Activation Patching

PATCH: Learnable Tile-Level Hybrid Sparsity for LLMs

PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?

PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

Peer review should constrain evaluative authority

PercepCap: Video Captioner with Structured Spatio-Temporal Perception

Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks

PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction

PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization

PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression

Phase-Adaptive Fusion: Spatio-Temporal Modulation for VLA Models

Phase Transitions in Heavy-Tailed Mean Estimation under $\ell_p$ Norms

PhysEval.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation

PhysTC: A Physics-Enhanced Dataset and Architecture for High-Precision Tropical Cyclone Forecasting

PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning

PINNBench: A Benchmark and Evaluation Study of Training Policy Selection in Hybrid PINN-Operator Solvers

Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Reranking

PIS: Pose-Interpolation Smoothness for Skinning Weight Refinement

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

POISE: Instance-Specific Prompt Tuning under Latent Mixture Target Distributions

PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation

Political Neutrality as Balanced Approval: A Large-Scale Human Evaluation of AI Responses

POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models

Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent

Position: Robust Reasoning Requires Internal Time, Not Scale Alone

Position: Telic Errors Make VLMs Unreliable Annotators in Sensitive Contexts

Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces

Posterior Sampling-based Online Learning for Episodic POMDPs

PPO in the Fisher-Rao geometry

Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging

Prediction Under Imperfect Compression: A Theory of Approximate MDL

Preserving Geometric Symmetry in Uncertainty Estimation for Molecular Forces

Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy

PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning

PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution

PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing

Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning

Privately Clipping Heavy-Tailed Data

PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety

Probabilistic Circuits for Irregular Multivariate Time Series Forecasting

Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures

Probe-Guided Gradient Balancing for Multimodal Learning

Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation

Prototype Topology Consistency for Visible-Infrared Lifelong Person Re-Identification

Provable Selective Auto-labeling with Reliability Guarantees

ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer

PULSE: A Synchronized Five-Modality Dataset for Sensorimotor Coordination in Long-Horizon Daily Activities

Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing

Quality-Diversity Optimization as Multi-Objective Optimization

Q-ViK: Question-Guided Visual KV Cache Eviction for Large Vision-Language Models

QWaveNet: Quantum-Enhanced Wavelet Network for Time Series Forecasting

RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

RADAR: Routing Agents via Difficulty-Aware Recovery

Random Attention Pattern Learning Enables Emergent Capabilities

Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds

RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation

RaVF: Learning Radar Velocity Fields via Spatial-Doppler Guidance

Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing

Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation

Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation

Reasoning over Coupled Receptive Fields: Eliminating Subgraph Redundancy at Scale

Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models

Re:Cognize - A Framework For Open-Set Comic Character Re-Identification

Recovering Evolving User Preference State via Adaptive Interaction-aware Representation Correction

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation

REFLEX: Reflective Evolution from LLM Experience

Reinforcement World Model Learning for LLM-based Agents

Reinforcing VLAs in Task-Agnostic World Models

Relation-Aware Graph Foundation Model

Relevance Is Not Necessity: Selecting the Necessary API Set for Tool-Using LLMs

Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment

Representation Forcing for Bottleneck-Free Unified Multimodal Models

ReSAM: Representation-Level Safety Margin Alignment for Vision–Language Models

Residual Calibration via Local Feature-Space Refinement

Resilient Latent Readouts for Long-Context Question Answering

ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search

Retain-Neutral Surrogates for Min-Max Unlearning

Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder

Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response

Rethinking Cross-Layer Information Routing in Diffusion Transformer

Rethinking Diffusion Decoding via Structural Commitment

Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language Models

Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding

Rethinking Learning from Label Proportions via Moment Matching

Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models

RETR: A Structure-Preserving RGB-Event Transformer for Robust 3D Lane Detection

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

Revisiting Autoregressive GCNs for Vehicle Routing Problems

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation

Revisiting the Adam–SGD Gap Beyond Single Factors

Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases

ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion

RGF: Recursive Generative Framework for the Edge-Cut Separable Problems

Riemannian Optimization for Low-Rank Adaptation via Desingularization

RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization

Risk-Aware Action Repetition via Expected Skip Evaluation

RoboExo: Structure-Guided Wrist-to-Exocentric Video Generation for Scalable Robot Learning

Robust Approximate Nearest Neighbor Search for Any Dataset

Robust Domain Generalization under Divergent Marginal and Conditional Distributions

RobustPruner: Decoupled Relevance and Uncertainty for Efficient Visual Token Pruning in MLLMs

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety

ROLLVERIFY: BRIDGING EFFICIENCY AND ACCURACY IN LONG-TAIL ROLLOUT REINFORCEMENT LEARNING

RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers

RTCBench: Evaluating Tool Use of Large Language Models Beyond Oracle Access

RUBRIC-MME: Real-User Behavior-grounded Rubric for Multimodal Interaction Capability Evaluation

RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation

S²MoE: Shared-Subspace Mixture of Sparse Experts

Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents

SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMs

SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation

SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation

SAME: Stability-Aware Embedding Extraction in Mixture-of-Experts Language Models

Sample-Efficient Optimization over Generative Priors via Coarse Learnability

Sandboxed Coding Agents are Competitive Omni-modal Task Solvers

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

SC$^3$: A Multi-Solvent Solubility Challenge and Benchmark

Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction

Scalable Fair Learning via Cramér-von Mises Regularization

Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing

SchedDiff: Diffusion-Based Priority Refinement for Job Shop Scheduling

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training

SeaPilot: Mobile Agent with Self-refining Environment Alignment

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs

Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation

Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation

SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search

Segment and Select: Vision-Language Segmentation in 3D Scenarios

Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling

Self-Distilled RLVR

Semantic-level Exploration for Multi-Agent Reinforcement Learning

Semiparametric Efficient Tests for Interpretable Distributional Treatment Effects

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents

SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark

Sequential Solution Concepts in Cooperative Games with Generalized Characteristic Functions

SETA: Scaling Environments for Terminal Agents

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning

Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits

ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens

Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees

SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural Network

SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning

Signature-Kernel Evaluation Metrics for Robust Probabilistic and Tail-Event Forecasting

Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization

Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics

SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

Single Shot HDR Recovery via a Video Diffusion Prior

SkillCIR: Intent-Guided Skill Composition for Training-Free Composed Image Retrieval

SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth Pruning

Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots

SOAR: Semantic Organ-Aware Pretraining for 3D CT Image Understanding

Soft geometric inductive bias for object centric dynamics

Soft-Radial Projection for Constrained End-to-End Learning

Sparse All-Layer Connector for Domain Generalised Semantic Segmentation

Sparse Fine-Tuning for Parameter-Efficient Adversarial Training

Sparse Updates Generalize Better Than Optimization: Stability Analysis for Randomized Subspace Descent

SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

SPDEBench: An Extensive Benchmark for Learning Stochastic PDEs

Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo

SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers

Spike-SFT: Selective Parameter Enhancement and Fusion for Efficient Spiking Neural Networks

Sponsored Questions and How to Auction Them

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

SQUEEZE: Preserving Homeomorphism and Smooth in Higher-Dimensional Flows

SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction

SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation

SSD: Shell-Guided Spherical Diffusion for Molecular Geometry Generation

Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models

Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Stable Partial Order Constraints for Temporal Causal Structure Learning

StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching

Stage-Aware Dual Alignment for Covariate Shift in Graph Domain Adaptation

StakeBench: Evaluating Language Understanding Grounded in Market Commitment

Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding

Statistical field theory for Markov decision processes under uncertainty

Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search

StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting

Stop or Restart? Principled Inference Control for Large Reasoning Models via the Pandora's Box

StoSplat: Ray-Aligned Stochastic Preconditioning for Feed-Forward 3D Gaussian Splatting

Stranger Things: When Objects Appear Without Their Typical Neighbours

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

Strategic Feature Selection and Regularization

StreamMind: Dynamic Streaming Cognition for Online Video Understanding

Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment

STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts

Strong Post-Training from Permissive, Reasoning-Dominant, Web-Scale Pretraining

Structural Self-Teaching for Compositional Generation in Unified Multimodal Models

Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding

Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration

SudoBench: A Contextual Authorization Benchmark for LLM Agents

SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework

Superplatforms Are Strategically Compelled to Counteract AI Agents

Sup-Norm Error under Proportional Asymptotics: Phase Transitions under Linear Regression

Surprises in Proper Positive-Only Learning

SurvCancel: A Longitudinal Dataset and Benchmark for Dynamic Order Cancellation Prediction in On-Demand Ride-Sharing Systems

Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL

SVDP: Training-Free Contextual Sparsity Predictors for Fast LLM Inference

Symplectic Normal Coordinates Flow for Generative Modeling of Hamiltonian Systems

Synaptic Strength Controls Trainability and Structural Stability in Rank-Deficient RNNs

SynMQG: Disentanglement and Mutual-Information Optimization for Synergistic Multi-modal Question Generation

T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals

Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems

TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees

TANGO: RNA Topology and Geometry Co-Design

Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning

Temporal Concentration from Rollout Errors: Implicit Preference Optimization For Text-to-Video Diffusion

Test-Time Adaptation via Self-Reinforced Optimal Transport for Zero-Shot OOD Detection with Vision–Language Models

Test-time Scaling of Diffusions with Flow Maps

Test-Time Sequential Steering of Diffusion Models via Preconditioned Crank-Nicolson

Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning

The Confusion is Real: GRAPHIC – A Network Science Approach to Confusion Matrices in Deep Learning

The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching

The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection

The End Justifies the Mean: Linear Ranking Rules for Proportional Sequential Decisions

The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations

The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning

The Heel of RLVR: Benchmark Glory Should Not Outpace Honest Measurement

The Narrative Gap: Can LLMs help us Navigate Diverse Narratives Across Languages?

The Optimization Prior: Instilling depth for shallow networks, detail for coarse networks

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action

The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.

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 Sparsity Whisperer

The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks

Think Before You Generate: Active Panoramic Exploration for Text-to-3D Scenes

Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought

Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling

Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration

TILT: Target-induced loss tilting under covariate shift

TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning

TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra

Tio: Language Models with Parallel Streams of Thoughts, Inputs and Outputs

TiRex-2: Generalizing TiRex to Multivariate Data and Streaming

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

TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection

Tokenization and Architecture Jointly Allocate Component Roles in Time Series Transformers

TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality

TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs

ToLD: Efficient Time Series Forecasting via Tokenized Truncated Latent Diffusion

Tool-Integrated Reasoning via Hierarchical Multi-Agent Reinforcement Learning

Topological Invariance and Breakdown in Learning Dynamics

Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction

TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation

Touch-R1: Reinforcing Touch Reasoning in MLLMs

Toward Multimodal Sheet Music Recognition and Understanding

Towards Anytime-Valid Statistical Watermarking

Towards a Unified Model for Flexible Job Shop Scheduling Problems

Towards Direct Evaluation of Harness Optimizers via Priority Ranking

Towards Financial World Modeling

Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values

Towards Identifiable Latent Additive Noise Models

Towards Multi-Human-Value Alignment via Value Localization in LLMs

Towards Optimal Pre-training Data Mixtures for Empowering Reinforcement Learning in LLMs

Towards Principled Task Grouping for Multi-Task Learning

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling

TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking

TRACE: Tourism Recommendation with Accountable Citation Evidence

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

Training ML Models with Predictable Failures

Trajectory-Matching Meta Pseudo-Labeling for Semi-Supervised Learning

TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control

Transferability for General Reasoning: An Automated Curriculum for Multi-Domain LLM RL

T-ReX: Learning Tile-Reuse Indexes for Structured Model Compression

TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG

TrustFlow: Adaptive Trust Calibration for Language Model Guided Reinforcement Learning

Trust Region Q Adjoint Matching

TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

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

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

Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction

U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models

Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning

Understanding the Challenges in Iterative Generative Optimization with LLMs

UniDG: Universal Defect Generation via Defect-Context Editing

Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems

UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding

Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation

UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification

Unlocking LLM Creativity in Science through Analogical Reasoning

Unsupervised Unlearnable Segmentation via Semantic Structure Disruption

Unveiling the Value of Motion for Cinematic Camera Trajectories

User Embeddings are Superpositions of Interpretable Behavioral Modes

Variational Active Flow Matching for Discrete Online Black-Box Optimization

VDE: Verifiable Dynamic Evaluation of Mathematical Reasoning via Typed Bipartite Graphs

Velocity-Space 3D Asset Editing

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

Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Video Generation Research Needs a Legally Sustainable Data Infrastructure

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

VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models

ViMU: Benchmarking Video Metaphorical Understanding

Virtual Head Attention

Virtual Task Prompting for Multi-Task Scene Understanding

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs

Visual Instruction Tuning Aligns Modalities through Abstraction

Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs

ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing

VLAN: Vision-Language Accessible Navigation

VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing

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

WaterDescatterGS: Diverse Underwater 3D Scene Reconstruction Using Gaussian Splatting

WATERFALL: Workflow for Adaptive Training with Evolutionary Reward Formulation and Automated Learning Loops

WavNAF: Learning Wave Propagation Priors for Neural Acoustic Fields

Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery

Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors

What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules

What Do Audio Models Really Hear? Layer Selection and Mechanistic Structure in Sound Representations

What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching

What Probing Reveals about Autonomous Driving: Better Predictions Lead to Better Planning

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 to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models

What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents

When All Paths Lead to Dead End: Deadlock-Depth-guided Monte Carlo Tree Search for Reentrant Blocking Hybrid Flow Shops

When and How to Canonize: a Generalization Perspective

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction

When does the noise schedule matter? A spectral classification of diffusion training objectives

When evolution cheats: Frozen-weights Baselines reveal static-solvers interference in evolved plastic spiking neural networks

When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees

When is Warmstarting Effective for Scaling Language Models?

When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

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

Who Watches the Watchers? Semantically-Constrained Reinforcement Learning for Red-Teaming Provenance Intrusion Detectors

Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention

Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space

Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It

WILD: Widely Linear Conditioning for Time Series Forecasting

World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video

Worst-Case Regret Bounds for Combinatorial Bandits with Ranking Feedback

WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching

xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs

Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints

ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics

(ends 1:00 PM)

11 a.m.

Creative AI Session 1 [11:00-2:00]

s -

Activation Steering the Nan-Shan in Typhoon

AgencyBudget: Controlling Unsolicited Change in Iterative Human–AI Co-Creation

Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die

AI Mom™

AI's Silent Omissions: Redistributing Bodily Agency

Algorithmic Flesh

ANCORA

Ars Incompleta: A Novel That No One Will Ever Finish Reading

Attention Garden

Automation of Creative Design Representation: A First Step Towards a Co-Pilot for Generative Design

Biocompiler: Compiling Spatial Network Optimization Problems into Living Solvers with Digital Fabrication System

Bodies in Dialogue: Exploring Perceived Agency through Embodied AI in Human-Robot Theatre

Born, not Made

Cache Machine

Cadence: Music-Responsive Stage Lighting in Concert Video Generation

____ Controls

COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami

Creative Compression in LLM-Based Dramatic Character Interpretation

Da Capo

Dancing Ink Spirits: Negotiating Agency in Generative Chinese Ink Animation

Don Qui-CoPilot: An Experiment in the Surrender and Reclamation of Self in the Age of Agentic AI

Draw This First

Effort

Entangled Matter: AI, Humans and Golems

Ethos Lithos

Everyone's a Director: A Trip to the Moon, recreated by 4.8 Million Votes

Exploring Textual Guidance for Video-to-Music Generation Models

FANVERSE: Exploring and Extending Branching Story Universes Across Canon and Fan Fiction

FlockWorld: Toward Population-Scale Multi-Agent Video World Models through Artificial Life Simulation

Frictional Intelligence

From Artists to Artisans: Preserving Agency Against Cognitive Fordism

From Memory: Mechanistic Interpretability and Emotion as Artistic Mediums

Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts

Give Me a Hand

glitch-ing bodies

Horror Vacui

How Much of This Is Mine? Shapley Credit for the Aesthetic Reranker

How to Get an Audience to Laugh at a Live Generative Story: Crowd-Sourced Humor and Shared Agency

Human Operator

Impossible Rooms

In a Grove, Again: Optimizing over Feasible Event Histories for Incentive-Driven Testimony

Incentives Shape How Humans Co-Create with Generative AI

Inner Witness: A Closed-Loop Neuroadaptive Audiovisual Installation

In the Mix: AI Support for Live DJ Track Selection

KAAYA: The Body Draws What the Eye Never Sees

Light Language Objects: Ambiguity and Otherness in Embodied AI

Lose Yourself: Controlling the Model

Love Mission 404: Manufacturing Spontaneity in a Generative Dating Show

LumiComposer: Negotiating Creative Control Between Illumination, Mapping, and Generative Music Models

Machine Eye

Magic Quill: A Real-time Score Engraving System for Live MIDI Performances

Memory Machines #3: an oceanic pas de deux

MINT: Musical Intent Representation in Human–AI Co-Creation

Music-Originated Zeitgeist for Artistic Representation and Translation (MOZART): Distributed Agency in Music-to-Physical-Painting

Neo Ferro-Mýrmēx Economy

nom nom: Metabolic Worldbuilding through Neural Cellular Automata

PaintCopilot: Modeling Painting as Autonomous Artistic Continuation

PainterBench: Evaluating Painterly Controllability in Generation and Verification

Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound

Performative Taste: When Creative Control Changes with Horizon

Playing the Plot: Optimizing Narrative Structure with Strategic World Models

Preference Without Assertion: Locating Aesthetic Agency in a Gaze-Driven Design System

Presence Is Not Placement: Auditing What Vibrato Metrics Measure

Pullim: Untangling the Knots within

Restored Lines: A Model Finds the Poet’s Hardest Line Breaks and Declines to Write Them

Rope Flow Music: An Embodied Instrument that Sonifies a Movement Practice

Shaping AI’s Beliefs Before It Generates: Human Sense of Agency in Creative AI

Smell with Genji: Rediscovering Sensory Experience with an AI Co-Smelling Partner

Spectral Evidence

Stellar Pathfinding

Story Sprout: A Picture-Book Studio Where Children Direct the AI and Keep the Pen

Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation

Symbiotic Traces: An Ecological Record of Language Model Training

Synthetic Capital: Symbolic Hierarchy in Fashion Photography and the Outsider Status of Generative Imagery

TextMixer: Writing via Sampling and Remixing

The Avatar in Chief

The Body at the Edge of the Signal: AI, Glitch, and Painting After the Machine

The Dead Ear: A Language Model’s Inherited Accent Is an Archive, Not an Author

The Generative No and Sourced Refusal in Human-AI Co-Creation

The National Average

The Plot Refuses the Author: Diegetic Contestability for Character-Driven AI Co-Writing

The Sound of Reasoning

Towards Measuring Creative Agency through Observable Signals in Human–AI Graphic Design

Transcendent Contact: Expanding Creative Agency Through Hallucination

Water Album: A Built Negotiation of Agency from Ink Gesture to Public Space

What Can AI Offer as a Design Probe for Creativity? Reflections from Co-Designing a Creative Writing Tool

What Value Forgets: Neural Search Within a Combinatorial-Game Value

When Brain Signals Steer Generative AI: Agency Beyond Causal Influence

When Rejected Properties Return: Measuring Veto Persistence in Conversational Image Editing

WHISPERS: An Interactive AI Thriller Series

Whose Hand Do You Prefer? The Steerability of Machine Aesthetic Judgment

Whose Hand is on the Vinyl? Transcribing a DJ's Scratch Gestures from Video into a Playable Instrument

Windchime: an Audiovisual Installation with Audio-Language Model implementations

Wishstone: Negotiating Voice Agency Through a Tangible Generative Keepsake

Δw ∈ ℝⁿ

(ends 2:00 PM)

1:30 p.m.

Affinity Event:

Affinity Support Pilot Program

(ends 4:30 PM)

2 p.m.

Sydney Invited Talk:

Barbara Engelhardt

Barbara E Engelhardt

(ends 3:00 PM)

3:30 p.m.

Sydney Oral Session 1A [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 1B [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 1C [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 1D [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 1E [3:30-4:30]

(ends 4:30 PM)

4:30 p.m.

Creative AI Session 2 [4:30-7:30]

(ends 7:30 PM)

5 p.m.

Sydney Poster Session 2 [5:00-8:00]

Posters 5:00-8:00

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control

$\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds

3D Consistency Tokens

ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective

AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation

Accelerating Diffusion Language Models via Structured Suffix Modeling

Accelerating Safe Reinforcement Learning with Massive Parallelism

A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry

AcousticBench: Measuring Acoustic Perception in Large Audio Language Models

ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning

AdaKVQ: Adaptive Mixed-Precision KV Cache Quantization For Efficient Reasoning Models

AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks

AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation

Adapting Vision Transformers to Organoid Imaging

Adaptive Covariance and Multi-Layer Alignment for Out-of-Distribution Detection

Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

Adaptive Multi-Frame Learning for Expressive and Stable Atomic Representations

Adaptive Random Forests from Online Learning and Testing by Betting

AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes

Addressable Memory for Video World Models

Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning

A Diagnostic Benchmark for Layered Layout and Template-Variant Reasoning

ADKV: A Low-Overhead Adaptive Delta Quantization for KV Cache in LLM Inference

Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training

Advectra: Asymmetric Latent Transport for Non-Stationary Physics

AEGIS: Adaptive Efficient Generative Inference Scheduling for Structured Latent Models

AegisFlow: Training-free Non-myopic Path-safe Guided Flow Matching

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

AeroMosaic:Transport-Aware Multimodal Evidence Fusion for Atmospheric Pollution Risk Inference

AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

A Frank-Wolfe Approach to Goldstein Stationarity

AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering

AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems

AgentTailor: Dual-Gate LLM-Assisted Re-ranking for Personalized Long-Tail Recommendation

A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory

AI Evaluation Should Require Standardized Item-Level Data Releases

AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference

AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space

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 Latent World-Action Model with Jointly Aligned Reasoning

Align as You Couple: Learning Spatial Resolved Inference from H&E Images with Mollified Flow Matching

All-Addition Spiking Diffusion Models with Attention Enhancement

All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping

ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs

A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models

A Mechanistic Analysis of Looped Reasoning Language Models

A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds

Amortizing Generative Guidance for Model-Based Reinforcement Learning

AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding

An Analytical Model of Compute-limited Multistage Training Pipelines

Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines

Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation

Anchored Protein Engineering

Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework

A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces

An Information-theoretic Framework for Auditing Unfairness in Training Data

Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive

AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training

APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts

Approaching I/O-optimality for Approximate Attention

A Principled Optimal Transport Framework for Frame Selection in Long Video Understanding

AQBENCH: Benchmarking Neural Surrogates for Air Quality Forecasting

ARCANA: A Benchmark for Abstraction and Analogical Reasoning

Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows

Are we really tilting? The mechanics of reward guidance in flow and diffusion models

ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation

ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection

Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts

A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models

As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does

ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations

ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?

Asymmetric Scaling Laws from Sparse Features

Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy

Asynchronous Agentic Poisoning

A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics

A Theoretical Framework for Self-Play Theorem Proving Algorithms

A Theory of Training Profit-Optimal LLMs

Atom-level Protein Representation Learning Improves Protein Structure Prediction

AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing

Auction-Based Online Policy Adaptation for Evolving Objectives

Auditing Single-Query Recoverability in Self-Supervised Representations

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 Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning

A unified pairwise distribution matching framework for graph domain adaptation under structure shift

AutoformBot: Formalizing Mathematics at Scale

Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models

Autonomous Scientific Discovery via Iterative Meta-Reflection

AuxGeoAgent: Synthesizing Challenging Geometry Proving Data via Planning and Symbolic Deduction

AWP: Activation-based Window Pruning for Gigapixel Object Detection

BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

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

BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations

Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery

BarrierSteer: LLM Safety via Learning Barrier Steering

BASIL-DCM: Biophysical Amortized Scalable Inference for Latent Dynamic Causal Modeling

Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models

Bayesian Decision Making around Experts

Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators

BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation

BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems

BDC-Merge: Cross-Architecture Model Merging via Dependency Alignment

BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets

Behavioral Probes for Information Flow in LLM Swarms

Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback

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

Benchmark Shadows: How Data Regimes Shape Parameter Footprints and Generalization

Bentkus-type asymptotic e-values

Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data

Beyond a Single Score: An Audit of Aesthetic Evaluation in Text-to-Image Pipelines Across Subcultural Visual Languages

Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting

Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning

Beyond Generation: Unlocking Discriminative Representations from Diffusion Models

Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness

Beyond ICA: Identifiability by Symmetry Breaking

Beyond Proxy Metrics: MLLM-Based Human Surrogate Evaluation for Explainable AI

Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents

Beyond the Grid: Continuous Dictionary Pursuit for Interpretable Signal Decomposition

Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL

Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image Enhancement

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

Bigger Isn’t Better: Why the Indiscriminate Scaling of Foundation Models Can’t Solve Biology

BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks

Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models

Boosting LLM Reasoning via Human-Inspired Reward Shaping

Bootstrapped Bipartite Actor-Critic for Diffusion RL

Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace

Brain2voice 2.0: High-performance voice synthesis brain-computer interface

BrainWhisperer: Leveraging Whisper for Speech Decoding in Neuroprosthetics

BRAVO: Bridge Matching for Autoregressive Video Generation

Breaking Curse of Dimensionality for Mutual Information Estimation with Vine Copulas

Breaking feature collapse in self-supervised time series encoder

BrickFlow: Connectivity-Guided Brick Reconstruction

Bridging Diffusion and Autoregression for Flexible Time Series Synthesis

Bridging Image Restoration and Recognition via Causal Mediated Unrolling

Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding

CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth

CA-Judge: Teach Large Models to Judge Anomalies via Comparison for Video Anomaly Detection

Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention

Calibration Is Not Control: Intervention Advantage for LLM-Agent Oversight

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

Can Complementary Signals Bridge Similarity Islands? Manifold-Augmented Graph Embedding for Multimodal Recommendation

CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas

Can VLMs Reason When to Stop for Human Safety?

Capacity-Constrained Online Convex Optimization with Delayed Feedback

Cauchy Scientific Networks: Loss–Architecture Alignment and Its Limit

Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach

Causally Structured Differential Network Modeling for Single-Cell Perturbation Prediction

CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning

CCTimeBoost: Learning Time-Varying Relative Risk with Case-Control Boosted Trees

Certified Robust Interpretability via Concept-Space Stability under Interventional Proxies

Chain of Dual Structures in Transformer Attention

Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs

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

Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces

Class–Domain Discriminability Guided Representation Enhancement for Domain Generalization

Closed-Loop Alignment: Socially Coupled In-Context Learning and Relational Posterior Collapse

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

Closing the Gap on the Sample Complexity of 1-Identification

Closing the Loop: Co-Evolving EM for Irregular Time Series Generation in Lifted Representations

Clustering-Free End-to-End Spoof Diarization with Encoder-Decoder Attractors

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation

Coarsening Linear Non-Gaussian Causal Models with Cycles

CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting

CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation

Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation

COHE: Auditing Non-Transitivity in Sample Difficulty Proxies for Vision Models

Colored Noise Diffusion Sampling

Combating Camouflage and Forgetting: Spatio-Temporal Dual Denoising for Money Laundering Detection

COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

Comp$^2$VLM: A Hybrid Framework Combining Quantization and Lossless Compression for Efficient Vision-Language Models

Compact Representations of Impact-Based Fair-Ranking Policies

Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time Adaptation

Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods

Computer Use at the Edge of the Statistical Precipice

Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning

Conservatism Controllable Compositional Guidance for Offline Safe Reinforcement Learning

Conservative Pareto Set Amortization for Offline Multi-Objective Optimization

Constant Term Shrinkage for Federated Learning

Constrained Modulatory Reservoirs for Context-Dependent Computation

Constructive Neural Policies for the Quadratic Assignment Problem via Multi-Expert Imitation

Context as Low-Rank Weights: Bounded Parametric Dynamic Memory for Unbounded Context

Contour Monte Carlo: Sampling via Energy Level Sets

Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning

Co-optimization for Adaptive Conformal Prediction

COSMIO: A Benchmark for Cross-Survey Modality Imputation

Cost-Aware Learning

CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling

CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving

Cross-Domain Knowledge Separation and Positive Transmission for Noisy Domain Incremental Learning

Cross-Model Circuit Discovery

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

CryptanalysisBench: Can LLMs do cryptanalysis?

CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition

CSFlow: Aligning Flow Matching with Human Contrast Sensitivity

CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization

CTRL: Continual Test-Time Reinforcement Learning for Large Language Models

Cyclic Discrete Diffusion: A Novel Multi-Class Segmentation Refinement Technique

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

DAGA: Dynamic Attention-Guided Adaptation for Self-Supervised Vision Transformers

Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning

Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards

DAWN: Dependency-Aware Fast Inference for Diffusion LLMs

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks

DDx-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs

Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction

Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation

Decomposed Graded Verifier for Generative World Modeling

Decomposing Conformal Uncertainty: Calibration- and Instance-Driven Feature Attribution

Decomposing Earth Embeddings with Sparse Autoencoders

Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation

Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance

Decoupling Action from Egocentric Observation for World Simulation

Decoupling Direction and Magnitude: Language-Steered Flow Matching for Super-Resolution in the Dark

Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos

DegBins: Degradation-Driven Binning for Depth Super-Resolution

DeGlare: Self-Supervised Specular Removal for Industrial Metallic Surfaces via Multi-Illumination Priors

Denoising-Time Heterogeneity in VLA Action Generation: A Controlled Study via Step-Wise Expert

Despa: Resolving Spatial Collapse in VLMs via Depth-Grounded Geometry

DETS: An Interval-Censored Evidential Sampling Framework for Cross-Domain Scientific Discovery

DexOPE: 6D Object Pose Estimation in Dexterous Manipulation

DiagSQL: A Diagnostic Validator for Text-to-SQL with Reward Allocation and Co-occurrence Shaping

DialBandit: Adaptive Sequential Search with Tunable Evaluation Fidelity

Dialect ASR based on Multi-View Pseudo-Parallel Augmentation and Noise-Robust Contrastive Learning

DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections

Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation

DiffCap-RL: Differential QA Rewards for Dense Image and Video Captioning

Differentiable Learning of Lifted Action Schemas for Classical Planning

DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting

Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models

Diffusion-State Policy Optimization for Masked Diffusion Language Models

DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising

Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers

Discretizing Continuous Time Series for Imputation with Masked Diffusion Training

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning

Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental Learning

DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation

Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning

DISTMOE: Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning

Distribution-Adaptive Policy Optimization

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling

Distributionally-Robust Policy Learning from Observational Data

DiversePlace: Diversity-Seeking Curriculum Reinforcement Learning for Macro Placement

DMax: Aggressive Parallel Decoding for dLLMs

dMoE: dLLMs with Learnable Block Experts

Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?

Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters

Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?

Don’t Learn What You Can Compute: Arithmetic Residual Blocks for Exact Arithmetic in Transformers

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Do You CARE to Generalize? Extracting Robust Concept Directions from LLMs

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models

Drift-Resistant Navigation World Model with Anchored Epipolar Guidance

DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation

DSR-TSF: Spectrum-Driven Dynamic Routing for Efficient Long-Horizon Time Series Forecasting

DSSNet: Deep Spectral Structure Profiling Network for Traffic Flow Prediction

DSSP: Diffusion State Space Policy with Hierarchical Full-History Conditioning

Dual Feature-Relational Alignment for Transferable Targeted Attacks on MLLMs

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network

DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable Rewards

DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Dynamic Causal Structure Discovery for Autoregressive Visual Generation

Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning

Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting

Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics

Dynamic Spectral Federated Graph-Level Clustering

DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models

DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD

EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization

EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation

Effect-Level Validation for Causal Discovery in Interactive Telemetry

Efficient Adjoint Matching for Fine-tuning Diffusion Models

Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts

Efficient Test-Time Adaptation For Robot Policies

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

Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models

EMO: Pretraining Mixture of Experts for Emergent Modularity

EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue

End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization

EngramState: Loadable Tool Priors for Efficient Function Calling

Ensuring Deployment-Time Safety of Neural Network Controlled Systems via Localized Certificate Repair

Entangled Schrödinger Bridge Matching

EnvFaultBench: Benchmarking LLM Agents on Software Environment-Fault Troubleshooting

Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent Interaction

Epitope-Conditioned Nanobody CDR Design via Retrieval-Augmented Protein Language Models

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning

EsoLang-Bench: Evaluating Large Language Models via Esoteric Programming Languages

Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models

Estimating Continuous Treatment Effects with Recourse Data

EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment

Evaluating Synthetic ECG Pretraining: When Can Patient-Free Simulators Substitute for Real ECG Data?

Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models

Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered

Event-Centric Perception in Weak-Signal Physical Streams with Multimodal LLMs

Every Measurement, Every Direction, All at Once: Multimodal Flow Matching for Molecules and Spectra

EviAttr-OW: Evidential Attribute Reasoning for Open World Object Detection

Evidence-RL: Towards Evidence-intensive Visual Reasoning

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement

Exactness Matters for Physical Rule Enforcement

Exact power indices for plurality-voting ensembles

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting

Explanation Mechanism Influences Human Reliance on Reinforcement Learning Agents

Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts

ExpRFT: Exponential Reward-Weighted Fine-Tuning for Offline RL in Multi-Turn Dialogue

Extending ROC Analysis to Uncertainty-Aware Risk Prediction with an Interval-Based AUC (iAUC)

Extracting Training Data from Diffusion Language Models via Infilling

Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation

Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling

FASTER: Rethinking Real-Time Flow VLAs

Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching

FAVLA: A Force-Adaptive Multi-Rate VLA model for Contact-Rich Robotic Manipulation

Feasible Policy Optimization for Safe Reinforcement Learning

Feature Recovery for Object Understanding Under Physical Transformation

FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning

FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning

Feed-Forward 3D Gaussian Splatting for High-Fidelity Animatable Hand Avatar Reconstruction from a Single Image

FerQ: Fermat Quotient Reformulation of High-Order Binary Optimization

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs

Filtered Conformal Ellipsoids for Graph-Native Time Series

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare Removal

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

FlashMol: High-Quality Molecule Generation in as Few as Four Steps

FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control

Flexformer: Flexible Linear Transformer with Learnable Attention Kernel

FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language 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

Flowette: Flow Matching with Graphette Priors for Graph Generation

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery

Focusing Influence Mechanism for Multi-Agent Reinforcement Learning

FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models

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

FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization

Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics

Foundation Model Informed Acquisition Functions for Molecular Discovery

Foundations of Categorical Equivariant Deep Learning

FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models

Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference

FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond

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

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Freshness-Gated Imagination: Step-Level Trust for Latent World Models

From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning

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 Noise to Diversity: Random Embedding Injection in LLM Reasoning

From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space

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 Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale

Frozen Memory Is Not Enough: Rethinking External Memory as Extraction

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Fusion or Confusion? Multimodal Complexity Is Not All You Need

FutureSim: Replaying World Events to Evaluate Adaptive Agents

fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets

GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling

GEAR: Generator-Adaptive State Space Models for Associative Recall

GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs

GEM: Interpretable Language Models via Geometric Embedding Alignment

Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems

Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs

Generalized Influence Functions for Better Model Change Estimates

Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport

Gen-Searcher: Reinforcing Agentic Search for Image Generation

Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction

Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers

Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations

GNES: Neural-Guided Evolutionary Program Search for Interpretable Multi-Agent Control

GOAT-AL: Pseudo Neural Collapse Guides Adaptive Coverage for All-Budget Active Learning

Gradient Regularized Newton Boosting Trees with Global Convergence

GradTrack: Detecting Noisy Labels via Temporal Trajectories of Class-wise Gradient Misalignment

GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis

Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation

Graph-Enhanced Attribute-Aware Modeling for Cloth-Changing Person Re-Identification

Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs

Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent

HACO: Hedged Agent Computing for Reliable LLM Systems

Hadamard Representation: Scaffolding Performance Across Model-free RL

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models

HALMES: Knowing When to Intervene in LVLM Hallucination Mitigation

HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models

HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly Detection

Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision

HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling

HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily

H-GenPO: Hierarchical Generative Policy Optimization via the Option-Critic Framework

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths

Hidden Tails: Certifying Tail-Risk Claims under Selective Labels

HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning

HIFC-IQA: Train-Free Cross-Domain Image Quality Assessment via Dual-Process Cognition

Higher-Order Action Supervision Makes A Strong Policy Class

Historical Relative Policy Optimization for Bootstrapping LLM Reasoning

Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies

How Data Augmentation Shapes Neural Representations

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

How do Small Transformer Models Learn Hard Math Tasks?

How Finite-Rank Bottleneck Shape the Low-Rank Adaptation Landscape

How Private is Private? A Comparative Study for Face De-Identification

How Selection Shapes Diversity in LLM Ecosystems

How to make the most of your masked language model for protein engineering

How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction

Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating

HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding

Hyperbolic Concept Embedding Model for Interpretable Medical Image Diagnosis

Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry–Task Alignment

HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification

Hypergraph-guided Global Mean-field Negotiation For Multiview Evidential Classification

Hypergraph Modeling of Transformer Attention for Hallucination Detection

HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Identifiable Feedback-Controlled Latent Flow for Unpaired Single-cell Spatio-Temporal Dynamics

iDETR: Implicit DETR for Tiny Object Detection

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

Implicit Goal Conditioning via Value Disaggregation

Implicit Neural Representations for Variational Problems on Graphons

Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks

Improving Audit Realism with Inference-Time Compute and Deployment Scaffolds

Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs

Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory

In-context Learning in Presence of Spurious Correlations

Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models

InfCLIP: Unified Data Valuation for CLIP Pretraining via Influence-Inspired Scoring

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 Discernment in Large Language Models

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control

Integrating Background Knowledge for Scalable Causal Discovery

Integrating digital twins with randomized experiments

Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning

interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification

Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability

Invariant Hyperbolic Unfolding: Radial Canonicalization for Label-Free Cross-Graph Link Prediction

Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench

Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies

Iterative ILP with Update-Size Control for Reducing Surrogate-Task Mismatch in Bit-Width Selection

Jump Start Your Policy Learning with Lessons from 145,000 Training Runs

Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests

Kernel Value Regression in Offline Reinforcement Learning

KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees

Knowing When Multivariate Forecasts Are Wrong

KnowVis: A Dual-View Benchmark for Diagnosing World-Knowledge Grounding in Text-to-Image Models

Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling

LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching

Large Language Model Failures from Hallucination to Homogenization Are Different Facets of Miscalibration

LaSA-Net: A Language-Guided Network for Outdoor Generalized 3D Referring Expression Segmentation

Latency-Conditioned Selection Bias in RLHF

Latent Introspection: Models Can Detect Prior Concept Injections

Latent Reasoning in Continuous Space for Unified Multimodal 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

Layerwise LQR for Geometry-Aware Optimization of Deep Networks

LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces

Learned Lagrangian Models of PDEs via Euler–Lagrange Residual Minimization

Learning Active Perception and Manipulation via Spatio-temporal Visual Memory

Learning Agentic Policy from Action Guidance

Learning-Augmented Streaming Algorithms for Approximating Boolean Max-CSPs

Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness Regularization

Learning from Disagreement: Multi-Teacher Distillation for Chinese Spelling Correction

Learning inexact alternating minimization

Learning Joint Semantic-Geometric Uncertainty for Structured Prediction with Closed-Loop Calibration

Learning Modular Addition with Auxiliary Modulus

Learning POMDP World Models from Observations with Language-Model Priors

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning

Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding

Learning to play with spikes. Characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing

Learning to Solve Compositional Geometry Routing Problems

Learning to Synergize Textual and Visual Prompts for Fine-Grained Traffic Element Detection in HD Maps

Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning

Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

LG-Bench: A Graph-Structured Evaluation Benchmark for Life Science

LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models

Lift, See, Act: Hierarchical Robot Policy Pretraining with 3D Foundation Models

LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing

LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling

LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs

LLM Routing Through the Lens of Recommendation: A Roadmap for Efficient AI Orchestration

LLMs Keep Thinking When Told Not To

Local Gaussian Processes on Compact Lie Groups

Local–Global Sparse Autoencoders for Multiscale Interpretability in Vision Models

Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

Locking Pretrained Weights via Deep Low-Rank Residual Distillation

LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data

Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval

LongSCOP: Semantically Consistent Long Video Outpainting

LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning

Look-ahead Variational Flow for Generative Online Reinforcement Learning

Lookalike3D: Seeing Double in 3D

Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning

Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits

LookThere! Sparse Vision by Reinforced Selection

LoopNav: Benchmarking Spatial Consistency in World Models

LoopPrune: Evolutionary Module Selection with Iterative Execution for Efficient Large Language Model Compression

LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution

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$^\star$: Every Task Deserves Its Own Memory Harness

Machine Unlearning in Low-Dimensional Feature Subspace

MANGO:Multi-Angle Neural Gated Operators for Chirp-Perturbed PDEs

Manifold-Aligned Adversarial Perturbation for Anti-Customization under Diffusion-based Purification

Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking

Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction

Manifold Random Features

Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs

MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals

Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

Mean Testing under Truncation beyond Gaussian

Mechanism Design for AI Overviews: Creator Incentives and Long-Term Profit

Mechanism-Level Chemical Reaction Simulation with Electron Bookkeeping Transformer

MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video Generation

MedHEB: Benchmarking Medical Embeddings Across Heterogeneous Clinical Evidence

Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization

MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory

Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning

Meta Inverse Prompting for Video Generative Models

Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

MinMax Recurrent Neural Cascades

Mirror Descent-Ascent for mean-field min-max problems

Mitigating Retaliatory Algorithmic Collusion in Repeated Games

Mixture of Activations: Token-Adaptive Mixing for Expressive Feedforward Layers

Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models

MMLongCite: A Benchmark for Evaluating Faithfulness of Long-Context Vision-Language Models

MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling

MobileWan: Closing the Quality Gap for Mobile Video Diffusion

Modality-Depth Routing for Visual Reasoning in VLM Post-Training

Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning

Modeling the Vividness of Imagined Natural Scenes Reveals a Model-Common Image-Level Component in Vision Models

Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning

Moment-Constrained Latent Steering for Flow Policy

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

MOOD: Benchmarking Post-Hoc OOD Detection for Materials Property Prediction

MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI

Most ReLU Networks Admit Identifiable Parameters

MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing

mRNABench: A curated benchmark for mature mRNA property and function prediction

MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling

Multi-Agent Coordination via Support-Preserving Distillation

Multi-Constrained Randomized Smoothing Certificates

Multi-Nonsmooth-Nonconvex-Objective Optimization

Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again

MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation

MUX: Continuous Reasoning via Multiplexed Tokens

MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks

My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization

NAGO: Noise-Aware Generative Operator via Flow Matching

Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions

NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation

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

Neighbor-Aware Snapshot-Based Temporal Graph Learning

Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows

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

Network Intervention by Polling Strategic Agents

Neural-Behavioral Representation of Natural Whole-body Movement in Monkeys

NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling

Neural Neural Scaling Laws

Neural population tuning statistics as priors for multitask generalization

Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations

Neural Signals Generate Clinical Notes in the Wild

Neuronal Identity as an Organizational Basis for Analyzing Neural Population Dynamics

NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity

New Coresets for Fair Clustering

NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training

No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning

No Free Alignment: Observability-Aware Alignment for Multimodal Heterogeneous Learning

No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse

Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers

Not All Layers Are Equal in Image-to-Video Transfer

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 Routing Drift Is Harmful: Trust-Region Projection for Class-Incremental Learning

Not All Slots Are Equal: Non-Co-Progressive Markov Bridge for Bundle Construction

Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure Infusion

Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty

ObsConDA: Observability-Constrained Data Assimilation with Control-Space Inference

Occupancy-based Quantile Risk Control

OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks

Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark

Off-policy Learning with Excursion Policies

OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment

On Communication-Efficient Training of Ensembles in Federated Learning

On Differential Private $\ell_1$, $\ell_2$ and $\ell_p^p$ Distance Queries

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning

ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

On Generalization in Bilevel Optimization with Overparameterized Models

On JEPA Isotropy

Online Decision-Focused Learning under Semi-Bandit Feedback

Online Directional Regression for Streaming Sufficient Dimension Reduction

On Reparameterizing the Score Function

On the Burden of Achieving Fairness in Conformal Prediction

On the Convergence of Success Conditioning for Policy Optimization

On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing

OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

Optimal Rates for Differentially Private Hypothesis Testing with E-values

Optimal Risk Bounds of Stochastic Gradient Descent for Shallow ReLU Networks

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

ORCA: Orthogonal Residual Consensus Alignment for Multi-View Clustering

Ordered Policy Optimization

Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems

Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness

Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion

Partially Performative Prediction

Past, Future, All at Once: Breaking Stability-Plasticity Dilemma via Post-hoc JANUS Rectification

Patch Hierarchical Attention Transformers for Efficient Particle Jet Tagging

Path-Guided Flow Matching for Dataset Distillation

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

PDF-HR: Pose Distance Fields for Humanoid Robots

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing

Permutation-Invariant Spectral Learning via Dyson Diffusion

Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-Horizon Agents

PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations

Persona-Model Collapse in Emergent Misalignment

Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models

Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy

PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling

PHOEBI: An Open-World Benchmark for Multi-Label Bacterial Identification in Phase-Contrast Microscopy

PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents

PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?

PhysEval: Quantifying the Gap Between Video Generation and World Physical Laws

PhysFlow: Physics-Intrinsic Velocity Regularization for Motion-Intensive Video Generation

Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment

Platonic Task Arithmetic

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

Pluralistic AI Alignment Requires Inference-Time Multi-Objective Control

Point4D: Long-range 4D Motion Reconstruction

Point Clustering Encoders

Pointillism: Probing-Based Model Compatibility for Robust Collaborative Machine Learning

Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases

Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization

Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions

Position: Machine Learning Conferences Should Introduce an Autonomous Research Track

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

PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

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

Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings

Predicting the Needle in a Petabyte Scale Haystack: Open-Vocabulary Event Anticipation in Satellite Imagery

Prediction-Augmented Trees for Reliable Statistical Inference

Predictively-Oriented Kalman Filtering

Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation

Pretext Reasoning: Scaling the Building Blocks of Interleaved Multimodal Reasoning

Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models

Primal-Dual Representation Learning for Low-Rank Constrained MDPs

Prior-Anchored Local Statistical Representation Rectification for Low-Light Image Enhancement

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: Priority-Guided Scanning in the Wavelet Domain for UAV Maritime Small Object Detection

PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization

Privacy Risk Scales with Effective Dimension in Federated Learning

PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking

ProactBench: Beyond What The User Asked For

Probabilistic Recursive Reasoning

Probing the Trajectories of Reasoning Traces in Large Language Models

Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback

probly: Uncertainty-Aware Machine Learning

ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Progressive Residual Warmup for Language Model Pretraining

Prompt Optimization Makes Misalignment Legible

Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble

ProPolar: Progressive Polar Decomposition for Implicit Neural Representations

ProtoVis-Nav: Prototypical Visual Imagination for Visual-Spatial Aligned UAV Navigation

Provable Explanations for Any-Order Neural Additive Models

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy

Pruning and Distilling Mixture-of-Experts into Dense Language Models

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding

Publishing Below-Threshold Triangle Counts under Local Weight Differential Privacy

PULSE: Probabilistic Uncertainty-Aware Longitudinal Simulation for EHR Trajectories

Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models

QuantDemoire: Quantization with Outlier Aware for Image Demoiréing

Quantifying and Optimizing Path Uncertainty in Masked Diffusion Models

Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise

Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions

Query as a Resource: Activity-Cost Guided Remote Sensing Domain-Incremental Object Detection

QUEST: Q-Learning for Uncertainty-Guided Efficient Search Teams

RA-ClipScore: Making Generative Model Evaluation More Interpretable

RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t

RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache Compression

RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud

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

RB-LDC: Redundancy-Balanced Latent Coding for Robust Diffusion

REACT: A Lightweight Reliability-Aware Framework for Spatio-Temporal Out-of-Distribution Prediction

RealDev-QA: Trajectory-Level Diagnosis for Developer RAG Under Real-World Noises

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

RECAP: Looking Once Is Not Enough for Vision-Language Reasoning

Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning

ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts

Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing

Recursive Multi-Agent Systems

REDACTED-Tunes: An Open 1.4M-Track Dataset and Perceptual Benchmark for AI-Generated Music

Re-evaluating Continual Learning with Few-Shot Adaptation

Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

Reflection with Action-Induced Visual Differences for Desktop GUI Agents

REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge

Reformulate LLM Reinforcement Learning for Stable Training under Black-box Discrepancy

Reinforcement Learning from Rich Feedback with Distributional DAgger

Relaxation-Aligned State Control for Test-Time Scaling in Generative Combinatorial Optimization

RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies

Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation

Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models

Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation

RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

Reranking with Intra-modal Visual Association for Text-to-Image Person Re-Identification

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data

Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching

Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective

Rethinking Memorization–Generalization Trade-Off in Generative Models

Rethinking Molecular Graph Backdoors under Chemistry-aware Admission

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS

Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle

Revisiting Activation Steering Through an Optimization Lens

Revisiting Decentralized Online Convex Optimization with Compressed Communication

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Richer or More Gates? Fan-In Trade-offs in Learnable Logic Circuits

Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization

RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement

Right Results, Wrong Reasons: Auditing Behavioral Reliance in Motion Forecasting

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

Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction

Robust and Efficient Backdoor Mitigation for ML Models via Tolerant Property Testing

Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures

Robust Statistical Estimators with Bounded Empirical Sensitivity

Robust Stream Classification using Time Neutralising Decision Trees

RoLL: Robust Low-Rank Learning via Nesterov Momentum

Root Cause Analysis of Measurement and Mechanistic Anomalies

Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness

ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models

Rosetta: Composable Native Multimodal Pretraining

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection

RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control

S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields

S3Former: Sequential, Structural, and Statistical Fusion for Continuous-Time Dynamic Graphs

SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering

SAFE-FEC: Semantically Constrained Adversarial Frontier Evolution for Factual Error Correction

SAFE-Hair: Scalp-Anchored Fields for Exportable Single-View Hair Reconstruction

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use 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

Sampling Is Not Curiosity: Why LLM Agents Should Investigate

SCALECUA : Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL

Scaling Laws for Multimodal Data Mixtures

Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations

Scaling Point-in-Time Language Models: Economic Evaluation of Embeddings

SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

SCTI: Self-Calibrated Trident Identification of Black-Box LLM Watermarks

SDHilb: Schrödinger Dynamics-Guided Neural Network with Adaptive Multi-Scale Hilbert Transform for Time Series Forecasting

SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation

SearchV: Evolutionary Fine-Grained Visual-Token Skipping for Efficient Vision-Language Models

Second-Order Complexity of Neural ODE Inference

Second-Order Complexity Theory for Risk, Explanation, and Calibration in Machine Learning

Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation

Seeing the World through Any Eyes

Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation

Selective Answering for Medical VQA via Parallel Independent Claim Verification

Selective Safety Steering via Value-Filtered Decoding

Self-Adjoint Flow Policy Optimization

Self-Cleaning Diffusion Models

Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery

Self-Supervised Reconstruction Knockoffs for Calibrated Unsupervised Feature Selection

Semantic-Bridge Federated Learning: Bridging CLIP Semantics for Heterogeneous FL

Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models

SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences

SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data

SF-DST: Adapting Vision-Language Models for Anomaly Detection via Asymmetric Modulation and A-LoRA

SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws

ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers

Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation

ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents

SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models

SignalBench: Comparing Dense Feedback Methods for Long-Horizon Agents

Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise

Signed-Permutation Coordinate Transport for RMSNorm Transformers

SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity

Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators

Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems

SimVLA: Attributing Gains in VLA Models Through Controlled Ablation

Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention

SitCom: Scaling Egocentric Multi-Party Spoken Dialogue for Situated Communication Assistance

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search

SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning

Smooth Partial Lotteries for Stable Randomized Selection

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

Sobolev Regularized MMD Gradient Flow

SODA: Selective Optimization with Deferred BN Alignment for Efficient Dataset Distillation

Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models

SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers

SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide Shots

Spark: Path-Aware Experiential Self-Evolution for VLMs Spatiotemporal Reasoning

Sparse blind deconvolution via thresholded Wirtinger flow

Sparsely Wired Mortal LLM Inference

Sparsity for Free: A Budget-Induced Equilibrium in Joint Topology–Parameter Search

SpatialBench: Is Your Spatial Foundation Model an All-Round Player

SpatialVAM: Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Speak Early: Speculative Speech Generation for Low-Latency SpeechLLMs

SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task

Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting

Spectral Progressive Diffusion for Efficient Image and Video Generation

Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model

SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding

SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models

Spikes as Detectors: Phase-Conditioned Spiking Dynamics for Time-Series Anomaly Detection

SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers

SPRM: From Cooperative Games to Marginal-Contribution Process Reward Modeling

Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios

SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Stable3R: Streaming 3D Reconstruction with Stable Geometric References

StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video

Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

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

StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems

Static-to-Dynamic: Animating Still Mattes via Generative Motion for Video Matting

STDec: Spatio-Temporal Stability Guided Decoding for dLLMs

Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

Steering Optimisation Trajectories in Diffusion Representation Learning

Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts

StructBridge: Structure-Grounded 3D Indoor Object Generation via 3D Latent Diffusion Bridge and Normal Refinement

StyleRoute: Diffusion Style Transfer via Regional Routing and Conflict-aware Projection

Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation

SwiftFlow: An Efficient One-Step Policy Learning via Improved Mean Flow for Robotic Manipulation

SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting

SynTeX-FL: Cross-Modal Text Transfer in Federated Learning for Medical Visual Question Answering

T3-S2S: Training-free Triplet Tuning for Sketch to Scene Generation

TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition

TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery

Tail Cues, Principal Corrections: Plug-and-Play Rectification for Open-Set Test-Time Adaptation

TailDiff: Elicitable Tail-Guided Diffusion for Risk-Sensitive Generation

TasteBench: multimodal benchmark for sensory prediction, from molecules to sustainable foods

Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies

Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher

Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models

Temporal Smoothness Constraints on Efficient Neurobiological Codes Imply Temporal Specialization

TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection

Testable and Actionable Calibration for Full Swap Regret

Test Time Search Requires Training for Diversity

Test time training enhances in-context learning of nonlinear functions

Text-side fragility in contrastive vision-language retrieval

TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization

The $1/\mathcal{W}$ Law: Context Length is the Dominant Energy Lever in LLM Inference Fleets

The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining

The Cost of Symmetry: Universality and Hardness for Permutation-Invariant Neural Networks

The Illusion of Multi-Agent Advantage

The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty

The Locality Cost of Semantic Patch Self-Distillation

The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation

The Minimax Rate of Online Isotonic Regression on Product Orders

The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative Guidance

The Reciprocity Gradient

The road reaches every place, the short cut only one: Self-Adversarial Shortcut Mitigation for AI-Generated Image Detection

The Spectral Amplitude Principle for Dynamics of Quantum Neural Networks

The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval

The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents

Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance

Thompson Sampling using Prior-fitted Diffusion Transformers

Tight Gap-Dependent Regret Bounds and Problem-Independent Bounds for Cost-aware Cascading Bandits

ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning

TopoRefine: Topology-Aware Correspondence and Residual Refinement for Training-Free Subject-Consistent Generation

To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation

Toward a theory of Evaluability

Toward Better Geometric Representations for Molecule Generative Models

Toward Interactive Understanding of Code APIs

Toward Minimal-dimensional Convex Calibrated Surrogate Losses for Classification with Rejection

Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents

TRACE: Trajectory-Aware Conceps for Explainable Video Understanding

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens

Traffic STGNNs across Sensor, City, and Time Shifts: Routing Concentration Tracks Sensitivity to Sensor Dropout

Training Deliberative Monitors for Black-Box Scheming Detection

Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction

Training-free Spatially Grounded Geometric Shape Encoding

Training Optimal Large Diffusion Language Models

Training Vision Transformers to Focus: Emergence of Attention Head Specialization

Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning

Transition-Aware Credit Assignment in Agentic Learning for LLM Reasoning

TransMem: Transition-Aware Retrieval for Evolving Personal Memory

Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

Treat Domain-Specific Languages as Design Variables in LLM Agents

TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference

TriTD: Tri-Partite Trajectory–Distribution Distillation for Real-Time Autoregressive Video Generation

TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models

Two-Clustering Regime of Token Dynamics in Causal Attention

Two Phase Rapid Simulation Based Inference with Differentiable Simulators

UGM: Unified Multi-scale Genomic Event Modeling with Site-level Joint Prediction

U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition

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 Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance

Understanding Generalization through Decision Pattern Shift

Understanding Goal Generalisation in Sequential Reinforcement Learning

UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

UNICOM: Unified Multimodal Modeling via Compressed Continuous Semantic Representations

Unified Approach for Weakly Supervised Multicalibration

Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts

UniSHARP: Universal Sharp Monocular View Synthesis

Universal Adaptive Proximal Gradient Methods via Gradient Mapping Accumulation

Universal Time Series Generation with Neural Controlled Differential Equations

Unleashing the Power of Intrinsic-Entropy-Driven Exploration for Off-Policy Generative RL

Unlocking Any-Order Generation in Pretrained Autoregressive Image Models

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

USAD: Uncertainty-aware Statistical Adversarial Detection

Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution

V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion

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

Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments

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

VERITAS: Veracity-Enhanced Robust Identification of LLM-generated Text Against Style-shifts

VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training

VESTA: Visual Exploration with Statistical Tool Agents

ViCoR: Estimating Visual Necessity via Counterfactual Residuals for Multimodal Medical Data Selection

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

Video-FLAIR: Not Whether to Reason, But How

ViDiC: Video Difference Captioning

VISD: Enhancing Video Reasoning via Structured Self-Distillation

VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries

Visual Anchoring for Scenario-Guided Forecasting

Visual Grounding First, Multimodal In-context Learning Follows

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models

VUM: Visual Unified Models for Image Generation and Perception

Wayfinder: Adaptive Resource Routing from Agent Citations

Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions

WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime Environments

What Claims Do LLM Benchmark Scores Support?

When Alignment Fails: Stabilizing Cross-Dynamics RL with Prototype Trust Regions

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 SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds

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 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 Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning

When Do Learned State Representations Break Sensitivity Analysis?

When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets

When Poison Meets Structure: Topology-based Defense against Poisoning Attack on Graph-based Retrieval-Augmented Generation

When Prompt Internalization Breaks: Continuous Experience Internalization in Large Language Models

Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering

Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?

Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition

Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers

Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs

Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning

Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning

Why Heavy-Tailed Weights Predict Model Quality

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning

WorldForge: Forging Unified World Modeling into Video Generation

World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

WsiSSM: A Weakly Supervised Subset-Matching Framework for Unified Classification and Segmentation of Histopathology Whole Slide Images

WURI: Watching Unfolding Risk in Agent Interactions

You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace Expansion

Your Teacher Can’t Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations

Zero-Shot Coordination among LLM Agents

Zero-Shot Instruction Following in RL via Structured LTL Representations

(ends 8:00 PM)

WED 9 DEC

9 a.m.

Sydney Invited Talk:

Satinder Singh

(ends 10:00 AM)

10 a.m.

Sydney Poster Session 3 [10:00-1:00]

Posters 10:00-1:00

$\mathrm{Bounded\mbox{-}RS}$: A Bounded Evaluation Protocol and Testbed for Representational Systematicity

$R^3$: 3D Reconstruction via Relative Regression

$\textbf{EchMo}$: 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

3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows

A2I: Adjacency-to-Image Structural Encodings for Graph Learning

AcceleGrad#: Adaptive Geometry-Aware Acceleration

Accelerated Image Editing via Consistency-Aware Source Token Pruning

Accelerating Neural Network Training with Augmented Koopman Dynamics

Achieving Better Local Regret Bound for Online Non-Convex Bilevel Optimization

A Cross-Interaction Neural Architecture for Submodular Functions

Active Learning From Positive and Unlabeled Examples

Active Memory Feedback Loop for Fast–Slow Dynamics in Liquid Neural Networks

AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL

Adaptive Communication Range for Scalable Cooperative Multi-Agent Reinforcement Learning

Adaptive Fine-Tuning Scheduler for Multi-Tenant Edge LLM via Convergence-Aware Bandits

Adaptive Gated Simplicial Propagation for Node Classification in Multimodal Graphs

Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling

AdaTree: Serving-Aware Adaptive Tree Construction for Speculative Decoding

Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options

A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry

Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning

AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Agentic Multi-Turn Reasoning: A Fairness Approach

Agentic Neural Architecture Search

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition

AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning

AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers

Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks

Aligning Flow Map Policies with Optimal $Q$-Guidance

ALIGN-Rec: Continual Recommendation under Heterogeneous Unlearning Requests

AlloGen: Conformation-Selective Binder Design with Differential State Scoring

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 Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems

Amortized-Precision Quantization for Early-Exit Vision Transformers

Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models

Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models

ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark

Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG Measurement

AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs

Announced Breaks Separate Conformal Reliability from Frequency Calibration

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer

Anytime-Valid Conformal Risk Control

Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Approximate Memory Suffices for Universal Approximation with State Space Models

Approximation in Contrastive Representation Learning

AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning

Archimedean Copula Inference via Taylor-Mode AD

Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge

A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data

Asking the Right Questions: Improving Reasoning with Generated Stepping Stones

AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents

Assessing Sample Quality in Conditional Generation under Compositional Shift

Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition

Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse

Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics

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

Attention Alignment Between Humans and Vision-Language Models

Attention-Based Sampler for Diffusion Language Models

Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers

Attributions All the Way Down? The Metagame of Interpretability

Auditing Correlated Failures in Frozen-Feature Pretrained-Encoder Pools for Medical Segmentation

Auditing Privacy Leakage in Tabular Foundation Model Embeddings

Auditing the Judge: Human-Grounded Bias Discovery, Quantification, and Mitigation in LLM Judges

Augmented Lagrangian Predictive Coding

A Unified Framework for Adversary-Aware Differential Privacy Bounds

A Unifying Perspective on Language Model Interpretability

Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents

AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

Avoiding Obfuscation with Prover-Estimator Debate

Balanced Multi-Task Learning from an Optimality-Gap Perspective

BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows

Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods

BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting

Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood

Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence

Below the Reliability Floor: Recovering True Success from Judge-Gated Loops

Benchmark for Assessing Olfactory Perception of Large Language Models

Benchmarking Optimizers for Large Language Model Pretraining

Benchmarks Design under Data Scarcity: From Coarse Labels to Diagnostic Evaluation of Biosynthetic Gene Cluster Models

Best-of-$N$ Guidance for Test-time Diffusion Alignment

Better Language Models Require Better Domain-Specific Inductive Biases

Beyond Coordinates: Encoding Graph Structure via Contextual Distribution and Relational Similarity

Beyond Correctness: Robustness-Driven Evolutionary Self-Training for Large Language Models

Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models

Beyond difficulties: Insights for provably efficient design of autocurriculum in RLVR

Beyond Downstream Scores: Controlled Diagnostics for Point-Cloud Self-Supervised Learning Evaluation

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing

Beyond Global Alignment: Structured Compositional Reasoning for Vision-Language Models

Beyond High and Low: Evaluating Graded Cognitive Diversity in LLM Persona Simulations

Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors

Beyond Outcome Rewards: Process-Aware Optimization for Search Agents

Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment

Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging

Beyond Prediction: Steering VLM Agents with Retrospective World Modeling

Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment

Beyond Row Alignment: Virtual-Camera-Aware Online Stereo Rectification

Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion

Beyond Single-Shot Conditioning: Test-Time Condition Refinement for Diffusion-Based Image Restoration

Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion

Beyond Structural Agnosticism: Stable-Rank-Guided LoRA for Structure-Aware Fine-Tuning

Beyond the Node Barrier: Zero-Shot Strategy Planning for LLM Training on Super-Nodes

Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation

Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes

Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG

BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data

Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences

Biomedical Acquisition-induced Style Shifts as Mixture Shifts: Style-aware Mixture-of-Experts Multimodal Prompt Learning

Birth-Death Structural Learning for 3D Gaussian Splatting

Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization

Block Optimism for Nonstationary Bandits with Latent Linear Dynamics

Block Sparse Flash Attention

Blur Issue Matters for Thermal Novel View Synthesis: A Floating Gaussian Suppression Approach

BoardGameArena: A Multi-Dimensional Benchmark for Strategic Reasoning of LLMs in Board Games

Boosting Graph Contrastive Learning via Manifold-Guided Representation Disentanglement

Bounds on Extrapolation across Phase Transitions with Generalized Regression

BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-Tuning

Brain Economy-Aligned Graph Transformers

Breaking Information Islands in Sparse Tuning via Small-World Connectivity

Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View Generation

Breaking the Static: Dynamic Text Conditioning for Diverse Image Generation

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 the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining

Brittlebench: Quantifying LLM robustness via prompt sensitivity

ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment

C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-Tuning

Can 4D Foundation Models Remember?

Can AI Agents Synthesize Scientific Conclusions?

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale

Can LLMs Reliably Grade Olympiad Proofs? A Controlled Study of Mathematical Verification with LLMs

Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance

CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening

CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios

Causal discovery needs explicit epistemic standards

Causal Discovery over Clusters of Variables in Non-Markovian Systems

Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning

Causal heteroscedastic structure learning from incomplete temporal data

Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization

ChainForge: Tool-Chain Hijacking Attacks against LLM Agents via Execution-Grounded Tool Synthesis

Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine

Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification

ChildPose: Foundation for Children Pose Modeling

CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination

Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions

CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

Clapping: Removing Per-sample Storage for Pipeline Parallel Learning with Communication Compression

Class-Incremental Learning via LoRA-based Elastic Ensemble of Experts

Claude Coke: Prevent Automated Crime by Agents

Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting

Coarse-to-Fine Autoregression over Hierarchical Discrete Codes for Molecular Graph Generation

Co-evolution: A "One-to-many" LLM Fine-Tuning Paradigm

Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization

Combating Data Laundering in LLM Training

Communication-Efficient Federated Learning of Latent Patient Representations from Multi-Institutional EHRs

Communication-Efficient Personalized Adaptation via Federated-Local Model Merging

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning

Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification

Component-Based Out-of-Distribution Detection

ComPose: When to Trust Hands for Object Pose Tracking

Compose Your Oracles: Off Policy Improvement with Aggregated Guidance

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

Concept-Based Mechanistic Interpretability Needs a Concrete Evaluation Paradigm

Conclusions from Circuit Extraction Depend on the Level of Description: A Controlled Comparison

Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates

Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation

ConforFlux: Particle-Guided Trunk Repulsion for Diverse Protein Conformations

Conformal Cache: Reliable Proxy-Discrepancy Caching for Fast Generative Inference

Constrained Factorization with Diagonal Scaling: Rank-Revealing Training and Pruning

Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives

Contact Geometry for Generative Models: An Unbalanced Optimal Transport Formulation

Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties

Context-Aware Generative Imputation for Robust Multimodal Learning in Missing Modality Scenarios

Continually Evolving Skill Knowledge in Vision Language Action Model

Continuously-Augmented Hybrid Masked Diffusion Model for Data Imputation

Contrastive Retrieval Heads for Improved Attention-Based Reranking

Contribution-Aware Structured Sparsity for Model Merging

Control-Augmented Autoregressive Diffusion for Data Assimilation

Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design

CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy

CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewards

CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization

CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection

Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback

Correspondence Pruning by Iterative Structural Rectification

Counting without Scale: Scale-Consistent Error Correction for Crowd Counting

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation

Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations

Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly well

Cross-Model Transfer Attacks against Large Vision-Language Models via Model Diversity Enrichment and Stochastic Parameter Sampling

Cross-Question Reliable Reinforcement Learning

CSBench: A Comprehensive Benchmark for Evaluating Project-Level System Construction in Computer Science

DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving

DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy Alignment

DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems

Decide Before You Record: Heterogeneity-Guided Pre-Acquisition Stimulus Selection for Cross-Day Neuroprostheses

Decomposing and Reshaping Scaling Laws through Token Learning Times

Decomposing Effects in Neural Causal Models

Decomposing how prompting steers behavior

Decomposing Temporal and Job-Induced Dynamics for Probabilistic Computing Workload Forecasting via Graph-Conditioned Dual-Branch Diffusion

Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student

Decoupling Label Shift and Surrogate Gradient Errors for Robust Federated Spiking Neural Networks

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality

Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows

Deferred Aggregation in Hierarchical Bayesian Optimization

Deformable 2D Gaussian Splatting

Delve into the Applicability of Advanced Optimizers for Multi-Task Learning

Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model

Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability.

DexMirror: Real-to-Sim Scene Mirroring for Sim-to-Real Dexterous Manipulation

DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling

DIAL: A Bounded-Monotone Adapter with Closed-Form Residual $L_\infty$ Bounds for Scalar-Controlled Refusal Modulation

Differentiable Cluster Discovery in Temporal Graphs

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models

Diffusion Guidance Is a Controllable Policy Improvement Operator

Diffusion Path Samplers via Sequential Monte Carlo

Diffusion-warm sampling of the XY model enables fast thermalization at scale

DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

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

Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models

Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling

Disentangling Homophilic and Heterophilic Patterns for Multi-Domain Graph Foundation Models

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

Distance Marching for Generative Modeling

Distilling Conditional Image Generators into Spatial Effect Maps

Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection

Distributionally Robust Black Box Optimization-based Bidding Strategy in Auction-based Federated Learning

Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules

Distribution Matching Distillation without Fake Score Network

DN-Flow: Driver–Navigator Structured Flow Matching for Mixed-Type Tabular Data Generation

Does Inference-Time Reasoning Really Improve Video Understanding?

Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT

DPA: Decentralized Primal Averaging with Quasi-Global Momentum for Highly Heterogeneous Data

DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model

Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts

Driver Attention as Competitive Allocation: A Scene--Task-Aware Dual-Branch Framework

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning

DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization

DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling

Dynamic Convolutions Improve Transformers

Dynamic Model Merging Made Slim

Dynamic Physical Adversarial LED Patterns via Reinforcement Learning

Dynamic Resolution Routing for Efficient Egocentric Grounding

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

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

ECG Dataset with Multi-Expert Annotations and Delineations

Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding

EDEN: Emergent Dynamics in Evolutionary Neural-networks for Robust Continuous Control

Edge of Stability Selectively Shapes Learning Across the Data Distribution

EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing

Editing Large Language Models with Geometry-Aware Regularization

Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models

EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction

Effective Knowledge Conflict Detection via Joint Agentic Optimization

Efficient and Accurate Zero Shot Generation of Symmetric Protein Complexes

Efficient Benchmarking Is Just Feature Selection and Multiple Regression

Efficient bias mitigation in T2I diffusion models using Concept Graphs

Efficient Evaluation of LLM Performance with Statistical Guarantees

Efficient Forecasting of Task Failures in LLM Agents through Adaptive Fault Injection

Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue

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 Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management

EgoTac: In-the-wild Tactile Prediction from Egocentric Vision

EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery

Eliciting Zero-Shot Named Entity Recognition in Large Language Models via Instruction Semantic Elaboration

Embeddings for Preferences, Not Semantics

Emergence of Physical Intelligence via Controllable Information Production

Emergent representations of graphical structure in mechanistic neural models of causal judgment

Emotion-Trained Vision Models Do Not Necessarily Learn EEG-Aligned Facial Dynamics

Empowering Time Series Analysis with Large-Scale Multimodal Pretraining

Encoding RNA Topology into Synthetic Alignments for 3D Structure Prediction

End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems

Energy-Based Operator Learning in Function Space

ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning

Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models

Entropy Guided Dynamic Patch Segmentation for Time Series Transformers

Environment-Robust Representation Learning with Empirical Bayes

EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation

EpiStream: Utility-Aware Temporal Abstraction for Dense-Action Streams

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

Equivariant Spherical Transformer for Efficient Molecular Modeling

Escape the Context Manifold: Preventing DiT In-Context Editing via Conditional Flow Hijacking

ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning

Estimating Implicit Regularization in Deep Learning

Euler-Mamba: Learning Resolution-Invariant State Evolution on Polar Manifolds for Asymmetric Pansharpening

EvalAwareBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models

Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints

Evolutionary foraging in grids: Intermittent search emerges as an optimal strategy

Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics

Expanding Flow Maps

Expanding LLM Agent Boundaries with Strategy-Guided Exploration

Expanding the Role of Diffusion Models for Robust Classifier Training

Explanation Multiplicity in SHAP: Characterization and Assessment

Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving

Exploiting Negative Multi-Cluster Structure in Class-Wise Embeddings for Weakly Supervised Multi-Label Learning

Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation

Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning

Extraneous Cognitive Load in Large Language Models

F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation

FACETS: Cross-Granularity Vision--Language Modeling for 3D Anomaly Detection

Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

Failure-Band Authorization for Filtered Retrieval

Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation

FalconPerception-HD: High Density Perception via Reinforcement Learning

Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

Fast Algorithms for the Label Propagation Operator on Signed Graphs

Fast and Consistent Structure Learning in Graphical Models via Approximate Cross-Validation

FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model

Faster Dynamic Graph Clustering with Hierarchical Graph Contraction

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Federated Concept-Based Models: Interpretable models with distributed supervision

Federated Unlearning with Gradient Adaptive Shaping

FedIBS: Federated Vision-Language Adaptation via Intrinsic Bias Selection

FedSOUL: Federated Continual Unlearning via Spectral Orthogonality

Feedforward Novel View Synthesis for Heterogeneous Cameras

FENet: Functional Embedding Neural Network for Change-Point Detection in Functional Time Series

Few-shot Task Learning via Compositional Concept Inference

Few-Shot Visual Concept Extraction for Steering Diffusion Transformers

Few-Step Cofolding with All-Atom Flow Maps

FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance

FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation

Fisher-Glass: Tail Sample Complexity from Nuisance-Projected Fisher Information

Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models

FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting

FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries

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

FLoRA-Chef: Making A Good LoRA Recipe in Federated Generalization

Flow Equivariant State Space Model

FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems

Flow Matching from Viewpoint of Proximal Operators

FlowMoP: Stochastic Multi-Person Motion Prediction

FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

fNIRSAtlas: A Large-Scale Benchmark for Functional Near-Infrared Spectroscopy Classification

Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards

Focusable Monocular Depth Estimation

Follow the Regularized Leader Does Not Converge in Constrained Optimization

Forecasting Microbial Dynamics: Evaluation Protocol and Prior-Spectrum Benchmark

FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images

FrameSelect: A Unified Library for Video Frame Selection and Evaluation

FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry

From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce

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 Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents

From Matching to Reasoning: Query-Aware Long Video Summarization

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

From Post-Hoc to Ante-Hoc: Consistently Explainable Semi-Supervised Time Series Classification

From “Weak” Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

FTerViT: Fully Ternary Vision Transformer

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

FuncFormer: Circuit Representation Learning via the Flow of Functional Propagation

Functional Gradient Descent with Adaptive Representations

G2Fusion: Geometric-to-Generative Image Fusion via Registration-Restoration Evolution

GADMVP: Adaptive Few-Shot Graph-Level Anomaly Detection with Multi-View Structured Prompting

GaitLingo: Self-Supervised Gait Representation Learning with Language Priors

GAMMA: Scalable 4D Gaussian Reconstruction Model for Novel View Synthesis of Monocular Videos

GauGal: Gaussian-Galerkin Electromagnetic Inverse Scattering Imaging

GEAR: Bridging the Planner-Actor Gap via Gradient-Aligned Policy Extraction

GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking

Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions

Generalized Intention Modeling in Multi-Agent Reinforcement Learning

Generating Physically Consistent Molecules with Energy-Based Models

GenRec: Knowing Where to Reconstruct and Where to Generate

GeoMamba: Geometry-Aware State Space Modeling for Image Restoration

Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift

Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMs

Geometry-Regularized Collapse Resistance via Consensus Enhancement for Federated Learning

GeoPano: Towards Geometrically Accurate Panoramic 3D Reconstruction from a Single Panorama

GeoWorld: A Geometry-First World Model for Reconstruction and Imagination

GGQR: Gaussian-Grounded Query Refinement for Feed-Forward 4D Gaussian Splatting

Git Context Controller: Manage the Context of Agents by Agentic Git

GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem

Global Importance Estimation for KV Cache Eviction

GPU Hierarchy Meets Structured Matrices: Fast Algorithms for State-Space Models

Gradient-Free Editing for Attribute Invariance in Graph Neural Networks

Graph Learning from Label Proportions using Topology-Aware Pseudo Labeling and Aggregation

Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems

Graph-Regularized Sparse Autoencoders for LLM Safety Steering

Grassmannian Geodesic Steering: Rank-Preserving Subspace Control for Inference-Time Alignment of Language Models

Ground False: Uncovering Errors in Formal Mathematics Benchmarks

GUARD: Scalable Gradient-based Unlearning with Adversarial Robustness Defense

Guidance For Prior Change via Density Ratio Estimation

Gym-Anything: Turn Any Software into an Agent Environment

Halt Fast! Early Stopping for Certified Robustness

Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Harmless in Pieces, Harmful in Motion: Detecting Multi-Agent Jailbreaks

Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration

HDL-RepoBench: Multi-Paradigm Repository-Level Code Completion for Hardware Design Languages

Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking

Hide to Guide: Learning via Semantic Masking

Hierarchical Adaptive Frame Sampling For Video Understanding

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

High-arity Sample Compression

High-Dimensional Robotic Reinforcement Learning with Developing Synergies

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization

Hit Expansion via Localized Exploration of Synthesizable Chemical Space

HOGWARTS: Mitigating Perspective Distortion for 6DoF Head Pose Estimation via Virtual Camera Space

HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields

Homological Barriers to Stable Local Nash Dynamics in Quadratic Zero-Sum Games

HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations

How Does Cutout Benefit Out-of-Distribution Generalization?

How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection

How Much Information is Needed for Accurate Kalman Filtering?

Humans Correct Their Judgements Through Debate, but Weaker AI Models Not

Hybrid Neural World Models for Physical Dynamics

Hydra-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes

HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution

I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video Generation

Identifying and Mitigating Diversity Collapse in Zero-Shot Personalization with I2I Editing Models

Identifying Latent Neural Dynamics with Recognition-Parameterized Gaussian Process Dynamical Systems

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

ImmuVis: Hyperconvolutional Foundation Models for Imaging Mass Cytometry

Importance-Weighted Operator Learning Under Probability Measure Shifts

Improved Robust Verifiable Federated Learning Based on Packed Secret Sharing

Improved Weakly Supervised Semantic Segmentation with A Relationally Optimized Prototype Memory Bank Framework

Improving LLM Final Representations with Inter-Layer Geometry

In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL

Independent Latents, Robust Neural Operators

InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories

InfoFlow: A Framework for Multi-Layer Transformer Analysis

In search of a definition of importance: Do attributions capture it?

Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

Integrating Strengths of Different Multi-Agent Workflows via Step-Aware Hybrid Topology Planning

Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction

Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMs

Internal Evaluation of Unsupervised Anomaly Detection Algorithms with Explanation

Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction

IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry

Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing

Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)

JEDI: Real-Time Jailbreak Defense for LLMs via In-Generation Detection and Intervention

Joint EM Image Super-Resolution and Segmentation with Semantic and Structural Priors

Jointly Reinforcing Diversity and Quality in Language Model Generations

Joint Optimization of Tool Creation and Use for Large Language Model Agents

Joint Sequence--Vocabulary Selection for Efficient LLM Distillation

JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments

Just Ramp-Up: Debiasing Regression-based Estimator for A/B Tests under Network Interference

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering

Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency

KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation

LACE: Latent Alignment via Counterfactual Embeddings

LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation

LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation

LAPrune: Logits-Aligned Scoring Proxy for KV Pruning via Vector Quantization

Large Language Models Enhanced Covariate-adjusted Response-adaptive Randomization Design

Large-Scale Pretraining unlocks Few-Shot Prediction for Relational Data

Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems

LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG

Learning-Augmented Online Portfolio Selection: Optimal Robustness-Consistency Tradeoffs

Learning Collision‑Free Dispatch Policies for Route‑Wise Decision‑Dependent Anomaly Detection

Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning

Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving

Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences

Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory

Learning from the Self-future: On-policy Self-distillation for dLLMs

Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints

Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers

Learning Menu-Based Mechanisms for Truthful Budget-Feasible Procurement

Learning Optimal Transport Plans Via Autoregressive Token Regression

Learning Semantic Consistency for Open-Vocabulary Dense Perception

Learning the Committor Function using Weighted Ensemble Simulations

Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

Learning to Ask: Metacognitive Action Policy for Large and Small Language Model Collaboration

Learning Transferable Cross-Day Representations for Few-Shot Neural Decoding

Learning Where to Look: Observation Policy Optimization for Thinking with Images

Learning with Multiple Correct Answers - Regret Bounds under Different Feedback Models

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents

Less is More: Compact-Token Masked Feature Learning for Skeleton Representation Learning

Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise

L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark

LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing

Linear Contextual Bandits with Quasi-Optimism

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

LiteNav: Lightweight Map-free Outdoor Visual Navigation

Literati: Towards Anytime Optimal Shape Generalized Trees via AO*

LLM-enabled Applications Require Systematic Threat Monitoring

LLM Is a Good Conditioner: End-to-End Sign Language Video Generation with VQ-Diffusion

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation

LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency

Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models

Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation

Locating and Repairing Domain Shift in VLM Trajectory Planning

Logarithmic Depth Suffices for In-Context Gradient Descent

LogicSR: A Unified Benchmark for Logical Discovery from Data

LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute

LoRAcles: Self-Supervised Weight-Space Interpretability at Scale

LoReC: Rethinking Large Language Models for Graph Data Analysis

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios

LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning

Machine Unlearning in Diffusion LLMs

MACRO: Training-free Multi-plane Attention for Closeup Render Optimization

MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM

Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse

Majority-of-Three is an Optimal PAC Learner

MAMQ-Net: A Robust Framework Leveraging Multi-level Tamper-aware Queries and Complementary Representations of Tampering Features for Progressive Image Forgery Localization

ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching

Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps

Manifold-weighted neural networks

ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

Market Incentives for AI Safety Investment

Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking

Mask-Conditioned Gradient Masking for Fine-Tuning Mixture-of-Experts Diffusion Language Models

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Matrix-Free Natural Gradient via Stochastic Truncated Metrics

Measuring Weak-to-Strong Legibility of Reasoning Models

Mechanisms of Misgeneralization in Physical Sequence Modeling

MedFlowBench: Auditing Medical Agents in Full-Study Workflows

Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks

MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

MedPsy: State‑of‑the‑Art Small Medical Language Models for Efficient Edge Deployment

MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Membrane Sensitivity and Deployment Fragility of Learnable Time Constants in Spiking Neural Networks

Memory is Not Search: Towards Proactive, Lifelong Memory in AI

MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition

Mental Health AI Must Move Beyond Diagnostic Prediction and Chat-Based Support: Toward Perspective-Aware, Multisensory Co-Experience

Mental-Models for Multi-Agent Systems

Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology

Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning

Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling

MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior

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

Minimax Optimal Two-Sample Testing under Local Differential Privacy

MiniPIC: Flexible Position-Independent Caching in <100LOC

MINT: Meeting-time INdicators for Truncation in Multi-Step Off-Policy RL

MIRAGE: Hierarchical MI-Surrogate Regulation for Graph Contrastive Learning

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models

Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models

MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol

ML Configuration Artifacts Should Be Closed Under Review

MMDiff: Multimodal Model Diffing for Feature Discovery and Control

MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs

MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization

Model Distribution-Aware Multimodal Dataset Distillation

Modeling quantum neural network gradient with reinforcement learning

ModelLens: Finding the Best for Your Task from Myriads of Models

Model Spec Midtraining: Improving How Alignment Training Generalizes

Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning

MolSpecFlow: Modality-Incomplete Molecular--Spectral Learning for MS/MS

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

MonarchRT: Efficient Attention for Real-Time Video Generation

MonoChunk3D: Monocular Online 3D Instance Segmentation with Persistent Instance States

Monroe: A Molecular Foundation Model for In-context Probabilistic Inference

MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning

Morpho-Temporal Decoupling: How Primate Neurons Expand Dendrites Without Losing Speed

MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport

MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport

MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control

MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues

MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data

MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP

Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems

Multilingual Safety Alignment via Self-Distillation

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

MySign: A High-Fidelity Motion-Capture Dataset for 3D Sign Generation in Bahasa Isyarat Malaysia

Natural Jammers: When Non-Robust Features Become Antagonistic

Natural-Language-Guided Protein Generation for Ligand-Binding Design

Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback

Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters

NesyProAct: Proactive Neural-Symbolic Control for Web Agents

Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity

Neural Preconditioned Born Series: A Metric-Matched Framework for Learning-based Preconditioners

Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone

NeuroInk: Retinomorphic Spiking Sequence Modeling for Handwritten Text Recognition

Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

Neuron Populations Exhibit Divergent Selectivity with Scale

NNCoxKL: Risk-Set Distillation from Probability-Free Prognostic Teachers for Deep Cox Models

No Free Best-of-Both-Worlds Learning in Repeated Bilateral Trade

Noise-Regularized Training for Learned Image Compression

Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement

No More, No Less: Task Alignment in Terminal Agents

Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning

Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems

Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL

Not All Tokens Should Be Treated Equally: Context Credits Reassignment

NoTA: Normalized Tensor Adaptation for Parameter-Efficient Continual Learning

NPCBench: A Clinical Apprenticeship Benchmark for Guideline-Constrained Care-Pathway Reasoning in Nasopharyngeal Carcinoma

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation

OccStress: Stress-Testing the 4D Occupancy Forecasting Chain

OFBD: Object-Focused Background Debiasing for Long-Tailed Learning

OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning

OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning

One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models

Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback

Online Data Selection for Instruction Tuning via Gaussian Processes

On Making $SE(2)$-Invariant Networks Optimal

On the fundamentals of gradient-based SAT solvers

On the Last-Iterate Convergence of Clipped Gradient Methods

OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators

OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal Regret

Optimistic Dual Averaging Unifies Modern Optimizers

Optimized Minimal 4D Gaussian Splatting for Efficient Dynamic Scene Representation

Optimizing Analytic Constants via AI-Guided Lean Proof Refinement

ORCA: Hunting Compositional Failures in Text-to-Image Diffusion

OroPrecipBench: a km-scale benchmark for spatial precipitation downscaling over complex terrain

OS-Omni: A Cross-Platform Benchmark for Generalist Computer-Using Agents

Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning

PACE: A Proxy for Agentic Capability Evaluation

PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

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

Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction

PARI: Policy-Driven Active Residual Intervention for Weakly Supervised Point Cloud Segmentation

Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers

PATH: A Dual Perspective for High-quality Text-attributed Graph Learning

Path-independent Flow Matching for Multi-parameter Generative Dynamics

PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion Sampling

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models

Permutation Sensitivity in t-SVD-based Multi-view Clustering

Persistent Planar Memory for Video World Models

Phase Kernel Lifts Capacity of Dense Associative Memory

PHIONet: Port Hamiltonian Inertial Odometry Network

PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools

PhotoFlow: Agentic 3D Virtual Photography Missions

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing

PhysFormer: Learning to Simulate Mechanics in World Space

PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

Physics-Constrained Generative World Model for Off-Road Terrain via Post-hoc Projection

PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

PI-EDG: Physics-Informed Full-Space Electron Density Generation from Molecular Geometry

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training

PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal

Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing Actions

Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions

Population-Aligned Persona Generation for LLM-based Social Simulation

Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation

Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement

Positional Encoding and Prompt-Order Sensitivity in In-Context Learning

Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable

PosterDuet: Co-Evolving Design Generation and Reward Optimization for Product Poster Synthesis

Post-Selection Distributional Model Evaluation

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection

Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels

Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation

Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery

Predictive but Not Plannable: RC-aux for Latent World Models

Predictive Representation Learning for Partially Observed Neural Dynamics

Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory

PriFT: Prior-Support Guided Token Reweighting for Supervised Fine-Tuning

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

Probability-Conserving Flow Guidance

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking

Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models

Proportionality in Ranking Compression

ProQuant: Progressive Quantization-aware Training for Edge MLLMs

ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model

Provable Joint Decontamination for Benchmarking Multiple Large Language Models

Provably Accurate Shapley Value Estimation in High Dimensions via Sparse Leverage Sampling

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization

QDMouse4M: A Multi-View 3D Mouse Spontaneous Behavior Dataset with Quantum-Dot Markers

QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space

quanda: An Interpretability Toolkit for Training Data Attribution Evaluation

Quantitative Assessment of Crystal Structure Prediction

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not

Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement

RADIUM: RadioActive Decay of Image-Underlaid Marks

RadOmni: Advancing Foundation Model for Non-contrast CT with Omni Radiology Knowledge

RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State

RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations

Rare-Class Signal Suppression in Long-Tailed Multi-Expert Fine-Tuning

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

Readiness-Aware Sample Selection for Noisy Labels with Class Imbalance

Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning

RealityTest: How People Probe AI Identity and Whether Models Disclose It

Reasoning-Aware IRT: Explainable Evaluation of Test-Time Scaling in Reasoning Models

Reasoning Poisoning: Utilizing Social-Engineering to Steer Chain-of-Thought

Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation

Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

Refinement as a Service: Algorithmic Predictor Refinement

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference

Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution

REGATE: Confidence-Calibrated Integration of Temporally-Aligned Exogenous Texts for Dynamic Graphs

Region-Normalized DPO for Medical Image Segmentation

Regularization Paths for Continuous DAG Learning

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow Models

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs

Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation

Reliability-Budgeted Edge–Cloud Adaptation for Continual Multimodal Dehazing on UAV

Reliability-Coupled Manifold-Aware Diffusion for Missing-Modality Inference

Reliable Chain-of-Thought via Prefix Consistency

Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration

ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting

RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations

Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence

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

Rest-Tuning: Data-Efficient Adaptation of EEG Foundation Models to Individuals via Resting-State Signals

Rethinking CT Synthesis through Semantics-Structure Alignment

Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions

Rethinking Knowledge Distillation for Diffusion Language Models

Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation

Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs

Rethinking Time Series Tokenization from a Frequency Perspective

Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios

Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks

Revisiting Gradient Ascent: Machine Unlearning from a Geometric Perspective for Source-Free Scenarios

Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity

Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs

Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation

RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory

RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models

RoboProcessBench: Benchmarking Process-Aware Understanding in Visual-Language Robotic Manipulation

Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration

Robust Offline Reinforcement Learning against Out-of-Distribution Dynamics in Autonomous Driving

Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts

RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism

RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks?

S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation

SAFE-DRIFT: Data Selection for Supervised Fine-tuning with Controllable Off-Target Drifts

Safety-Aware Latent Space Reasoning in Large Language Models

SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning

SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity

SAGE: Semantically Disentangled Representation Learning through Latent Geometry Constraint and Large Language Model

Same Words, Different Judgments: How Preferences Vary Across Modalities

Sampling-Based Safe Reinforcement Learning

SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery

SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?

Scalable Minimal-Change Learning for Controllable Image Editing

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons

Scaling Laws for Synthetic Pretraining in Radio-Map Prediction

Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining

SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation

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

ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection

Score-based Variational Inference via Quantum Maximally Mixed States

SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation

Search, Edit, and Fold: LLM-Guided MSA Optimization for Protein Conformation Prediction

Second-Order Complexity Theory for Neural Networks

Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes

Seeing Together, Acting Apart: Shared Environmental Understanding for Multi-Robot Navigation

Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning

Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning

Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor

Selectivity Makes State-Space Models Universal Sequence Approximators

Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization

SelfGuard: Self-Supervised Deviation Modeling for Multi-Modal Jailbreak Detection

Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation

Semantically Complementary Spectral Views Learning for Graph-Level Anomaly Detection

Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-Spoofing

Semantic Residual: A Paired-Oracle Decomposition of LLM Multi-Agent Systems under Lossy Channels

Separating Common and Unique Directions for Model Merging

Serialization Tax in Shared-Latent Exchangeable Decisions

Settling Pure Differentially Private Covariance Estimation

SGEvolve: Semantic Gradient Guidance for LLM-Driven Evolutionary Search

Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks

SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining

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

Simmer: A Scalable Pretraining Recipe for Video-Text Encoders

Simple yet Effective Budget-Feasible Procurement Auctions for Submodular Welfare Maximization

Simplified Reversible Residual Networks

Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

SkillOrchestra: Learning to Route Agents via Skill Transfer

SkillOS: Learning Skill Curation for Self-Evolving Agents

SkiP: When to Skip and When to Refine for Efficient Robot Manipulation

Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation

SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing

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

SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation

SolvMix: Learning Formulation-State Landscapes for Liquid Electrolyte Conductivity Prediction

SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver

Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge

Spatial-temporal Attributes Enhanced Prompt Weighting and Fusion for Video Recognition

SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation

Spectral Feedback for Test-Time Alignment of Protein Diffusion Models

Spectral Transformer Neural Processes

Speculative Decoding Is Per-Token, Not Path

Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer

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 Interpolation for Backward-Compatible Multimodal Representations

SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera

SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting

SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents

SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants

Stability and Generalization in Looped Transformers

Stabilizing RL+Search for Imperfect-Information Extensive-Form Games

Stable Max Coverage Under a Cardinality Constraint

State of Thought Enables Endogenous Reasoning

Statistical Mixing Guarantees for Contractive Echo State Networks

ST-Bridge: Bridging Sketch and Text with Large Language Models for Coarse-to-Fine Image Retrieval

Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond

SteerVTE: Seamless Video Text Editing with Style and Glyph Control

STEMFly: Enhancing UAV Vision-Language Navigation via Sensor Grounding, Temporal Diversity and Episodic Memory

Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces

StiCAS: Compositional Activation Steering via Stiefel Manifold Coordinate Transport

Stitched Value Model for Diffusion Alignment

STParOpt: An End-to-End Framework for Execution-Aware Parallelism Inference and Optimized CUDA Migration

StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models

StructLens: A Structural Lens for Language Models via Maximum Spanning Trees

Structural Blindness in Latent Data Assimilation: Representation Geometry Misleads Sensor Design

Structure-aware Reinforcement Learning for Protein Directed Evolution

Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search

Submodular Benchmark Selection

Subprocess-Constrained Markov Decision Processes

Support Mismatch as a Benchmark Failure Mode for In-Context Prediction

SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades

Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology

Symmetric Interventions for Eliciting Model Intent

SympFNO: Structure-Preserving Fourier Neural Operators for Physical Surrogate Modeling

Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems

SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions

Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models

Taming the Tails: Why Distributionally Robust Optimization Needs New Theory for Imbalanced Regression

TanGCE: Manifold-Aware Concept Erasure

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents

Temperature-Regulated Stochastic Sampling for Diffusion-Based High-Quality Molecular Generation

Temporal Backtracking Search for Test-time Generative Video Reasoning

Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics

Temporal Prototype Alignment for Frozen-Feature Dataset Distillation

Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs

TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows

Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling

Test-Time Learning with an Evolving Library

Test-time Scaling for Diffusion Language Models with Frequency-Aware Remasking

Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization

The AI Observatory: A Public Measure of Real-World AI Use

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 Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play

The Block Catastrophe of Marginal Calibration in Certified Requirements Traceability

The Butterfly Effect in Reasoning: Branch-Structured Distributional Memory for Stochastic Agents

The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory

The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning

The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

The Geometry of Agent Skills: Non-Commutative Composition in Representation Space

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 Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

The Pok\'emon Theorem and other Fairness Impossibility Results

The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression

The Quantization Benefits of Residual-Free Transformers

The Rate-Distortion-Polysemanticity Tradeoff in SAEs

The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset

The Subjectivity of Monoculture

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail

The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation

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

Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators

ThinkSafe: Self-Generated Safety Alignment for Reasoning Models

TIDE: Trajectory-Aware Watermark Propagation for Text-to-Image Diffusion Models

TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Too Aligned to be Real: Detecting AI-Generated Images via Cross-modal Alignment Shift

Tools as Continuous Flow for Evolving Agentic Reasoning

ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning

Topology-Aware Optimal Transport for Source-Free Test-Time Adaptation in Anomaly Segmentation

TopoPrune: Robust Data Pruning via Unified Latent Space Topology

Toward Executable Multi-framework Front-end Code Generation with Self-Correction

Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion

Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning

Towards Principled Fine-Grained MoE Expert Pruning via Pseudo-Boolean Approximation

Towards Self-Supervised, Generalizable and Decomposable 4D Driving Scene Reconstruction

Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective

TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics

Track4D: Representing Dense 3D Tracking for Video Diffusion Models

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-Based Backdoors Are Not Cryptographic

Training-Free Entangler Selection for Quantum Neural Networks via Hilbert–Schmidt Geometry

Training-Free Generative Sampling via Moment-Matched Score Smoothing

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving

Transcoder Adapters for Reasoning-Model Diffing

Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic

Transformers Can Learn Multiclass Classification In-Context: Isotropy Governs Generalization

Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning

Tree-Sliced Orlicz Integral Probability Metric

TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks

TriBet: Relative E-values for Online Machine-generated Text Detection

Trie-Aware Transformers for Generative Recommendation

TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Trivialized Generative Models on Lie Groups

Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification

TrunkFish: Making Model Width Incrementally Refinable

Trust, but Don’t Verify: Epistemic Blind Spots in LLM Source Evaluation

Trustworthy AI Must Account for Interactions

Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching

Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems

Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching

Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy

Uncovering the latent structure of interwoven population and temporal codes

Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization

Understanding Model Reprogramming: A Reachability and Relabeling Perspective

Understanding Randomization in Greedy Model Search

Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis

Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs

Unified Loss-Aware Density Control for 3D Gaussian Splatting

UniForm: Segment-Aware GRPO for Joint Punctuation Restoration and Inverse Text Normalization

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

Unifying Partner and Environment Diversity to Improve Human-AI Coordination

UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering

Unlocking Compositional Generalization in Continual Few-Shot Learning

Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling

Unpacking the Evaluators: How Configuration Shapes the Evaluation of Alignment in Explainable AI

Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise

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

Utility-Constrained Policy Optimization

VAANI: Capturing the language landscape for an inclusive digital India

Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization

Variable-Length Generative Protein Design via Generalized Poisson Flow

Variational Cover Modification Steganography

Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

VicEdit: Learning to Edit Videos from Visual In-Context Examples

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

VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning

ViLo: LiDAR Localization with Vision-Language Priors

VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual Instructions

Vision Token Pruning via Query-Vision Interaction Decomposition

Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images

Visual-Advantage On-Policy Distillation for Vision-Language Models

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models

Vortex: Efficient and Programmable Sparse Attention Serving

Walking the Hypercube: Unbiased Quantum Partition Functions Without the Matrix

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

Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning

WavCIL: Wavelet Coefficient-Domain Invariant Learning for Dynamic Graph OOD Generalization

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them

What Arranges Features in Activation Space? Non-Classical Predictive Geometry in Next-Token Predictors

What Cohort INRs Encode, and Where to Freeze Them

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation

What the Geometry of Good Models Tells Us

What to Forget in Unlearning? Forget Set Curation for Language Models

When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition

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

Where and When Identity Forms: Identity-Vital Attention Redistribution for Training-Free Subject-Driven Generation

Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning

Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis

Why Routers Freeze: Infinite Width Learning Dynamics for Mixture of Experts

Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression

Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers

WordEval: Evaluating Word-Native Operation Fidelity in Document Editing

Words That Make Language Models Perceive

WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction

X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation

xHC: Expanded Hyper-Connections

Z-AXIS: From Deterministic Ground to Agentic Depth for Enterprise Evaluation

Zeroth-Order Sharpness-Aware Learning with Exponential Tilting

Placeholders 10:00-1:00

Sydney Temp BTF Poster Holder 1-1

Sydney Temp BTF Poster Holder 2-1

Sydney Temp BTF Poster Holder 3-1

Sydney Temp BTF Poster Holder 4-1

Sydney Temp BTF Poster Holder 5-1

Sydney Temp BTF Poster Holder 6-1

(ends 1:00 PM)

11 a.m.

Creative AI Session 3 [11:00-2:00]

(ends 2:00 PM)

2 p.m.

Sydney Invited Talk:

To score or not to score

Cheng Soon Ong

(ends 3:00 PM)

3:30 p.m.

Sydney Oral Session 2F [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 2A [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 2B [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 2C [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 2D [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 2E [3:30-4:30]

(ends 4:30 PM)

4:30 p.m.

Creative AI Session 4 [4:30-7:30]

(ends 7:30 PM)

5 p.m.

Sydney Poster Session 4 [5:00-8:00]

Posters 5:00-8:00

$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning

$PAS^2$: Physics-Anchored Spectral Reasoning for Air Quality Forecasting

$\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics

A Batched Hartigan's $k$-Means Clustering

A Benchmark for Omni-Modal Reasoning in Long Videos

AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration

AC/DC on a Budget -- Alternating Sparse Phases

AdaCodec: A Predictive Visual Code for Video MLLMs

AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions

Adaptive Attribute Completion with Representation Space for Incomplete Graph Domain Adaptation

Adaptive Joint Testing of Policies in Discounted Markov Decision Processes

Adaptive multiscale operator correction via learned spectral subspace and physics-informed optimization.

AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift

ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models

AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising

ADMIT: Support-Gated Memory-Write Admission for Document QA Agents

A Dual-Domain Vision Transformer with Spectral Positional Bias

Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models

Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization

Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners

AEGIS: Almost Surely Safe Offline Reinforcement Learning

AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation

Agent$^2$ RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?

Agent Explorative Policy Optimization for Agentic Multimodal Reasoning

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

AI Control for Sandbagging on Fuzzy Tasks

AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection

Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

Aligning Inductive Bias for Data-Efficient Generalization in State Space Models

Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models

AMGenC: Generating Charge Balanced Amorphous Materials

A Model of Diverse Sampling from Language Models

An Equivariance Principle for Optimizer Design: Symmetry-Compatible Updates for Embeddings, LM Heads, and MoE Routers

Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion Editing

AppCIF-Bench: An Application-Level Complex Instruction Following Benchmark for Large Language Models

Approximation of Maximally Monotone Operators : A Graph Convergence Perspective

Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events

A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees

ARES: How Reliable Are LLM User Simulators for Recommender A/B Testing?

A Retained-Signal Interface for LLM Watermark Robustness under Paraphrase

ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation

ARROW: Augmented Replay for RObust World models

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling

Artificial Aphasias in Lesioned Language Models

ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning

ASH: Agents that Self-Hone via Embodied Learning

Ask-E: An Environment for Calibrated Question Generation

Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?

Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling

A Stability Analysis of AdamW: Unstable Equilibria and Non-Convergence

A Statistical Framework for Algorithmic Collective Action with Multiple Collectives

A Subgoal-driven RL Framework for Improving Long-Horizon Web Agents

A Surrogate Perspective on Convergence of Fixed-Target DQN

AsymPipe: Accelerating Large-scale DiTs Image Editing via Asymmetry-Aware Pipeline Parallelism

AsyncOPD: How Stale Can On-Policy Distillation Be?

A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

A Trust Region Approach for Learning Schrödinger Bridges

Attribution-Guided Shared-Private Decoupling for Noise-Reduced Audio-Visual Representation Learning

AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos

Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic

A Unified Framework for Image-to-3D Part Generation via Variable Granularity

A Unified Image and Video Encoder for Multimodal LLMs

AutoHoney: Automating, Deploying, and Evaluating Scheming Honeypots Across Production Codebases

Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization

Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments

Autoregressive Appearance Prediction for 3D Gaussian Avatars

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

Auxiliary Clues Aware’s Geometry Problem Solving

AVIS: Adaptive Test-Time Scaling for Vision–Language Models

Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley Axioms

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

Bandits via Additive Quantized Representations

BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition

Basis-Mediated Bilinear Attention: A New Method for Greatly Reducing Query--Key Pathway Parameters

BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates

Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds

BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments

BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation

Beckmann Transport Models: From Autonomous Flows to One-Step Maps

Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs

Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception

BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials

Benchmarking Open-Ended Multi-Agent Coordination in Language Agents

Bet Imaginatively, not Historically in Independent-Data Sequential Testing

Beyond Average Flatness: Domain-wise Flatness for Domain Generalization

Beyond Decoupled PEFT: Geometry-Aware Low-Rank Adaptation via Riemannian Reparameterization

Beyond Eigenfunctions: Divergence Principal Functions for Representation Learning

Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search

Beyond Flat Gossip: Tiered Gossip Learning for Scalable Collaborative AI

Beyond IID: How General Are Tabular Foundation Models, Really?

Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms

Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural Denoising

Beyond Node Sequences: Relational Diffusion for Unified Graph Learning

Beyond Normal References: Discriminative Few-Shot Anomaly Detection

Beyond Outcome: Trajectory-Driven Prompt Optimization via Multi-Dimensional Rewards

Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept

Beyond Stabilization: Dual-EMA Teachers for Global–Local Semantic Learning in Semi-Supervised Medical Image Segmentation

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation

Binary Regression: Universal Ising Model, Binary Expansion and Beyond

Biological Graph Priors Enable Representation Learning for Cellular Microscopy

BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging

BioSafetyBench: Agentic Cascade Evaluation for the Bio-AI Ecosystem

Block-OBS-GS: Exact Per-Block Joint Brain Surgery with Gauss–Seidel Refinement for LLM Pruning

Boosting Multiagent Reinforcement Learning at High Replay Ratios with Ensemble Reset

Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation

Boundary Mass in Feature Space as a Label-Budget Diagnostic for Representations

BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning

BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning

BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning

Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models

Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers

Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning

BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling

Bridging CLIP with DINO: Cross-Modal Information Maximization for Online Test-Time Adaptation

Bridging Compute- and Data-Optimal Pretraining

Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling

Bridging the Gap: Position-Independent Cache Reuse for Hybrid SSM-Attention Architectures

BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget

Build-and-Find: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases

Busemannformer: Horospherical Self-Attention for Hyperbolic Graph Transformers

C2G-BENCH: A Cyber-Physical Evaluation Benchmark for Hierarchical Reinforcement Learning in Grid-Interactive Hyperscale Data Centers

C3: Long-Horizon Character Consistency via Causal-Continuous State Dynamics and Memory Rewriting

C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation

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

CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

Calibrating Generative Models to Feature Distributions with MMD Finetuning

CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying

Can LLMs explain themselves truthfully with code?

CAPER: Clause-Aligned Process Supervision for Text-to-SQL

Capricorn: Highly Efficient and Secure Mixture of Experts Inference Framework

CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search

Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs

CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes

CHAIN: Complementary Signed Graph Propagation for Uncertainty Quantification in Large Language Models

Chain-of-Thought Is Not Explainability

Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation

Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers

Cheap Talk, Real Stakes: Commitment and Exploitation in Human-LLM Strategic Interaction

Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

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

CLIOPATRA: Extracting Private Information from LLM Insights

Closed-Form Implicit Neural Representations

Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models

Closing the Loop with Fixed-Point Self-Attention

CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning

Co-Evolving Policy Distillation

Cognitive Firewalls: A Synthetic Account of Cross-Lingual Reasoning Collapse

Commit Then Explore: Reasoning Models Diversify, Not Converge

CommunityKV: Efficient Long-Context Decoding via Graph Partitioning

COMPOSE: Composing Future Theorems from Citations and Formal Structure

Compositional Generalization Certificates via the Van Kampen Theorem

Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks

Compressing Collections of Trees with Decision Equivalence

Computational Depth Predicts Quantization Sensitivity in Multimodal Models

Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation

Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation

Conservative neural posterior estimation via distributionally robust training

Consilience for Verifier-Free Test-Time Scaling

Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability

Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning

COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

Counterfactual Explanations for Time-Series Classification via Constrained Flow Matching

Coverage-Verified Sparse Attention: Closed-Loop Quality Control for Long-Context LLM Decoding

Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models

CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter

CRISP: Compositional Reasoning over Images via Stackable Programs for VLMs

Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions

Cross Flow: One-Step Generation Across Latent and Pixel Spaces

CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation

Cross-Layer Evolution Graph Learning for Fine-grained VLM Hallucination Detection

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse

CruxBench: A Benchmark of Information Discovery

CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models

CURE: Visual Reprogramming of Vision-Language Models under Limited Supervision

Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization

Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models

DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments

Darwin-7B: A Multi-Omic Foundation Model for the Human Gut Microbiome via Sparsified Quality-Aware Tokenization

Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations

DC-Ocean: Deep Latent Compression for Global High-Resolution Ocean Forecasting

DDGE: Disentangled Dirichlet Geodesic Evaluation for Robust Few-Shot Learning

Decentralized Q-Learning in Markov Potential Games

Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations

Defining Operational Conditions for Safety-Critical AI-Based Systems from Data

DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction

Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision

DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences

Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators

Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL

Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection

DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention Discrepancy

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

DICEQuant: Distortion-Compensated Rounding with Dual-Ended Shrinkage for LLM Quantization

Differentiable Belief-based Opponent Shaping

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision

Diffusion LLMs are Natural Adversaries for any LLM

Diffusion Transformers with Residual Adaptive Layer Normalization

DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting

Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization

DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance

Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning

Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models

Disentangled Multimodal Learning for Scalable Dynamic IR-Drop Analysis

Dispatchable Coordination Envelopes for Embodied Collaboration Under Sequential Uncertainty

Distillation of Foundation Models for Time-dependent PDEs

Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs

Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving

Distributed-Order Fractional Spiking Neural Network

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

Distributionally Robust Mixture-of-Experts Training

Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation

Do Diffusion Models Learn to Generalize Basic Visual Skills?

Does Cross-Panel Pretraining Transfer Under Marker Heterogeneity? A Large-Scale Empirical Study in Clinical Flow Cytometry

Do Less, Decide Better: Optimal Human Dispatching in AI-Assisted Decisions

Do LLMs Feel Social Pressure? Locating and Steering Social Desirability Bias in LLMs

Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

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

Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing

DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams

Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes

Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL

Drift Q-Learning

DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization

DriveFuture: Future-Aware Latent World Models for Autonomous Driving

Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems

DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

DSBTR: A Diffusion Schrödinger Bridge Trajectory Refiner for Multi-Agent Trajectory Prediction

DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models

DTGS: Physics-Embedded Dynamic Thermal 3D Reconstruction with Gaussian Splatting

DualSAT: A Dual-Branch GNN-Transformer Framework for SAT Solving

Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems

Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning

Dynamic Context Modeling for Longitudinal Mental Health Monitoring under Distribution Shift

DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models

EditDistill: Is It Possible to Guide Video Editing with Image Editing

Efficient, Accurate and Stable Gradients for Neural ODEs

Efficient algorithms for linear regression with heteroskedastic errors

Efficient Computation and Best-Response Dynamics in Anonymous Two-Action Games with Linear Utilities

Efficient Prediction of Pass@k Scaling in Large Language Models

Efficient Reasoning via Constrained Optimization in Latent Space

Efficient Variational Inference for Log-Gaussian Cox Processes via Voronoi Tessellation

EGCA: A Spectral Perspective on Forward Process Design in Diffusion Models

Ego-HMB: Human Motion Bridging from Egocentric Images via Motion Bridge Diffusion Model

EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision

Eliciting Secret Knowledge from Language Models

EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes

Empirical Bayes Rebiasing

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

EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference

Energy-Adaptive Equivariant State Space Models for Noise-Robust Protein Structure Representation

Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion

Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach

Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

Error-Guided Bellman Calibration for Semi-Offline Value Estimation

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

Evidence Guided Dual Expert Memory with Joint Routing for VLLMs Online Correction

EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution

EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory

Exact Channel Decoupling via Joint Diagonalization and Uniform Splicing for Diffusion Transformer Quantization

Exact-Form Regret and Conservative Correlated Equilibria

Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method

Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows

Explaining Cross-Modal Model Behavior with Gradient-Estimation-Based Feature Interaction

Exploring Multi-Order Self-Similarity for Motion Understanding

Exposing and Mitigating Temporal Attack in Deepfake Video Detection

Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality

ExtrapAir: Air Quality Inference at Unmonitored Locations via Weather-Bridged Spatial Attention

Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL

Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking

FADE: Fractional Anomalous Dynamics Extrapolation for Training-Free Diffusion Transformers Acceleration

Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence

FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head

Fast and slow gradient descent dynamics of logistic regression through weak alignment

Fast Sandwich Products in Clifford Algebra

FC-DGCN: Deep Graph Convolutional Network for Face Clustering and Recognition

FeatCal: Feature Calibration for Post-Merging Models

Felid: A Flexible and Efficient Design for Transformer Fine-Tuning over Encrypted Data

FELPS: Fair and Efficient Scheduling for Multi-LoRA Serving System

Fewer Tokens, Fewer Layers: Efficient Vision Token Pruning and On-Policy Distillation to Accelerate VLMs

Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language Models

Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG

FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting

FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation

First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems

FISC: Time-Series Forecasting via First-Layer Statistical Calibration Constraints

FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis

FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction

FLIP: Fast and Accurate Global Lipschitz Estimation for Large Feedforward Networks

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

FlyingDrones: A Dataset and Benchmark for Optical Flow Estimation from UAV motion

FM-ChangeNet: Learning Change through Pathwise Feature Transport

FOAM: Factored One-sided Adam-Moment for Practical and Scalable SOAP

Forced Orders: What LLM Leaderboards Hide About Model Comparisons

ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching

Foundation Pareto Flow Policy for Multi-Objective Reinforcement Learning

Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification

FrequencyBooster: Advancing Pixel Diffusion for High-Fidelity Image Generation

From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model

From Clips to Streams: A Unified Framework for Streaming Sign Language Translation

From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability

From I/O to Code with Discovery Agent

From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs

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

FuseAdapt: Adaptation-Space Fusion for Multi-Modal Semantic Segmentation with Missing Modalities

GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment

GEMS-3D: A Large-Scale 3D Gravity, Electrical, Magnetic, and Seismic Earth Simulation Dataset for Multimodal Geophysical Learning

Generalizable Physics Simulation through Compositional Energy Minimization

Generation Navigator: A State-Aware Agentic Framework for Image Generation

Generative Actor-Critic with Soft Bridge Policies

GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation

Geometric Velocity Regularity for Flow Matching on Manifold-Concentrated Data

Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMs

Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality

Geometry Matters in Packed 3D Attention

GeoMIND: A Benchmark for Spatial Understanding in Robotic Manipulation

GeoRad-3D: Factorized Geometry Transport and Residual Radiometry for 3D Radar Nowcasting

GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing Segmentation

gfnx: Fast and Scalable Library for Generative Flow Networks in JAX

Glance Before You Tell: Anomaly-Guided 3D Radiology Report Generation with Heat-Conduction Slice Encoders

Global Context Guidance for Diffusion Large Language Models

Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures

GMO-E²DIT: Grounded Multi-Operation Editing for E-Commerce Images

GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

Gradient Routing Localizes and Removes Unintended Behaviors in RL

Graph and Simplicial Complex Prediction Gaussian Process via Hodgelet Representations

Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning

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

Grounding Driving VLA via Inverse Kinematics

GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents

GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes

Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer

HALO-VGGT: Heterogeneity-Aware Lightweight Online Compression Allocator for Efficient VGGT

HAMSTAR: Hamiltonian Structured Inter-Period Refinement for Long-Term Time Series Forecasting

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

HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse

HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning

Heteroscedastic Variational Last Layers

Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs

HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection

HiFloat4 Format for Language Model Pre-training on Ascend NPUs

High-Dimensional Learning Dynamics of Attention-Indexed Models

High dimensional theory of two-phase optimizers

Higher-Order Cell Tracking Transformer

HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis

HIRaD: Hidden Interaction Inference from Predictive Radar Dynamics

HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure

Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization

Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion

HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation

Horizon Adaptive Offline Policy Learning via Value Stitching

How are linear representations learned? Exact solutions to the dynamics of abstraction

How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression

How Do Language Models Compose Functions?

How Far Is Too Far? Object Recognition Declines Monotonically with Semantic Distance

How Likely Are Voting Rules Equitable?

How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding

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

HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning

HumanScore: Benchmarking Human Motions in Generated Videos

Hybrid Reinforcement Learning for One-step Degraded Infrared and Visible Image Fusion

HyperSkill: Multi-Modal Skill Learning on the Unit Hypersphere

HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding

IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories

Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access

Implicit Value Probing: Inferring Human Value Preferences via Strategic Multi-Turn Conversations

Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization

Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters

Improving Flexible Image Tokenizers for Autoregressive Image Generation

Improving Neural Processes in the Low-Data Regime via Context-Subset Training and Self-Distillation

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures

Individuals Matter: Improving Deep Multi-View Clustering via Explicit Single-View Enhancement

Inferring Computational Structure from Neural Recordings with Gain-Modulated Linear Dynamical Systems

InfiniteVL: A Systematic Approach to Highly-Efficient, Ultra-Long Multimodal Understanding

Information-Theoretic Generalization Bounds for Sequential Decision Making

In STeP: Speculative Tensor Parallelism for Concurrent Heterogeneous Inference of LLMs

Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation

IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning

Interpretable Multiway-Split Trees

Intervention-Guided Image-Free Classifier Expansion for Fine-Grained Recognition

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds

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

I-Perceive: A Foundation Model for Vision-Language Active Perception

IRCasDiff: Two-Stage Cascaded Diffusion for Compound Infrared Face Reconstruction

Irreducible Supervision Enables Compositional Generalization in Post-Training

Is a Linear Probe Evidence of a Linear Representation?

Is Dimensionality a Barrier for Retrieval Models?

Is Memorization Actually Necessary for Generalization

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness

Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

Keep or Preempt? Termination-Aware Scheduling for LLM Serving with Speculative Decoding

KernelDNA: Cross-Layer Kernel Sharing via Decoupled Neural Adapters

Kernel-Gradient Drifting Models

Kernelized Activation Steering

Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech

Knocking-Heads Attention: Drop-in Shared Projections for Cross-Head Coordination

Knowledge Transfer Scaling Laws for 3D Medical Imaging

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

KV Cache Compression via Attention Output Distortion Minimization

LAMP: Language-Modulated Geometric Preservation for Multi-Modal Object Re-Identification

Language Model Memory and Memory Models for Language

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 Models Develop Belief State Geometry In-Context

Large Language Model Selection with Limited Annotations

LARGO: Low-Rank Hypernetwork for Handling Missing Modalities

Latent Abstraction for Retrieval-Augmented Generation

Latent-Lens: Visual Perception in Small Language Models Through Latent Communication

Latent Refinement Decoding: Enhancing Diffusion Language Models by Refining Belief States

LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection

Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks

Learnable Diffusion-based Positional Encodings for Link Prediction

Learnable Spectral Activations

Learn from your own latents and not from tokens: A sample-complexity theory

Learning Agentic World Vision-Language-Action Models for Autonomous Driving

Learning Augmented Exact Exponential Algorithms

Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance

Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions

Learning Generalizable Hand-Object Tracking Control without Human Demonstrations

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation

Learning Informative Invariant Representations via Hierarchical Latent Decomposition

Learning Rate Transfer for Hybrid Transformer-SSM Architectures

Learning Reveals Invisible Structure in Low-Rank RNNs

Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

Learning Scene-Grounded Interaction Priors for Scene-Aware Human Motion Prediction

Learning Spectral Compositional Koopman Operators for Global-to-Regional Weather Forecasting

Learning Survival Models with Right-Censored Reporting Delays

Learning to Audit ML Models with Theory of Mind

Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs

Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

Learning to Recommend in Unknown Games

Learning to Surpass: Training Tool-Using Agents with Anchored Feedback

Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift

Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration

Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment

LeCellModel: Interpretable Density Estimation over the Gene Expression Manifold

Leveraging unlabelled data for generalizable neural population decoding

LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing

Linear Ensemble Sampling with Fewer Ensembles

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments

LLM-Auction: Generative Auction towards LLM-Native Advertising

LLM Flow Processes for Text-Conditioned Regression

LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference Acceleration

LLM-WikiRace: A Benchmark for Planning and Reasoning over Real-World Knowledge Graphs

Local-Interaction Learning Dynamics: A Markov Random Field Framework for Convergence of Deep Neural Network Learning

LOCU: Löwdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization

Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs

Long-Context Generation Is a Sampling Problem

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

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

Making Open-Source Text LLM Watermarks Durable Against Merging

M*: A Modular, Extensible, Serving System for Multimodal Models

Manifold-Guided Stereo-Monocular Refinement for Endoscopic Stereo Disparity Estimation

ManiFusion: Unlocking High-Throughput Generation via Superposition in Manifold Space

Many Benign Errors are Better than A Few Severe Ones: Evaluating Hallucination Severity

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR

MapShift: Controlled Post-Intervention Evaluation for Embodied World Models

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

MARS: Multi-resolution Adaptive Routing for Sequential Recommendation

MaSC: A Masked Similarity Metric for Evaluating Concept-Driven Generation

Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning

Masked Generative Pretraining Improves Cross-Dataset Transfer in Pixel-Space Diffusion

MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic Sensing

MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents

Measuring Coherence in Predictive Models

Mechanistic Interpretability with Sparse Autoencoder Neural Operators

Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search

MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning

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

MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

Memory-Efficient Federated Fine-Tuning of LLMs via Block-wise Progressive Training

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

META-PAP: Meta-learning for Prompt-aware Preference Pairing in LLM Alignment

MEV: A Multi-Event Video Dataset for Long-Take Generation

MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph

MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis

MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI

Mind the Parameters: Lightweight and Efficient Brain Visual Decoding with Shared Tensor Cores

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

Mitigating Overgeneralization in RND via Spectral Target Design

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring

MixForensics: Blend Before You Encode for Generalizable AI-Generated Video Detection

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering

MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation

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

MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic

MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation

Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP

Model Collapse is a Singular Complexity Trajectory

MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario

Motif-Mamba: network motif improved mamba for long-range sequence modeling

MSC-Mol: Modality-Synergy Contrasting for Multimodal Molecular Representation Learning

Multi-Level Alignment Framework for Long-Term Olfactory Neural Decoding

Multimodal AI Detection In Two Words

Multimodal Context-Aware Human Motion Generation with Language, Vision, and Object

Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA Design

Multiple Instance Verification

Multiscale Microenvironment Vector Space Projection for Uncovering Diverse Pathological Biomarker

Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting

Multi-view Relational Distillation for Spatial Reasoning with Vision-Language Models

Mutual Predictability Decomposition: Learning Interpretable Cross-Set Structure via Bi-Directional Prediction

NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling

NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning

Nature3D-AD: Geometry-Aware Feature Learning for Natural-Growth 3D Anomaly Detection

Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback

Near-Optimal Regret in Adversarial Kernel Bandits

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 Operator-based Curriculum Learning for Physics-Informed Neural Networks

Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generative Modeling

Next Forcing: Causal World Modeling with Multi-Chunk Prediction

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima

NIV: Neural Axis Variations for Variable Font Generation

NOFE – Neural Operator Function Embedding

Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models

Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot

OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation

Offline Constrained Reinforcement Learning under Partial Data Coverage

Offloading Score: Measuring AI Reliance through Counterfactual Workflows

OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory

OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling

On approximation and estimation of Schrödinger potentials without the curse of dimensionality

One Avatar, Any Budget: Robust LoD for Dynamic Gaussian Avatars

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

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 Unified Representation: Resolving the Appearance-Semantics Dilemma via Structural Regularization

Online Allocation with Unknown Shared Supply

Online Control with Multiple Sensors

Online Localized Conformal Prediction

On Nash Equilibria in Participatory Budgeting with Donations and Beyond

On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets

On the Necessity of Guidance Decay: From Three-Phase Analysis in Gaussian Mixture Models to Dynamic Optimization

On the Runway Cascade of Transformers for Language Modeling

OpenCoF: Learning to Reason Through Video Generation

Opponent Modeling in Incomplete-Information Continuous Colonel Blotto

Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets

Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries

Optimizing the Envy Cycle Elimination Algorithm

OrangeTree: A Linear and Tree-based Time Series Forecasting Model Supporting Multiple Input and Output Lengths

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

Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers

P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation

PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models

Pairwise AUC Optimization Needs Corrective Power: A Unified View

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models

Paradoxes of Game Theoretic Equilibria and Price of Anarchy

Parallel Broyden methods for efficiently evaluating nonlinear state space models

ParallelKernelBench: Can LLMs Write Fast Multi-GPU Kernels?

Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation

PatchKV: Weight Space Compensation of KV Cache

PatchScout: Thematic Web Data Collection via Information Foraging

PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design

PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction

Permanent and Transient Representations for Continual Reinforcement Learning

Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts

Phantom Transfer: Data Poisoning can Survive Data-Level Defences

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

Physics-Informed Functional Tucker Method with RKHS Factors for Sparse Spatiotemporal Reconstruction

PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks

PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

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

Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units

Point Tracking Improves World Action Models

Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences

PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery

PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs

Pooling Versus Ensembling for Ridge Regression Under Covariate Shift

PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty

Position: Adopt Constraints Over Fixed Penalties in Deep Learning

Position: Machine Learning Models for Reaction Transition States Deserve Better

Position Without Positional Embeddings: A Directional Mechanism in NoPE Transformers

Posterior-First Neural PDE Simulation: Inferring Hidden Problem State from a Single Field

POST: Progressive Object-Slot Tokenization for Multimodal Large Language Models

PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation

PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI

Preconditioned Flow Matching

Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants

PreDiff: Sequential Recommendation by Denoising Preference Distributions

PREPING: Building Agent Memory without Tasks

PRIME: A Modular Approach for Private Synthetic Data

Principled Design of Diffusion-based Optimizers for Inverse Problems

Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling

Prism: Harmonizing Missing Modalities via Implicit Structural Alignment on Lightweight Pulse RWKV for Multimodal Crack Segmentation

PriSM: Prior-guided Shared-basis Mixture Personalization for LLMs under Sparse User Histories

PRISM: Spectral Pruning and Reconstruction for Parameter-Efficient Model Merging of MLLMs

Private Online Prediction from Experts with Small Losses

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability

Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference

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

ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design

PROTEUS: A Self-Evolving Red Team with Surface Expansion for Agent Skill Ecosystems

Provable Pruning for Efficient 3D Gaussian Splatting via Coresets

Provably Reliable Classifier Guidance via Cross-Entropy Control

Provably Safe, Yet Performant Reinforcement Learning

PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders

Q-CoMove: Differentiable Quantum Circuit Priors for Coordinated Motion in Multi-Component Embodied Systems

Q-Focus: Let the Question Guide What to See in Long Videos

Q-Residual Physics: Hamiltonian-Structured Quantum Residual Learning for Embodied Dynamics

Quantile-Coupled Flow Matching for Distributional Reinforcement Learning

Quantile Geometry Regularization for Distributional Reinforcement Learning

Query-Limited Community Recovery in Stochastic Block Models

RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain

RadarFlowPose: Vision-Inspired Coarse-to-Fine Skeleton Refinement with Flow Matching

RADAR: Relative Angular Divergence Across Representations

Random-Effects Centroids for Domain Generalization

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

RANSAC Scoring Done Right

RAPTOR: Ridge-Adaptive Logistic Probes

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

RCSTAT: A Statistical Framework of Relative Contextualization in Transformers

REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers

Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMs

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation

Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?

REAL-MED: Benchmarking LLM Agents on Real-World Medical Tasks

Real-World Dual-Pixel Raindrop Removal: A New Benchmark and Degradation-Adaptive RWKV Baseline

Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object Detection

Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models

Reasoning with Undecoded Tokens in Diffusion Language Models

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

Recovering the Apresjan Hierarchy Using Linkage-Based Clustering

Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization

Re-examining Low Rank adaptation for private LLM fine-tuning

Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias

ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation

ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization

Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization

Reinforcement Learning Agents Are Swimmers

Reinforcement Learning-Guided Symbolic Execution for Efficient and Exploitable Smart Contract Analysis

RelAgent: LLM Agents as Data Scientists for Relational Learning

Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

Remote Photoplethysmography Based on a Skin Reflection Exponential Model

Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry

RePiD: Efficient Recursive Pixel-Space Diffusion via Hierarchical Patch Denoising

Replicability is Asymptotically Free in Multi-armed Bandits

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

Requential Coding: Measuring Model Compressibility by Coding Data Instead of Parameters

RESBev: Making BEV Perception More Robust

RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent

ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction

Resolution-Aware Structural Density Peak Clustering

Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting

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 Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient Coordination

Rethinking Projector Training in Multimodal LLMs

Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data

Rethinking Sequential Locate-Then-Edit: Optimality and Stability

Rethinking Softmax Attention: Polynomial Activations for Transformers

Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking

Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation

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

RIGOR: Risk-Gated Topology Adaptation for Robust LLM Multi-Agent Reasoning

RISE-Video: Can Video Generators Decode Implicit World Rules?

Robust Concept Unlearning in Diffusion Models via Directional Stability Regularization

Robust Conditional Conformal Prediction via Branched Normalizing Flow

Robust Latent Space Bayesian Optimization with Marginalized Kernel

Robust Multi-view Clustering against Imperfect Information

Robust Residual Correction via Selective Deployment for Time Series Forecasting

Robust Reversible Recovery for Adversarially Protected JPEG Images

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

RoPE Is Not a Proper Relative Position Embedding

Rotation-Invariant Vector Normalization for Molecular Force Learning

RotVLA: Rotational Latent Action for Vision-Language-Action Model

Route-Consistent Adaptation for Stable Quantization of Mixture-of-Experts Models with Theoretical Guarantees

RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking

Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics

RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology

S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation

S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF

Saddle-to-Saddle Dynamics in Self-Supervised Shortcut Learning

Safe Active Learning with Future Viability Guarantees in Time-Series Models

Safe Evolution with Circuit Anchors

Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning

Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation

SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology

SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

Scalable Token-Level Hallucination Detection in Large Language Models

Scaling Limits of Long-Context Transformers

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet

Scattered by Design: Why Per-Output Pruning Resists Structured Compression

SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition

SCHOLARPEER: A Multi-Agent Framework for Automated Peer Review

scMAF: Single-Cell Multi-Omics Clustering via Adaptive Modality Fusion

ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping

Search-Tree Scaling in Parallel Monte Carlo Tree Search

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 Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners

Selected-Tail Reliability in Verifier-Guided Best-of-$N$ Inference

SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

Self-Programmed Execution for Language-Model Agents

Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning

Semantic-Statistical Prior Banks for Federated Low-Shot Learning under Non-IID Clients

Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

SeqDiCO: Sequence-oriented Diffusion for Scale-Generalizable Neural Combinatorial Optimization

Sequence-to-Sequence Modeling with Camera-Induced Priors for Multi-View Stereo

Sequential Membership Inference Attacks

SFPR: Structural Fingerprinting for LiDAR-to-OpenStreetMap Place Recognition

SGNNBench: A Holistic Evaluation of Spiking Graph Neural Networks on Large-scale Graphs

Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory

Short-Context Dominance: How Much Local Context Natural Language Actually Needs?

Simplicity is Enough: ReAct Agents for Prompt Optimization

SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization

Simulating Human Memory with Language Models

Skill-Adaptive Noise Scheduling for Diffusion Policies

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking

SLiDE: Structured Linear Dynamics for Forecasting with Exogenous Inputs

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning

Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation

SoccerNarrate: Event-Grounded Streaming Soccer Commentary with Macro-Window Preference Alignment

SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions

Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning

Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems

Sparsely Supervised Diffusion

Sparse Planning in Visual World Models via Cost Gradients

Spectral Asymptotics of Neural Network Jacobians: Convergency, Universality, and Phase Transition

Spectral Degeneration of Softmax Attention under Isotropic Score Geometry

SpectralKV: Redundancy-Aware KV Cache Compression via Spectral Coreset Selection

Spherical Flows for Sampling Categorical Data

Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF

SPLICE: Structured Prompt Local Iterative Combinatorial Evolution

Split-and-scale Latent 3D Representations

Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting

SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks

SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs

Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch

Stabilizing Few-Shot Object Detection with Language-Conditioned Probabilistic Prototypes

Stabilizing the Dynamic Low-Rank Training

Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining

Standardization of Post-Publication Code Verification is Possible with the Support of the Community

STAR: Boosting Time Series Foundation Models for Anomaly Detection Through State-Aware Adapter

State Copying Crowds Out Reasoning: Mechanistic Evidence for Delta Planning in Autoregressive Models

ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling

SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting

STEER: Route-Aware Adaptive Reasoning for Autonomous Driving

STEP: Learning STructured Embeddings for Progressive Time Series

Step-wise Rubric Rewards for LLM Reasoning

STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs

Strong Stochastic Flow Maps

Structural Support Certificates for Mechanistic Hypothesis Selection

Structured State-Space Regularization for Generation-Friendly Image Tokenization

Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness Prediction

Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis

Structure, Subspace and System: Push the Real Limit of Extremely Low-Bit Quantization for MoE-LLMs

StylePlan: Style-Conditioned Intent Planning for Zero-Shot Coordination

Subliminal Learning Is Steering Vector Distillation

SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation

Sustainability in the Loop: AI Model Development Should Be Multi-Objective

SWE-GPU-Bench: Can Language Models Solve Real-World GPU Software Engineering Tasks?

SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass

SymDrift: One-Shot Generative Modeling under Symmetries

SynBench: A Benchmark for Differentially Private Text Generation

SynerVLA: Exploiting Embodied Execution Phases for On-Device Dual-System VLA Acceleration

SynGeo: Synergizing Seeing and Proving through Revisable Geometric States

T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval

TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering

Tactile MNIST: Benchmarking Active Tactile Perception

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

TailAdapt: Heavy-Tailed Sparse Variational Adaptation for Long-Tailed Class Incremental Learning

Tail-Risk-Aware Stackelberg Learning

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement

Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces

Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning

Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving

TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios

Temperature Guidance For Robust Reward Conditioning In Diffusion Planning

Test-time Multi-agent Coordination by Decomposed Value Gradient Flow

The Alternation Depth Principle for Neural Operator Design

The Design Space of Tri-Modal Masked Diffusion Models

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

The Foundation Model Transparency Index

The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws

The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics

The Laplacian Keyboard: Beyond the Linear Span

The Marauder’s Map: Bézier Manifolds Reveal Hidden Surfaces for Model Merging and Ensembling

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature Learning

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

The Scaling Paradox of Tool-Calling LLM Agents Under Realistic MCP Faults

The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility

The Symmetries of Three-Layer ReLU Networks

The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler

The VLM as Sensor: Bayesian Active Search for Long Video Understanding

Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation

Thinking with Imitation: Adaptive Reinforcement-Imitation Learning for Tool-Augmented Scientific Reasoning

Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback

TimeOperator: A Function-to-Function Approach to Time Series Modeling

Time series analysis with Gumbel dynamics

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

TOM-Pruning: Target-aware Output Manifold for LLM Pruning

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

Top-$k$ Identification with Correlated Biased LLM Judges via Anchor Leverage

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing

Toward Online Robust Zero-Sum Markov Games with Function Approximation

Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving

Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images

TraceSim: A Generative Simulator and Benchmark for Joint scRNA-seq and Lineage Tracing

Tracing Persona Vectors Through LLM Pretraining

Trading Sensing for Structure: Sparse IMU-EMG Fingertip Force Estimation via Neuro-inspired Structured Modeling

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement

Training Language Models via Neural Cellular Automata

Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning

Trajectory-Consistent Dropout for Uncertainty Decomposition in Hamiltonian Neural Networks

TrajLift: Encoding Verbal Memory Dynamics via Heat Diffusion on Semantic Hierarchies

Transferable SCF-Acceleration through Solver-Aligned Initialization Learning

Treating Hyperparameters as Interventions: Task-Invariant Representation Learning for Transferable HPO

TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Trust Region Policy Distillation

TSFM Meets LLM: Context as Covariate

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Tuning the Tuner

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

UGO: Unified Architecture for General Multi-Object Tracking by Segmentation

UltraFlash: Accelerating Megapixel Visual Synthesis

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift

Understanding Layer Patching in Model Size Interpolation

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients

UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video

UniCustom: Unified Visual Conditioning for Multi-reference Image Generation

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation

V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation

Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses

Variational Monte Carlo for Quantum Excited States via Nested Low-Rank Approximation

VecDBLens: A Modular Framework for Diagnosing Vector Databases Retrieval Pipelines

Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Verifying Agents in Rubric-Graded Environments

VeriScope: Measuring Verification-Ready Verilog Artifacts

Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification

VeriVul: A Verification-Guided Framework for Generating Realistic Vulnerability Benchmarks

Vermeer: Autoregressive generative modeling of microscopy predicts protein localization

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

VI-Bench: Benchmarking Prompt Inversion from AIGC Videos

VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Tokens

Video-Mirai: Autoregressive Video Diffusion Models Need Foresight

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding

VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model

VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

Visual Expert Skipping for MoE-MLLMs via K-Armed Bandit based Expert Estimation

VocalGrad: Evaluating Acoustic Perception in Audio Language Models

Voice "Cloning" Is Actually Style Transfer

WaveletLoRA: Frequency-Aware Content-Style Decomposition for Personalized Image Generation

WAXAL: A Large-Scale Multilingual African Language Speech Corpus

Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

What do EEG Foundation Models Capture from Human Brain Signals?

What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach

What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models

What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective

What Gets Measured Gets Managed: Sign-aware Recommendation Needs Sign-aware Evaluation

What MLLMs Learn about When they Learn about Multimodal Reasoning

What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting

What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation

What Was That Again? Certified Robustness for Automatic Speech Recognition

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

When Can Digital Personas Reliably Approximate Human Survey Findings?

When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models

When Does Structure Help? Statistical Tradeoffs for Structured Reverse Processes in Diffusion Large Language Models

When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement

When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity

When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

Which Pairs Should We Compare for DPO?

Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training

Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?

Why DiT Models Underperform as Representation Learners without Long Skip Connections

Why Learning Rediscovers the Closed-Form Diagonal Regularizer

Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models

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 Motion Models: Flexible Sequence Modeling of SE(3) Trajectories

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

WorldVLA: A Unified Vision-Language-Action and World Model

WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps

XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding

XTC: Head-Aware Sampling by Excluding Top Choices

XTraj: A Coarse-to-Fine Autoregressive Framework for Transferable Trajectory Generation

ZetaEvolve: Learning to Search through History-Conditioned Potential Value

Placeholders 5:00-8:00

Sydney Temp BTF Poster Holder 1-2

Sydney Temp BTF Poster Holder 2-2

Sydney Temp BTF Poster Holder 3-2

Sydney Temp BTF Poster Holder 4-2

Sydney Temp BTF Poster Holder 5-2

Sydney Temp BTF Poster Holder 6-2

(ends 8:00 PM)

THU 10 DEC

8 a.m.

MLRC 2026 [8:00-5:00]

(ends 5:00 PM)

9 a.m.

Sydney Invited Talk:

The Knowledge Box: AI and Epistemic Dispossession

Shannon Vallor

(ends 10:00 AM)

10 a.m.

Sydney Poster Session 5 [10:00-1:00]

Posters 10:00-1:00

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

Achieving Directional-Stationarity from a Single Random Direction Step

A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models

A Composite Activation Function for Learning Stable Binary Representations

A Computational Perspective to Data Ablation Experiments

Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation

Adaptive Entropy-Sparing for Efficient Reasoning

Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation

AdaSRU: Adaptive Source-Free Recommendation Unlearning via Gradient-Constrained Optimization

Ad-Hoc Teamwork from Human Demonstrations

Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair

Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

AET-Bench: Pixel-Accurate Atomic Tomography Is Not Atom-Accurate

A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling

A Foundational Model System for Datacenter Machine Repairs

A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing

Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback

Agentic AI Design Should be Mediated to Promote Social Welfare

Agentic Geometry Problem Solving via Human-like Parallel Bidirectional Reasoning

Agentic-imodels: Evolving agentic interpretability tools via autoresearch

Agent Security is a Systems Problem

AgentVista: Evaluating Multimodal Agent in Ultra-Challenging Realistic Visual Scenarios

Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks

Agnostic Language Identification and Generation

A Graph Foundation Model for Unified Clustering

Agree to Disagree: Multimodal Autonomous Negotiation and Calibration for Entity Representation Learning

AgriManager: A Framework and Benchmark for LLM-RL Generalization in Agricultural Management

AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation

AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes

AI Models Can Provably Hide Arbitrary Capabilities

Algorithms for Linear Equations with Min and Max Operators Under (Absolutely) Halting Condition

Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning

Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions

Alignment Dynamics in LLM Fine-Tuning

Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation

AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models

A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems

Amortized Guidance for Image Inpainting with Pretrained Diffusion Models

AMUSE: Anytime Muon with Stable Gradient Evaluation

Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation

An Efficient Geometric Characterization of Robust Fair Learning

Angular Networks: Low-Bit Learning from Randomized Similarity Estimators

Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation

AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling

ApertureAttn: Native 4K Video Generation with Image-Only Supervision

Are Well-Trained Surrogates Optimal? Rethinking the Surrogate Role with Instability for Unlearnable Examples

Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models

ASAP: Attention Sink Anchored Pruning

A Scalable Multi-Task Model for Virtual Sensors

Assign and Add: A Mechanistic Study of Compositional Arithmetic

Assistive Dueling Bandits: No-Regret Algorithms for Assisting No-Regret Users

Asymmetric Flow Models

Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse

ATLAS: Adaptive Temporal Learning for Single-Cell Multi-Omics Alignment and Dynamics

AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas

Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety

Attention Drift: What Auto-Regressive Speculative Decoding Models Learn

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models

AudioAgentBench: Evaluating Multi-Turn Voice Agents on Real-World Tasks

A Unified Theoretical Framework for Task Recognition and Task Learning in In-Context Learning

AURA: An Autonomous Retouching Agent with Photographic Visual Thinking

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

Automated Causal Effect Estimation through Self-Evolving AI

Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers

BASTION: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

BA-T: An Iterative Transformer for Two-View Bundle Adjustment

BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial Training

Bayesian Causal Experimental Design for CATE Estimation under Noncompliance

BeamWitness: Rooted Subgraph Beam Search for Selective Graph Representation Learning

Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training

Benign Reinforcement Learning Can Amplify Latent Backdoors

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

Beyond Flat Frames: Hierarchical Graph Reasoning for Long Video Understanding

Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC Ensemble

Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting

Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving

Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias

Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction

B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode

Bits Beat Tokens: A Regret Rate Distortion Theory for Large Language Model Agents

BLARM: Animating 3D Objects from Video via Blending LAtent Rigid Motion Primitives

Blind-Window Forecasting: Real-Time Benchmarking and Multimodal Reconstruction for Tropical Cyclones

Block Sphere Vector Quantization

BrainEM: A Large-Scale and Diverse Benchmark for EM Neuron Segmentation in Connectomics

Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo

Breaking the Synthesis Barrier for AI-Designed DNA Libraries

Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances

BSO: Safety Alignment Is Density Ratio Matching

Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning

Can Ideologues Agree on Quality? From Non-identifiable Latent Factors to Collective Outcomes

Can In-Context Learning Support Intrinsic Curiosity?

Cannistraci-Hebb Channel-wise Dynamic Sparse Training of Convolutional Neural Networks with Contextual Modulation

Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization

CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors

CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning

CAST: Certifiable Aggregation of Smoothed Teachers for Robust Policy Adaptation

Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization

CausalConflictBench: Can Multimodal Models Follow Local Mechanisms That Conflict with Commonsense?

Causal Discovery with False Positive Error Control

Causal Effect Identification with a Single Agnostic Proxy

CausalMix: Data Mixture as Causal Inference for Language Model Training

CEO-Bench: Can Agents Play the Long Game?

Certification-Enhanced Generalization Bounds

Chain-of-Correction: Progress-Aware Policy Steering via Anchor-Grounded Predictive Reasoning

Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation

Channel-wise Vector Quantization

Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation

Chatter Attack: Resource Consumption Attack for Large Language Models

Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences

Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents

CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models

CIPHERGRID Benchmark: From Multimodal Rule Inference to Sequential Action

Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse

ClinStab: Stability-Oriented Learning for Medical Time Series via Dual-Stream Alignment

CLUE: Closing the Loop on Conflict and Collapse in LLM Unlearning

CMI-Trans: Cross Modal Inconsistency-aware Transport for HSI-LiDAR Classification

Coarse-to-Refine: Trajectory Self-Refinement in Single Autoregressive Pass for Driving VLA

COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition

CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning

CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments

CoLa3D: Composable Latent 3D Decomposition

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

COMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning

Communication-Efficient LLM Adaptation over Decentralized GPU Meshes

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction

Comparing Linear Regions in ReLU-Type Networks: Theory and Monte Carlo Methods

COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling

Compatible Likelihoods for Flow Matching on Manifolds

CompJudge: Fine-Grained Comparative Evaluation using Multimodal LLM for Subject-Driven Generation

Concept frustration: Aligning human concepts and machine representations

Concise Reasoning Through the Lens of Lagrangian Optimization

CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA

Conditional Evaluation of Language Models with Cheap Auxiliary Signals

Consistency-Preserving Concept Erasure via Unsafe–Safe Pairing and Directional Fisher-weighted Adaptation

Contextual Flow Matching for High-quality Visual Content Generation

Context Value Informed In-Context Reinforcement Learning

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

ContinuLoc: Continuous Pose Inference over Neural Fields for UAV Geo-Localization

Continuous Audio Thinking for Large Audio Language Models

Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration

Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability

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 Dynamic 3D Shape Generation via 3D Trajectories and Text

Controllable User Simulation

ControlSVG: Exploring Controllable SVG Generation with Autoregressive Models

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit

Cool Graphs: Active Property Search Towards Quantum Nano-Refrigerators

Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL

CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents

CoT-Guard: Small Models for Strong Monitoring

Counterfactual Estimation under Composite Treatments via Progressive Distribution Alignment

CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations

Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games

Crafter: Towards Automated Reproducible Machine Learning via Agentic Code Generation

CREF: Forecasting Benchmarks for the Age of Agents

Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets

Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning

Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration

CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness

CuBic: Curvature-Driven Dynamic Inference Caching for Fast, High-Fidelity Flow Matching

CURE: Counterfactual Unsafe-token Re-masking for Diffusion Large Language Model Test-time Alignment

Curriculum Learning for Safety Alignment

CUVET: A Partitioning Approach for Continuous Treatment Assignment At Scale

CWAGraph: Retrieving What Was Never Explicitly Identified in Graph-Based RAG

CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation

DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks

DARE: Dual-Level Adversarial Learning with Domain-Aware Regularization for Whole Slide Image Classification

DART: Zero-Shot Dual-Side Alignment Routing for LLM Performance-Cost Tradeoffs

DASS: A Solver-Agnostic Dynamic Auxiliary Search Strategy for Symbolic Regression

DataComp-VLM: Improved open datasets for Vision-Language Models

Data-Efficient Learning for Constraint Satisfaction Problems via Relational Biases and Hard Axiom Clamping

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

Dataset Distillation via Drifting

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models

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 Representations Mitigate the Alignment–Specificity Trade-off in Multi-Omics

Decoupled Complementary Fields on 3D Gaussian Maps for Embodied Navigation and Reasoning

Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting

Deep Double Q-learning

Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes

Deep Minds and Shallow Probes

DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction

DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning

Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Delightful Distributed Policy Gradient

DELTA-TTS: Adapting Autoregressive Model into a Diffusion Language Model for Text-to-Speech

DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

Depth through Recurrence: Towards Ultra-Efficient On-Device ASR

D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces

DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics

Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty Aware Differentiable Optimization

Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation

Differentially Private Model Merging

Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems

Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

Diffusion Models without Classifier-free Guidance

Diffusion Thinking for Fast Long-Form Spatial Reasoning in Vision--Language Models

DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation

DiM$^3$: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging

DiPhon: Diffusion on Graphons for Scalable Graph Generation

DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis

Discovering dynamical parameters of synthetic multicellular systems from image sequences

Discrete Langevin-Inspired Posterior Sampling

Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors

Disentangled Representation Learning via Flow Matching

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

Diverse Representative Rashomon Sets for Sparse Generalized Additive Models

Diversity Combining for Multi-Path LLM Reasoning

DocAtlas: Long-Document Understanding as Mutable-State Interaction

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

DPLC: Dirichlet Process Guided Long-tail Clustering

Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields

DRILL: Training World Models to Improve Policies, Not Predict Pixels

DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving

DrPO: Drifting Preference Optimization for One-Step Generative Models

dStructAD: Domain-Level Structured Normality Representation with Variation Calibration for Time Series Anomaly Detection

DUST: Directional Uncertainty-aware and Scale-invariant Transfer Learning

Dynamic Representation Modeling for Federated Medical Image Domain Generalization

Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion

E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion

EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting

EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs

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

EditFlowSR: Revisable Expression Generation for Symbolic Regression

EDMA: Entropy-Driven Multimodal Answering

Effect-Driven Skill Abstractions for Offline Reinforcement Learning

Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima

Efficient Adaptive Data Analysis over Dense Data Distributions

Efficient Agentic GPU Kernel Optimization with a Compact Domain-Specific Language and Speed-of-Light Guidance

Efficient and Simple Data Mixing All The Time

Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

Efficient Pre-Training with Token Superposition

Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion

Efficient Training of Deep Spiking Neural Networks with Input-Driven Derivative-Free Updates

Efficient Tree Draft for Long-Context Speculative Decoding

EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

ELF: Embedded Language Flows

Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot

Emergence of a Shared Canonical Object Frame from In-the-Wild Videos

Emergent Biological Capabilities in a Foundation Model for Molecular Interactions

EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing

Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity

Empirical regularities in subjective decision-making by LLMs

Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers

Energy Is All We Need: Beyond FLOPs in Model-Heterogeneous Federated Learning

Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior

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

Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization

EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language Models

Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis

ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation

Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning

EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample

Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews

EventLens: Event-Structure Reinforcement Learning for Video Understanding

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

EvoGround: Self-Evolving Video Agents for Video Temporal Grounding

EvoInspect: A Unified Self-Evolving Multi-Agent Framework for Industrial Hardware Inspection

Evolutionary System Prompt Learning for Reinforcement Learning in LLMs

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs

Exploring Lifelong Adaptation: In-Context Reinforcement Learning in Non-Stationary Environments

Extending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation

Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons

Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models

FacEDiT: Talking Head Video Editing via Facial Motion Infilling

Fair Range k-Supplier Clustering in Offline and Streaming Models

Fast and Stable Gradient Approximation for Bilinear Forms of Hermitian Matrix Functions

FEAD: Fine-Grained Epipolar Attention Diffusion for Large-Disparity Light Field Spatial Super-Resolution

FedCAG: Federated Causality-Aware Graph Learning for Multi-Cloud Workload Forecasting

Federated Graph Learning with Local Message Compensation

Federated Logic Gate Networks via Boolean Feature Selection

Feedback World Model Enables Precise Guidance of Diffusion Policy

Ferrogen: Generative Pipeline for Guided Search of Novel Ferroelectric Material for Logic and Memory

FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection

Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models

Fine-Tuning Language Models to Know What They Know

Fisher information and the geometry of memorization in neural networks

Flexible Flows for Biological Sequence Design

Flexible Routing via Uncertainty Decomposition

FloatDoor: Platform triggered Backdoors in LLMs

FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance

Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment

Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents

Fractal-G: Topology-Aware Heterogeneous Graphs for Medical Image Segmentation

Fractional State Space Transition for Long Sequence Modeling

FrameScout: Scouting Query-Relevant Frames for Long Video Understanding

FreDRec: Frequency-Decoupled Knowledge Distillation for Multimodal Recommendation in Missing Modalities Scenarios

Free Decompression with Algebraic Spectral Curves

Frequency-Structured Hamiltonian Neural Network for Multi-Timescale Dynamics

Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation

From Contexts to Conditionals: Statistical Self-Consistency of Persona Prompting

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 Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation

From Generic to Dedicated: A Novel Optimizer for Online Continual Learning

From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes

From Retrieval to Recognition: Knowledge-Enhanced Foundation Models for Time Series Classification

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering with Generative Optimization

Fully First-Order Algorithms for Online Non-Convex Bilevel Optimization

FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models

FusionNeXt: Sequence-First 3D Multi-Modal Fusion in the Era of LLMs

GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning

GAPS: Gradient-Aware Adaptation-Gap Scoring for Time-Series Anomaly Detection with Foundation Models

Gauge-Symmetric Dual Lagrangian Frameworks for Born-Oppenheimer Molecular Dynamics

Gaussian Density Splatting Network

Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors

Generalization at the Edge of Stability

Generalization Bounds for Neural Networks with Sparse Connectivity

Generalized Laplacian in Spectral Seriation on Manifold Data

Generalized Priority-Aware Shapley Value

Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife

Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data

GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video Generation

Geometric Instability of Hidden-State Trajectories Predicts Reasoning Failures in Large Language Models

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 Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds

Geometry-Calibrated Conformal Abstention for Language Models

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

GeoPMR: Preserving Relational and Hierarchical Geometry in Multimodal Molecular Representation Learning

GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization

GIVLA: Deep Geometry Internalization for A Lightweight VLA via Geometry Instruction and Gradient-Informed Training

GLARE: Generating Listening Heads with Appropriate REactions

Goal-Conditioned Supervised Learning for Multi-Objective Recommendation

Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

Gradient Boosted Trees for Retrieval-Augmented Generation

Gram-Calibrated Anchoring for Class-Incremental Learning

GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis

Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation

GraphMemRL: Action-Native Reinforcement Learning for Persistent Graph Memory Construction

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation

Grounded or Fabricated? Unsupervised Detection of LLM Hallucinations via Contextualized Influence on Response Embeddings

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

Group Distributionally Robust Optimization with Flexible Sample Queries

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

GWScore: A structural diversity metric for consistent text-to-image generation

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories

HALO: Heterogeneous-Aware LoRA Optimization via Rank Allocation and Client-Aware Projection

HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training

HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices

Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-visual LLMs

HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching

Hessian-Dependent Sample Complexity in Zeroth-Order Stochastic Optimization: Suboptimality of Convex-Support Sampling and Optimal Sample Complexity

Heterogeneous Graph Federated Learning with Structure-Aware Data-Free Distillation

Hierarchical Variational Policies for Reward-Guided Diffusion

Hierarchical World Models with Implicit Dynamics

HiLoc: A Hierarchical Representation Method for Spatial Localization in Multimodal Large Language Models

Hindsight Relabeling is All You Need for Reach-Avoid Learning

History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes

Hodge Laplacian Quasi-Harmonic Flows for Option Discovery

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

How Can SignSGD Outperform SGD? A Functional Scaling Law Perspective

How Diffusion Models Memorize

How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants

How Does Pruning Change Decisions in Large Language Models?

How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study

How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

How Post-Training Shapes Biological Reasoning Models

Hyperbolic Concept Bottleneck Models

Hyperbolic Language Models: From Zipf to Compute-Optimal Scaling

HyperGen: Learning Structure-Aware Spectral Flows for Hypergraph Generation

Hypergraph Generation with Latent Diffusion

Hypergraph Representation Learning with Hyperlink Random Effects

HyperNSDE: Personalized Neural SDEs for Joint Static—Longitudinal Clinical Data Generation

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

HypMoE-ReID: Hyperspherical Mixture-of-Experts for Large Scale Person Re-Identification

IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder

Idempotency Exposes Consistency Problems in Sparse Autoencoders

Identifying Structural Biases from Causal Mechanism Shifts

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 Matting without Matting-Specific Annotations via Eikonal Fields

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects

Improving Consistency in Retrieval Augmented Systems With Group Similarity Rewards

Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation

Improving Self-Supervised Vision Transformers with Cross Distillation

Improving the Diffusability of Motion Tokenizer

Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates

Inadvertent Context Leakage in Language Models

INEUS: Iterative Neural Solver for High-Dimensional PIDEs

Inexact Bregman Sparse Newton Method for Efficient Optimal Transport

Inference-Time Self-Aligned Drifting for Few-Step Flow Matching

Inferring learning rules in deep neural network architectures from animal learning data

Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis

Information Parity for Code: The Scope of Transfer in Multilingual Code Models

Information Propagation via Sign-Flip Dynamics

Information-Theoretic Generalization for Set-Input Optimization-Valued Objectives

Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms

InSpect: A Curated Natural History Collection Dataset for Insect Specimen Understanding

INSPO : Unlocking Intrinsic Self-Reflection for LLM Preference Optimization

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration

Integrated Imputation-Classification for Supervised Learning with Missing Data

Interleaved Head Attention

InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling

Intrinsically Interpretable Attention via Sparse Post-Training

Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators

Iterative Chow Filtering for Learning with Distribution Shift

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions

Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models

KL for a KL: On-Policy Distillation with Control Variate Baseline

KNOT: A Knowledge Entanglement Benchmark for Robust Unlearning Evaluation

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

Language Models Demand New Computer Science

Laplacian Heads Improve Transformers by Smoothing Token Representations

LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning

Latent-space Attacks for Refusal Evasion in Language Models

LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models

Learning Continuously Evolving Spatio-Temporal Explanations for Traffic Flow Forecasting

Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard

Learning Neuronal Wiring Rules from Morphological Token Sequences

Learning Options for Compositional Motor Control with Adapter Banks

Learning Pareto Stationary Fronts via Single-Pass Backpropagation

Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature

Learning Reach-Set Geometry for Tighter Probabilistic Neural Network Verification

Learning Reusable Motor Motifs for Continuous Animal Behavior Modeling

Learning to Commit: Next-Commit Prediction via Online Supervised Contrastive Reflection

Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

Learning with Enumeration: Neural-Guided SAT Framework for Cryptographic Key Recovery

Learning with Synthetic Data via SGD in High-Dimensional Linear Regression

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 Language, More Latents: Annotation-Efficient VLAs for Driving

Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images

LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding

LiFT: Likelihood-Free Tree-Structured Policy Optimization for Flow-Based VLAs

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration

LINE: LLM-based Iterative Neuron Explanations for Vision Models

Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure

LLM Active Alignment: A Nash Equilibrium Perspective

LLM Agents Already Know When to Call Tools - Even Without Reasoning

Local Manifold Identification with Latent Linear Models and OT Flows

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions

Long-Term Composition of Human-Object Interactions

Long Video Instructional Editing in the Wild

Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation

Looped Diffusion Language Models

LoopWeaver: Weaving Feedback Loops into Hierarchical Generation under Constraints

LoRAtorio: An intrinsic approach to LoRA Skill Composition

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution

Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment

LP-RAG: Learning to Retrieve with Link Predictors

Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks

M$^3$: Reframing Training Measures for Discretized Physical Simulations

MainFL: Intertemporal Data Valuation for Robust Auction-based Federated Learning

Making LoRA Identifiable: Orthogonal Alignment for Continual Learning

Malicious Node Injection: A Transferable Adversarial Attack on GNN Fairness

Map-Guided Caching: A Global Perspective for Efficient Diffusion Transformer

MapPolicy: Structure-Aware Imitation Learning for Robot Manipulation via Physically Constrained Scene Map

Masked Diffusion Vision-Language Models for Temporal Action Localization

MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Protocol Modeling and Analysis

Matching2Matching: Zero-Shot Light Field Image Denoising with Matching View Construction

MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning

MathCD: A Benchmark Dataset for Cognitive Diagnosis with Semantic Information

Matryoshka Transcoders and Hierarchy Misalignment: When SAE Absorption Protection Does Not Transfer

MaxSketch: Robust Distinct Counting in Streams via Random Projections

MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search

MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in 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

Measure-to-measure Regression with Transformers

MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale

MemDLM: Memory-Enhanced DLM Training

Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation

Mesh-Free Convolution: Learned Spectral Attenuation and Transport

MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement

MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off

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

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

MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning

MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding

MinPath: Learning Efficient LLM Reasoning via Minimal Dependency Paths

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation

Mitigating Memorization Where It Happens

MixNLQ: An Effective Post-Training Nonlinear Low-Bit Quantization Method for Large Language Models

MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing

MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs

Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement

MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting

Modelling Opinion Dynamics at Scale with Deep MARL

Module Specialization in Transformer Factual Recall under Correlated Fact Distributions

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

MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays

MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents

Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation

MoTo: Mixture of Tokenizers Towards Fair Multilingual Language Modeling

Multigroup Fairness and Omniprediction: Separations and Equivalences

Multi-Scale Representation Learning for Single-Cell Multi-Omics

MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation

Native Audio-Visual Alignment for Generation

NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation

Nearly Optimal Bounds for Orthogonal Trace-Sum Maximization

Near-Optimal Best-of-Both-Worlds Algorithms for Decoupled Exploration and Exploitation in Multi-armed Bandits

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models

Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception

Network of Theseus (Like the ship)

Neural Causal Models under Markov Equivalence

Neural Garbage Collection: Learning to Forget while Learning to Reason

Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing

Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment

NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

NeuroHorizon: Long-Horizon Forward Prediction of Neural Population Activity via Autoregressive Decoding with Hierarchical Memory

NeuroMem: A Neuroplastic Memory Framework for Lifelong Agents through Delayed Consolidation

Newton-PINet: A fast physics-informed neural network with Newton linearization for meta-learning nonlinear PDEs

Next-Latent Prediction Transformers Learn Compact World Models

Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting

Nonparametric Estimation of a Factorizable Density using Diffusion Models

No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting

NorSA: Accelerating LLM Decoding via Normalized Sparse Activation

Not Only Where, But When: Temporal Scheduling for RLVR

NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion

NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training

ODDR: One-Step Deshadow Diffusion via Reward Guidance

OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes

Omni-Interactive Universal Embedder

One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration

One-Time Soft Alignment Enables Resilient Learning without Weight Transport

On Fitting Flow Models with Large Sinkhorn Couplings

Online Learning via Learned Latent Bayesian Tracking

On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation

On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation

On the Limits of Latent Reuse in Diffusion Models

On the Memorization of Consistency Distillation for Diffusion Models

On the Selectivity of Generative Models in Structure-Based Drug Design

OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning

Open-Vocabulary 3D Part Segmentation with Semantic Propagation Hawkes Process

Operads for compositional reasoning in LLMs

Opt-Arena: Evaluating, Selecting, and Generating Optimization Modeling Data via Tripartite Graphs

OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation

Optimal Subgroup Discovery at Every Support Threshold

Order-Marginalized Scoring for Masked Diffusion Models

Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection

OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies

Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models

PACE: Progress Actively-internalized Conditioning Execution for Long-horizon Manipulation

PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes

PanoHK360: A Large-Scale 8K Urban Panoramic Dataset and Benchmark for Depth Estimation

PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World

Parallel Fixed-Point Spiking Neurons for Efficient Training of Spiking Neural Networks

Parallel-in-Time Variational Inference for Latent Stochastic Differential Equations

PARE: Pruning and Adaptive Routing for Efficient Video Generation

PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide VQA

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

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?

Perception, Not Reasoning, Limits Visual Theory of Mind

Periodic Complex Stochastic Processes for Retrieving Atomic Structures of Unknown Matters

PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation

Personalized LLM Alignment Should Be Counterfactually Verifiable

Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding

PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging

Phase-DGS: Phase-Guided Dynamic Gaussian Splatting from Unsynchronized Multi-view Video

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFE

PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

PISCO: Precise Video Instance Insertion with Sparse Control

PitchBench: Measuring Pitch Hearing in Audio-Language Models

PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?

Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation

Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry

PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization

Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators

PolySplat: Workload-Regime-Aware Rasterization for 3D Gaussian Splatting

PoSafeNet: Structured Safety Learning via Compositional Projection

PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition

PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar Geometry

Position: Semantic Uncertainty Measures Disagreement, Not Reliability

Post-ADC Inference: Valid Inference After Active Data Collection

Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization

Posterior-Tracking for Best-Arm Identification in Bernoulli Bandits

Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics

Post-Selection-Safe Pessimistic Utilities for Offline Multi-Objective Reinforcement Learning

Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers

Predicting Quantization Price for Selecting PTQ Configurations Before Deployment

Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series

Pref-DetectGPT: Unveiling Machine-Generated Text via Preference-Aware Curvature Measurement

Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success

PreFT: Prefill-only finetuning for inference efficiency

Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation

PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior

Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries

Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design

Process-Aware LNS for Large-Scale MILP via Context-Enhanced Fine-Tuned LLM-driven Selector

PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling

Prompt-Conditioned Semantic Bottleneck for Cross-Domain Face Attack Detection

Proper Scoring Rules for Agentic Uncertainty Quantification

Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation

Prysma: Efficient Modality Adaptation for SLO-aware LLM-based Video Question Answering

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

QEC Model Zoo: Democratizing AI-enhanced Quantum Error Correction

Quantum Best Arm Identification with Limited Round of Adaptivity: Lower Bounds and Algorithms

Quantum Composite Hypothesis Testing with Small Error

Query Lower Bounds for Approximating the Top Eigenvector of Asymmetric Matrices

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning

RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies

Random-Projection Tree Stein Variational Gradient Descent

Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment

Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation

Raven: High-Recall Sequence Modeling via Sparse Memory Routing

Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners

RECIPE: Learning to Rank Complete Precursor Sets for Inorganic Retrosynthesis

ReCoG: Relational Concept Graph for Training-Free Personalization

Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning

Recursive Semantic Divergence for LLM Agent Consistency

Reinforcement Learning for Code Optimization

Reinforcement Learning for View-Adaptive Distillation in 3D Gaussian Compression

Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching

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

RelFlexformer: Efficient Attention Transformers for Integrable Relative Positional Encodings

Reliable Clustering and Quantization via Distortion-Constrained Optimal Transport

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

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation

Representation Preconditioning for Efficient Diffusion Model Training

Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility

Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity

RescueBench: Can Embodied Agents Save Lives in the Wild?

Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing

Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization

Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling

Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

Rethinking Vector Field Learning for Generative Segmentation

Rethinking Visual Reasoning in Text-to-Image Reward Modeling

Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings

Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery

Reversing the Roles of Signal and Noise: Modeling Noise in Astronomical Images without Paired Data

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

Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective

Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

Reward Is Not a Universal Interface for Generative Reinforcement Learning

RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models

Risk-guided Estimation-aware Acceptance for Learning with Synthetic Data

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

RL Excursions during Pre-training: How early is too early for on-policy learning?

RobustGenBench: A Benchmark for Robust Generalization to Adversarial and Common Perturbations, with Applications to Vision and Vision-Enabled Large Language Models

Robustness of Internal Signals for Hallucination Detection in Vision-Language Models

Robust Noisy Inductive Matrix Completion with Local Linear Convergence

RobustStress: Stress-Testing AI-Generated Text Detectors under Gradual Perturbations

ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression

RRL-HOI: Reflective Reinforcement Learning for Open-Vocabulary HOI Detection

RSSA: Robust Semantic and Spatial Aligner for Collaborative Perception

Rubato: Signature Attention for Irregular Multivariate Time Series Forecasting

RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models

SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Safe Linear Bandits with Unknown Safety Gaps

SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models

SAGE: Semantic-Agnostic Image Embedding for Generalized AI-Generated Image Detection

SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

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

Sample Efficient Generative Molecular Optimization with Joint Self-Improvement

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-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

SAVE: Sparsity-Aware Influence Estimation for Vocabulary-Expanded LLMs

SAX: Advancing Video Diffusion Models for Sequential Action Execution

SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information

Scalable Supervised Optimal Transport of Gaussian Mixture Models

Scale-Invariant Empirical-Bayes Laplace Approximation for ReLU Networks

Scaling Causal Reasoning with Increasingly Complex Causal Simulators

Scaling Laws for SAE Training Data

Scenes as Objects, Not Primitives : Instance-Structured 3D Tokenization from Unposed Views

SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding

SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

Screening Lipid Nanoparticles through Structure-Ratio Alignment

scShapeBench: Discovering geometry from high dimensional scRNAseq data

scTrilemma: Balancing Identity, Invariance, and Reconstruction in Single-Cell Representation Learning

SDAE: Semantic-Diversity-Aware Exploration for Efficient Reinforcement Learning in Large Language Models

SDFlow: Similarity-Driven Flow Matching for Time Series Generation

SEAR: Sample Efficient Action Chunking Reinforcement Learning

See, Read, Compare: Candidate-Aware Verification for Agent Test-Time Scaling

See to Believe: Segmentation by Reasoning with Visual Evidence

Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation

Select Smarter, Not More? Prompt-Aware Evaluation Scheduling with Submodular Guarantees

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration

Semantic-Level Invariant Representation Learning for Cross-Hospital Clinical EEG Modeling

SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation

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

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

Seq-LoRA: Sequential Bayesian Low-Rank Adaptation for Large Language Models

Sequential Behavioral Watermarking for LLM Agents

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction

SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs

Sharper Guarantees for Misspecified Kernelized Bandit Optimization

Shift-Aware Identity-Guided Latent Refinement for Referring Audio–Visual Segmentation

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Simple Baselines are Competitive with Code Evolution

Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image

Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-Spoofing

Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models

SkillGen: Verified Inference-Time Agent Skill Synthesis

Skill-Level Effects in Behavioral Cloning: When Low-Skill Data Improves Performance

Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization

SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing

Sliced Wasserstein Meets Quantum Optics: Provable Wavefunctions Tomography with Scarce Noisy Measurements

Small Model Portfolios for Many Deployment Profiles: Submodular Coverage under Bundled Constraints

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

Social Choice Foundations for Simulation-Augmented Generation

Social Interaction Breaks Replicate Independence in Controlled-Clone LLM Agents

SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models

Soft Contamination Means Benchmarks Test Shallow Generalization

SOLAR: AI-Powered Speed-of-Light Performance Analysis

Solver-as-Teacher: Solver-Guided On-Policy Post-Training Framework for PDE Foundation Models

Sound Verification of Deployed Neural Networks

SPA-Q: Structure-Preserving Adaptive Post-Training Quantization for Monocular Depth Estimation

Sparse Layers are Critical to Scaling Looped Language Models

Sparse Repair in Reasoning Traces: A Structural View of Test-Time Inference

Spatially-Grounded Long Video Generation with Self Geometry Forcing

Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models

Spectral-Aligned Pruning for Universal Error-Correcting Code Transformers

Spectral Estimation with Deformed Decompression

Spectral Identifiability for World Models: Polynomial Projectors, Resolvent Stability, and a Krylov Bottleneck

Spectrally Decomposed Equivariant Graph Neural Networks for Interatomic Potentials

Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models

Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting

SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction

SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere

SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays

Sport Is The Next Grand Challenge For Artificial Intelligence: Toward A Science Of Human Physical Skill

SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers

S&P: Towards Scalable and Powerful Graph Learning with Hierarchical Structural Acquisition

Stability-Enhanced Federated Learning with Accelerated Gradient

Stabilizing Off-policy LLM Optimization with Prefix Importance Ratio

Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators

Stable Resolution-Invariant Emulation in Entropically Controlled Kinetic Methods

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision

State Augmented Flows

State Evolution Awareness for Category-agnostic 3D Point Cloud Tracking

Statistical Complexity of Soft Bellman Residual Minimization

Statistical Limits of Affine Equivariant Estimation

StatLUT: Statistical Feature-Driven Multimodal 3D LUT Generation for Photorealistic Style Transfer

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion

Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing

Stochastic Optimization with Random Search

Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States

Strategic Evaluation: Incentivizing AI Capability Coverage with Private Benchmarks

Strategist: Designing Agentic Reasoning at Scale

Strengthening LLMs for Tabular Prediction with Structural Priors

Strengthen Out-of-Distribution Detection via Adaptive Mahalanobis Gap

Stroke-Audited Quadratic Bezier Splatting with Structural Initialization for Efficient Painting Rendering

Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding

Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging

Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning

Support Before Frequency in Discrete Diffusion

SurGe: Improved Surface Geometry in Point Maps

SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference

Susceptibilities for Neural Networks Learning from Physical Data

SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning

SWE-Git-Bench: A Worktree-Level Benchmark for Real Merge Conflict Resolution

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

Symmetry-Guaranteed Prediction of High-Order Tensor Properties for Crystalline Materials via Irreducible Decomposition

Symplectic Reck: In-Situ Learning of Gaussian Quantum Operations

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

Synsema: Syntax-Guided Learning of Semantically Valid Programs

Synthetic Anchor-Assisted Prototype Alignment for Heterogeneous Federated Learning

Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data

Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale

Take It or Leave It: Intent-Controlled Partial Optimal Transport

TALK: One-Shot Batch Design for Protein Variant Effect Prediction

Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning

Tatemae: Detecting Alignment Faking via Tool Selection in LLMs

Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution

TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization

Tempered Guided Diffusion

TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model

Temporal Pair Consistency for Flow Matching

Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design

Tensorion: A Tensor-Aware Generalization of the Muon Optimizer

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Test-Time Graph Recalibration: Enhancing Robust Zero-Shot Inference for Graph Foundation Models

Test-Time Prompt-Agnostic Decomposition

Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

Tethered Predictive-Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems

Text-Based AI Tools for Research Integrity Must Be Audited on Linguistic Fairness Before Deployment

TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation

The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety

The Graph Concept Bottleneck: Decoding Combinatorial Reasoning in GNNs for Interpretability

The Heavy Hitter Oracle: Enhancing Frequency Estimation in Skewed Data Streams

The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models

The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric

The Minimax Rate of Second-Order Calibration

The Missing Corpus: Infinite Ground Truth for File-Grounded LLM Evaluation

The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption

TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals

TIMA: Test-Time Internalization for Agentic Memory

Time-Frequency Decoupled Cross-Scale Partial Optimal Transport for Time Series Domain Adaptation

Time–Frequency Non-Stationary Modeling for Multivariate Time Series Forecasting

Token-Conditional Expert Dropout: Implicit Regularization for Stable MoE Pretraining

Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference

Tool-IQA: Augmenting Image Quality Assessment with Simple Tools

Topic-Aware Contextual Cascading Bandits

Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning

Toward Efficient Reasoning of Large Language Models via Latent Concept-Pyramid Modeling

Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

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 Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics

Toward the Goldilocks Blind Compression of Quantum States

TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs

TraceTriage: A Benchmark for Cost-Aware Stop-or-Continue Decisions in Delayed-Outcome Workflows

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Training-Free Open World Object Detection

Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers

Training on Documents About Monitoring Leads to CoT Obfuscation

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video Generation

Transductive Generalization for GNNs via Optimal Transport

Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing

Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback

TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Traversal-Invariant Positional Encoding for Serialized Graphs

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

TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models

Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA

TriPrompt: Progressive Local Prompting for Few-shot Out-of-Distribution Detection

Tropical Boundary Complexity of Deep ReLU Networks

Truth as a Compression Artifact in Language Model Training

TSB-SEG: A Systematic Time-Series Segmentation Benchmark

TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models

Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework

Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting

Uncertainty Quantification for Large Language Diffusion Models

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

Underlying Functional Structure of Reinforcement Learning

Understanding and Mitigating Structural Forgetting in Fine-Tuned Time Series Foundation Models

Understanding Generalization Requires Universal Induction

Uni-Cheb: A Basis-Agnostic Learnable Chebyshev Filter for Multimodal Spectral Modulation

UniDBO: A Unified Dual-Branch One-Step Denoising Framework for Autonomous Driving Scenario Generation

UniFlowDock: Flexible Docking with Complete Equivariant Velocity Fields

Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA

UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising

UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

Unsupervised Domain Adaptation for Semantic Segmentation Based on Instance Spatial Geometry

Untrusted Content Masking for Web Agents with Security Guarantees

Unveiling Fine-Grained Visual Traces: Evaluating MultiModal Interleaved Reasoning Chains in Multimodal STEM Tasks

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V Inference

Value-Rectified Distillation for Flow-based Offline Reinforcement Learning

ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding

Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation

Variance Reduction for Expectations with Diffusion Teachers

Variational Consequence-Driven Offline Reinforcement Learning

VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals

VecUQ-OT: Aggregating Uncertainty Measures via Multivariate Ranks

VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design

Verifier-Backed Hard Problem Generation for Mathematical Reasoning

Verigrad: Verification-Driven Multi-Agent GPU Kernel Generation for High-Order MLIP Derivatives

VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

vExpert: Virtualizing Expert Storage for Adaptive Load Balancing in Distributed MoE Inference

Video-Zero: Self-Evolution Video Understanding

ViewRec3D: Learning to Recommend 3D Viewpoints for AI Photography

View-Spectral Reconciliation Learning for Text-based Multispectral Aerial–Ground Person Re-Identification

VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling

VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning

Visual Text Compression as Measure Transport

Visual-to-Executable Procedural Reconstruction of Buildings.

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Watermarking Should Be Treated as a Monitoring Primitive

WaveSem: Frequency-Adaptive Tokenization for Disentangling Semantics and Noise in Genomics

We Should Distinguish Unlearning From Untraining

What Do SAE Features Encode? Evidence from Human Neural Activity

What Is Worth Representing? Representational Empowerment for Continual Model Construction

What, Where, and Boundary: Hierarchical Cognitive Decomposition for Echocardiography Video Segmentation

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 LeJEPA learn a World Model?

When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation

When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents

When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring

When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion

When Less is More: The LLM Scaling Paradox in Context Compression

When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy

When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks

When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification

When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation

Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers

Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic Grokking

Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups

Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs

Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS Research

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking

Why Latent Actions Fail, and How to Prevent It

Why Transformers Struggle with Distribution-Independent In-Context Learning

WorldSpeech: A Multilingual Speech Corpus from Around the World

XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

Z-Cache: Accelerating Diffusion Transformers via Self-Reflection

(ends 1:00 PM)

2 p.m.

Sydney Invited Talk:

The Future of AI Evaluation

José Hernández-Orallo

(ends 3:00 PM)

3:30 p.m.

Sydney Oral Session 3F [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 3A [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 3B [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 3C [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 3D [3:30-4:30]

(ends 4:30 PM)

Sydney Oral Session 3E [3:30-4:30]

(ends 4:30 PM)

5 p.m.

Sydney Poster Session 6 [5:00-8:00]

Posters 5:00-8:00

$\mathbf{\mathtt{MAD\text{-}Bench}}$: How Do Multimodal Agents Deceive You?

$R^2E$: A Role-driven Reward Evolutionary Framework for Automated Reward Function Design

$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation

3DABSeg: Adaptive 3D Ankle Bone Segmentation with Multiscale Feature Fusion Mixture-of-Experts

A2Eval: Agentic and Automated Evaluation for Embodied Brain

A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution

A Black-Box Reduction from Regret to Multi-Level Coverage

Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement

Accelerating the Inference Era with AI-Driven, Globally Optimized HW/SW Co-Design

ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting

A Characterization of Latent Variable Causal Models Consistent with Observational Data

AdaCal: Adaptive Calibration for Robust Sparse Attention in Long-Context LLMs

Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

Adaptive and Neutral Theory of Evolution Strategies for Large Language Models

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 LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries

Adaptive-Margin Masking and Restoration for Balanced Multimodal Learning

Adaptive Stepsizes for Eligibility Traces in Deep Reinforcement Learning

A Differentiable Interior-Point Method in Single Precision

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory

Adversarial Corpus Selection to Attack Subgraph Matching based Graph Retrieval

Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball

AEON: Unifying Video and 3D World Models

AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting

Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification

Affine-invariant Cubic Newton with Weak Learners

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents

Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction

AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?

Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection

A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning

Agnostic Online Learning with Reliable Abstention

A Hierarchical Tokenization Framework for Voxel-Level fMRI Representation Learning

ALETHEIA: A Multi-Frequency Eddy Current Pulsed Thermography Dataset for Neural Operator Learning in Nondestructive Testing

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds

AlphaPROBE: Alpha Mining via principled retriveval and on-graph biased evolution

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration

Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring

An Axiomatic Analysis of DPO and NLHF as Reference-Dependent Probabilistic Voting Rules

An Efficient Algorithm for Thresholding Monte Carlo Tree Search

An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models

A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

APPSolver: Adaptive Patch Partitioning for Point-Wise Ship Flow Prediction on Unstructured Meshes

A Primal-dual Approach for Semi-Infinitely Constrained Reinforcement Learning

A Private Empirical Defense Against Privacy Audits

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

ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation

A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines

AsdaKV: Attention-Overlap Driven Semantic KV Retrieval for Long-Context LLMs

A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets

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 systematic evaluation of vision-language models for observational astronomical reasoning tasks

A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes

ATI-VLA: Action-Centric Predictive Vision–Language–Action Models via Actionable Alignment Then Adaptive Injection

AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution

Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones

Attention-based Routing for Interpretable Multimodal Brain Encoding

Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention

Attention Transfer Is Not Universally Effective for Vision Transformers

Auditing Instruction Robustness in Vision-Language-Action Models via Diversity-Aware Red Teaming

Augmented Equivariant Mesh Networks for Anatomical Segmentation

A Unifying View of Anchoring via Operator-Side Tikhonov Regularization

AutoDataBench: How Far Are LLM Agents from Autonomously Engineering Post-Training Data Pipelines?

AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding

Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation

Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation

Bayesian Backprop as Belief Propagation: Single-Pass Predictive Uncertainty

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

Behavioral Foundation Models for Quality Diversity

Behavior Pack Optimization for Video MLLM Post-Training

Benchmarking Vietnamese Legal Knowledge of Large Language Models

Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub

BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics

Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback

Beyond Accuracy: A Diagnostic Benchmark for Hypothesis-Driven Experiment Planning in LLM Agents

Beyond DSA: Conjugacy-based Comparison of Dynamical Systems

Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation

Beyond MNIST: Limitations of Amplitude Encoding on Quantum Classification

Beyond Pixel Space: Frequency-Domain Uncertainty Estimation for Structure-Aware Diffusion Guidance

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Beyond Selection: Token Parameterization for Extreme Visual Token Compression

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding

Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models

BFS-PO: Best-First Search for Large Reasoning Models

Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning

BiLi: Bridging the Last Mile in LiDAR Localization

Bilinear Matching Bandits

Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles

BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs

Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge

BMAttn: Block-Aligned Mixed-Precision Attention Quantization for LLM Inference

BodyBench: Evaluating Adversarial Image Defenses Against AI Nudification Inpainting

Boosting Off-Policy RLVR with Data-Centric Replay

BootstrapAgent: Turning Repository Setup into Reusable Agent Knowledge

Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG

Breaking the Exactness Barrier: Interleaved DeepSeek Sparse Attention for Efficient Long Context Reasoning

Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning

BRIDGE: Brain-Vision Representation Integration through Depth and Granularity Encoding

Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering

Bridging Sequence and Structure with Unified Domain Adaptation for Drug-Target Interaction Prediction

Bridging the Gap Between Harmfulness Belief and Refusal Behavior for Safety Alignment

BucpTSF: Breaking the Uniform Computation Paradigm in Time-Series Forecasting

Budget-Conditioned Clipping Policies for Differentially Private Federated Learning

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

Calibration without Ground Truth

Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset

Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?

Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations

Canopy: Tree-Aware Rollout Scheduling for Agent Reinforcement Learning

Can We Trust Item Response Theory for AI Evaluation?

Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing

CAPO: A Primal-Dual Framework for Constraint-Aware Prompt Optimization

CASQRec: Collaborative-Adaptive Semantic Quantization for Multimodal Recommendation

Causal Discovery under Time-Varying Delays

CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving

Causal Inference for Sequential Settings under Interference and Latent Confounding

Causal learning with the invariance principle

CellMSA: Context Modeling for Single-Cell Representation Learning

Chain-of-Thought Oversight Should Not Treat Faithfulness as Monitorability

Character Mixing for Video Generation

CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism

ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip Routing

ChronosAlign: A Large-Scale, Updatable Benchmark for Decomposing Temporal Alignment in LLMs

Circuit-Level Knowledge Distillation for Large Language Models

CITE: Anytime Valid Statistical Inference in LLM Self-Consistency

Class-Domain Incremental Learning with Extensible Multi-Center Modeling

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation

Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

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

Closing the Approximation Gap in Simulation-free Latent SDEs

Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes

Code2World: A GUI World Model via Renderable Code Generation

Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features

CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion

Code Review Bench: An Automated Benchmark for Evaluating the Software Factory

CoE-Agent: Co-Evolving Patient-Doctor Agents via Interactive Policy Graph Optimization for Clinical Decision Making

CoffeeBench: A Benchmark for Long-Horizon Strategic Decision-Making in Multi-Agent Economies

Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation

Colour me shocked: Exact Molecular Hessians from MLIPs in O(N) time using sparse differentiation!

CompilerKV: Risk-Adaptive KV Cache Compression via Offline Experience Compilation

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

Compute Allocation Under Model-Provider Competition

Compute-optimal data scaling for neural surrogates via multi-fidelity training

Concentrated Gradients Amplify Forgetting: Dominant-direction Projection for Continual Multimodal Learning

Concept-Aware Wasserstein Routing with Vision-Language Guidance for Few-Shot WSI Classification

Concord-SLAM: Cross-Render Concordance for Boundary-Native Semantic Gaussian SLAM

Conditional independence and graphical models for rankings

Conformal Prediction for Distribution-to-Distribution Regression

Confounding-Aware Client Selection in Federated Learning via Causal Mediation Analysis

Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods

Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models

Continuous-depth Deep Gaussian Processes

Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

Continuous Personalized Diffusion Model via Spinor-Component Forward Geometry

Contrastive Identification and Generation in the Limit

Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models

Control Charts for Multi-Agent Systems

Controllable Generative Sandbox for Causal Inference

Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization

Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration

CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation

Correction Space Steering for Hallucination Mitigation in Large Vision-Language Models

CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings

Cortically-Resolved Recurrent Architecture for fMRI

CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language Models

Counterfactual Online Conformal Prediction Under Adaptive Logging

CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

Coupled Guidance for Flow Matching

CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment

CPSea2: Composing Terminal Geometries for Structurally Diverse Cyclic Peptide Binder Design

Credit Assignment with Resets in Language Model Reasoning

CrossWeave: Emergent Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment

CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building

CSCN: The Crossed Subtree Convolutional Network

CSLA: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training

CTE-Bench: Audited Counterfactual Trace Evaluation for Stateful Software Simulators

CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users

CycleSpectra: Cyclic Motion Spectra for Phase-Queryable 4D Cardiac Reconstruction

D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs

DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models

DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images

D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform

Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions

Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration

Decoupling is the Key: Scaling Deep Value Networks in Reinforcement Leanring

Deep Gaussian Processes on Directed Acyclic Graphs

Deep Research as Rubric

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

Delay-Embedded Representations for Robust Saccade Classification in Noisy Oculographic Signals

DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models

Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves

Deriving Hyperparameter Scaling Laws via Modern Optimization Theory

Designing Cell-Type-Specific Regulatory DNA with Guided Discrete Diffusion

DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation

Detecting Hidden ML Training With Zero-Overhead Telemetry

DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English

DiffCool: Label-Free Synthesis of Chip-Tailored Heat Sinks via Thermal-Aware Diffusion

Diff-Kalman: Difference-Driven Learning for Structure-Preserving Kalman Filtering

DiffScore: Text Evaluation Beyond Autoregressive Likelihood

Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning

Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction

DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding

DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO

DiscoverPhysics: Benchmarking LLMs for out-of-the-box scientific thinking

Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics

Distributional Estimation of 3D Object Orientation

Distributionally Robust Domain Randomization with Learned Risk-Sensitive Dynamics Samplers

Distributionally Robust Listwise Preference Optimization

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

DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation

Does Compression Imply Generalization? A Minimum Description Length Perspective

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization

Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents

Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability — Diverse Evaluation Is Required

Don't Discard Your Rollouts: Reusing Teacher RL Traces for Student Distillation

Don't Waste Population: Post-Anneal Refinement for Combinatorial Optimization

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?

DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation

dRAE: Representation Autoencoder with Hyper-Spherical Codes

DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images

DriveStreamBench: Evaluating User-Conditioned Watch-and-Notify in Streaming Driving Video

Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures

DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning

DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation

Duality Models: An Embarrassingly Simple One-step Generation Paradigm

DualSteer: Dual-Space Steering for Robust Jailbreak Mitigation of Large Vision Language Models

DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech

D-VLA: A High-Concurrency Distributed Asynchronous RL Framework for Vision-Language-Action Models

DyJR: Preserving Local Policy Plasticity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay

Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding

Dynamic Query as Budgeting for Tiny Object Detection

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Dynamics-Informed Adaptive Offline RL for Real-Time Tokamak Plasma Control

DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models

Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model

DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions

Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation

ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation

Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommender Systems

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

Efficient Algorithms for Distributed Saddle Problems

Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging

Efficient evaluation and error pattern discovery for blackbox AI systems

Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning

Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training

Efficient SAM 3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive Representations

Efficient Scaling of LLM Training with Flexible Context Parallelism

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation

EmbodiedObject: All-in-One Object Understanding with SLAT

EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge

Enabling VLA Action Self-Verification via VLM Token Probability Bucketing

Energy-Tweedie: Score meets Score, Energy meets Energy

Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution

EnterpriseBench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance

EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation

Epigenomics-Guided Flow Matching for 3D Genome Super-Resolution

eSAM: Editing SAM3 Attention for Training-Free Referring Segmentation

ES-Merging: Biological MLLM Merging via Embedding Space Signals

Estimating Model-Level Membership Inference Vulnerability Without Reference Models

Evaluating Test-Time Scaling of General LLM Agents

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning

Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark

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

Exact Posterior Score Estimation for Solving Linear Inverse Problems

ExoC2T: An exogenous-driven spatio-temporal learning framework for cross-city transfer

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

Expert-guided Bayesian optimization for sustainable protein formulation

Explaining and Preventing Alignment Collapse in Iterative RLHF

ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection

Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL

Exposing Private Corpus Leakage in Multimodal RAG

Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors

Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models

FairMT: Fairness for Heterogeneous Multi-Task Learning

FairSplit: Decomposing the Embedding Space for Fair Classification

FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation

FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Fast and Accurate Probing of In-Training LLMs' Downstream Performances

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference

Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data

Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics

FAUST: Federated Asynchronous Update with Staggered Timescales for Low-Communication Foundation Model Training

Feature Information Dynamics in Diffusion

Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning

Feeling of Knowing in Large Language Models

fev-bench: A Realistic Benchmark for Time Series Forecasting

Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models

Fiedler-Regularized Causal Discovery for Sparse Connected DAGs

Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting

FinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining

Finding Koopman Invariant Subspaces via Personalized PageRank

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

First-Token Attraction in Mamba Dynamics

Fisher Decorator: Refining Flow Policy via A Local Transport Map

FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping

FLASH: Efficient Visuomotor Policy via Sparse Sampling

FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems

Flipping Bits, Not Gradients: Sharpness-Aware Minimization Directly on the Boolean Hypercube

Flow-Guided Target-Space Alignment via Path Consistency

FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network

Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints

FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing

FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification

ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation

Forecasting Downstream Performance of LLMs With Proxy Metrics

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning

Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space Models

FracEncoder: Towards Adaptive Cognitive Trajectories via Fractional-Order Context Encoding

FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry

Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large Models

Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation

FRESCO: A Novel Consistency Control for Asynchronous Pipeline Parallel Training

From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation

From Expert Knowledge to Optimization Modeling: Prototype-Based Data Synthesis and Logical Reinforcement Learning

From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers

From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMs

From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization

From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

From Table to Cell: Attention for Better Reasoning with TABALIGN

From Tokens to Tactics: Adversarial Text Optimization in an Axis-Aligned Rhetorical Strategy Space for Harmful Content Detection

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views

Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow Matching

FUTON: Fourier Tensor Network for Implicit Neural Representations

GCD: Correcting Hidden-State Bias in Off-Policy Agentic RL

GenAI Evaluation Results are Largely Artifacts of Evaluation Design Choices: Evidence from Audit Studies of Resume Screening

Generalization Without Compression Penalty: A Stability Analysis of Error Feedback

Generating in the Limit with Infinitely Many Hallucinations

Generation-Drift-Guided Block Pruning for Large Language Models

Generative Modeling by Value-Driven Transport

Generative Structure from Motion with Native 3D Diffusion

GeneZip: Region-Aware Compression for Long Context DNA Modeling

GenRM-Flow: Generators are Process-aware Reward Models in Flow Matching

GeoG2U-Bench: When Does Generation Help Understanding in Ultra-High-Resolution Remote Sensing?

Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension

Geometric Prompt-Trajectory Planning for Test-Time Scaling

Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning

Geometry-Aware Self-Supervised Electrophysiology Representation Learning

Geometry-Aware Subspace Perturbation for Heterogeneous Federated Learning

GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators

Glob3R: Global Structure-from-Motion with 3D Foundation Models

Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs

GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors

GMOS: Grounding Moving Object Segmentation in 3D Space and Time

GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding

GoT: A Game-Theoretic Approach to the Game of Twenty Questions

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

Gradient Descent’s Last Iterate is Often (slightly) Suboptimal

Gradient-Mine Units: Scorched-Earth Strategy for Model Protection against Unauthorized Fine-Tuning

Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate

Growing a Neural Network in Breadth, Depth, and Time

Guided Data Generation for Understanding Model Behavior

HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing

HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs

Heteroscedastic TrueSkill: Modeling Match Noise and Player Consistency

Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

High-Dimensional Conditional Independence Testing via Random Projection Aggregation

High Performance Differentially Private Fine-Tuning using Dataset Distillation

High-probability Convergence of Gradient Methods under Markovian Stochasticity

Hint Tuning: Less Data Makes Better Reasoners

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift

Holistic EvoLution via Intrinsic eXchange for Unified Multimodal Models

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

HOPE: Hand-Object Pressure Estimation from Monocular Videos

HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration

How does feature learning change the function space evolution?

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 Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences

How Much is Left? LLMs Linearly Encode Their Remaining Output Length

How to Interpret Agent Behavior

How Useful Is Cross-Domain Generalization for Training LLM Monitors?

Hydra-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control

HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression

IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow

IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition

IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer

Improved Sample Complexity for Markov Games via Variance-Aware Bandit Learning

Improving Neural Decoding Performance for Language BCIs by Explicitly Modeling Context-Induced Noise

In-Context Learning Can Help Vision Language Models Overcome Training Prior

In-context learning to predict critical transitions in dynamical systems

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

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise

Inferring how internal brain state shapes neural responses with state-dependent diffusion models

Information Loss and Disparate Effects in Network Embeddings

InformedXRD: Reproducible Benchmarks and Physics-Informed Evaluation for Powder Diffraction Symmetry Classification

Instance-Dependent Bandit Convex Optimization in One Dimension

InTAct: Interval-based Task Activation Consolidation for Continual Learning

IntegrityBench: Can LLMs Be Trusted as Co-Scientists? A Research Integrity Benchmark

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

Intent-Aware Caching for Efficient LLM Serving

Inter-domain Inference for Gaussian Process Variational Autoencoders

Internalize External Competence for Visual Instruction Editing

Intrinsic Information Theoretic Analysis of ReLU Nets

Intrinsic-Preserving Schrödinger Bridge for Direct Part-Aware 3D Generation

Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

Iterative Latent Refinement for Value Learning in Offline Goal-Conditioned RL

Iterative Nonlinear Computation Underlying Abstract Reasoning

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation

Joint protein, mRNA, DNA sequence design and optimization with nucleotide-level Potts models

Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation

KiteNorm: Variance Regularisation for Stable and Scalable Post-LN Transformers

Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use

Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers

LAPLEX: The FFT of Learnable Laplace Kernels

Large Language Models as Graph Computational Solvers via Topology-aware Residual Attention

Latent Action Reparameterization for Efficient Agent Inference

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning

Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models

LDM-is-AE: Latent Diffusion is an Intrinsic Auto-Encoder for End-to-End Image Generation

Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation

Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling

Learning CLI Agents with Structured Action Credit under Selective Observation

Learning Deployable Causal Action Geometry under Temporal Non-Stationarity

Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems

Learning Robust Reasoning through Guided Adversarial Self-Play

Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval

Learning to Continually Learn via Meta-learning Agentic Memory Designs

Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards

Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

Learning to Generate Multiple Objects from Dense and Occluded Layouts

Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret

Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing

LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

LINK: Learning to Localize from Known to Unknown Scenes

LITE: A Lightweight Lazy Sampler for Efficient SGD

LITHE: Lattice-Indexed Twin Hadamard Encoding for Diffusion Personalization

Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators

LLMs Show No Signs Of Individuated Metacognition

Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning

Local Sparsity Enables Unsupervised LLM Safety Detection

LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition

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

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis

Long-Horizon Agency Belongs in the Harness, Not the Context Window Only

Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities

Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models

Long-Term Risks of Risk-Based Allocation

Looped Transformers with Layer Normalization Provably Learn the Power Method

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery

LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization

LR-V2X: Loss Resilient Collaborative Perception under Low-Bandwidth Communication

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning

ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts

MARS: Enabling Autoregressive Models Multi-Token Generation

MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation

Matched-Control Tests of Partition-Source Claims in One Routed Distillation Family

Measuring Collapse and Correction in Homogeneous-Panel LLM Debate

Measuring Layer-wise Intrinsic Dimensionality of FFNs in LLMs via PCA

Mechanistic Circuit Identification for Controllable Data Generation

MechParser: A Vision-Language Framework for Parsing Chemical Reaction Mechanism Diagrams

Med-Agentic: Distilling Agentic Medical Reasoning with Internalized Meta-Capabilities

MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models

MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory

Memorization Is Folding: Topological Signatures of Noisy-Label Learning

Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models

MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

MemPilot: Learning Transferable Latent Memory Mechanisms for LLM Reasoning

MENDR: Manifold-Embedded Neural Data Representations for Channel-Agnostic EEG Foundation Modeling

Merging RLVR-Trained Experts via Policy-Shift-Guided Spectral Alignment

MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting

METAFORGET: Audit-Driven Update-Policy Learning for Reliable Language Model Unlearning

MetaLoop: Benchmarking the Full Metacognitive Loop in LLMs

Metaphor Is Not All Attention Needs

Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts

MHWA: Multi-timescale Hierarchical World-Action Model

MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation

Mind the Gap: The Divergent Rebound Dynamics of Diffusion and Autoregressive Model

Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models

MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding

MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation

MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound

Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow Matching

Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning

Mitigating Knowledge Conflicts in Retrieval-Augmented Generation via Inference-Time Representation Editing

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 Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing

Mixture-of-Top-$k$ Attention: Efficient Attention as Scalable Fast Weights

MMCompass: Diagnosing Position Bias in Generative Multimodal Reward Models

mmLIP: mmWave Radar-Language Interactive Pretraining via Point Confidence

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

MobileMoE: Scaling On-Device Mixture of Experts

MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes

Model-Aware Tokenizer Transfer

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds

Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields

Models Designed to Forget: Machine Unlearning via Key Deletion

MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment

MorphoGen: Free-Form XML Evolution for Robot Morphology Design

MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts

MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning

M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals

MSCR: Jointly Balancing Modality Utilization and Discovering Synergistic Information

MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts

Multi-bit LLM Watermarking with Certified Semantic Distortion

Multiform Attack for Transferable Cross-Modal Person Re-Identification

Multilateral Resistance-Guided Graph Message Passing for Trade Flow Prediction

Multiscale Supervised Unbalanced Optimal Transport Flow Matching

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards

MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents

MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction

MVVBench: Benchmarking 4D Reasoning in Vision-Language Models

Nahual: A Sequence Model for Language and Atoms

NARRA-Gym for Evaluating Interactive Narrative Agents

Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

Narrowing the Collaboration Gap, Probably

Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training

Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs

NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents

Neural Optimal Transport in Hilbert Spaces

NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization

NORA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning

NORMA: Norm-Guided Explanation Subgraph Discovery

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution

NyoomFloat12: Accelerating LLM Inference via Lossless 12-bit Weight Compression

OASIS: Online Adaptive Steering for In-Training Safety of LLMs

Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning

Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals

OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization

Offline Inverse Reinforcement Learning with Unified Diffusion Planning

OHATP: Graph Anomaly Detection with Orthogonal-Hyperspherical Augmentation and Topology Perception

OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models

OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling

OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs

On Concentration Inequalities for Sampling without Replacement

On Data Engineering for Scaling LLM Terminal Capabilities

One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning

Online Differentially Private Consistent Clustering

Online Evaluation of LLMs via Dyadic Designs

Online Fair Division Meets Reordering Buffers

Online Quantile Omniprediction for Proper Losses

On-Policy Counterfactual Influence

On the Feasibility of Identity Manipulation for Diffusion-Based Face Privacy Preservation

On the Information Loss of Multi-Token Prediction: Origin and Solution

On the Instability and Stabilization of Blockwise Muon

On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs

On the Nonlinearity of Learning Rate Scaling for LLM Training

On the Recoverability of Causal Relations from Bulk Gene Expression Data

On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime

OopsWorld! Operation-Grounded Seamless World Generation

Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks

OpenSanctions Pairs: A Large-Scale Dataset for Pairwise Entity Matching

Open Vocabulary Domain Unlearning

Optimizing Agent Tool-Use via Trajectory-based Insight Evolution

Origami as a Real-Image Benchmark for Procedural State-Transition Reasoning

OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models

Otter Weather: Skillful and computationally-efficient medium-range weather forecasting

Outlier-Robust Multi-Output Gaussian Processes

Out-of-Distribution Detection in Continual Learning

Overcoming Kernel Redundancy for Scaling Logic Gate Networks

OverLay++: Dense-Overlap Layout-to-Image Generation Dataset

PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design

PANDA: Prior-guided Attentional Dual-path Architecture

Panoptic Saliency Ranking

PaperLens: How Predictable Is Paper Acceptance?

Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General

Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics

ParaPC-FM: Accelerating Parallel Sampling via Principled Initialization

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation

Patch4Patch: Restoring Structural Connectivity in Patch-based Vision Encoders

Path Dependence under Adaptive AI Delegation

Pathway-Aligned Regulator Tokens for Interpretable Spatial Gene Expression Prediction from Histologyatial Transcriptomics Prediction from Histology

PDE-PFN: Prior-Data Fitted Neural PDE Solver

PepDDG: Peptide–Protein Binding ΔΔ𝐺 Prediction via Information Channel Decomposition

Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning

PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection

Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation

PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

PhyTS: A Benchmark for Scientific Time Series

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

PISG: Constraint-Aligned Signal Amplification for Diffusion-Based Combinatorial Optimization

Pixels over Symbols: Sensory Realism Improves Behavioral Alignment in Models of Cognition

PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

Planning Persuasion, Not Utterances: Profile-Conditioned Open-Loop Search for Dialogue Strategy

PlasticMem: Adding Temporal Reasoning to Diffusions for Consistent Long Video Generation

Plausible Biomolecular Structure Prediction via Physics-informed Reinforcement Learning

PoEM: Predicting New RL Outcomes from Existing Policies

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs

Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning

Position: AI Development Should Prioritize Cognitive Security

Practical Non-Stationary Graph Gaussian Processes

Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning

Prediction-Powered Inference Across Many Tasks for AI Evaluations and Social Science Research

Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement

Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers

Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment

Pretraining Curricula Enable Selective Fine-tuning

PRIME: Poincaré return induced measure for learning partially observed dynamical systems

PRIM: Meta-Learned Bayesian Root Cause Analysis

Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference

PRISM:Disentangling Preference Distributions for Generative Ranking

PRISM: Human Point Cloud Reconstruction via Skeleton-Guided Diffusion from MmWave Radar

PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning

ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification

Probabilistic Tiny Recursive Model

Probing Visual Planning in Image Editing Models

ProEdit: Inversion-based Editing From Prompts Done Right

ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images

Prompt Ensemble Image Puriﬁcation for Test-time Adversarial Robustness of CLIP

Prompting Diffusion Models for Zero-Shot Instance Segmentation

Propagation of Chaos in Contextual Flow Maps

Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation

Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction–Reality Gaps

Prototype-Aligned Multi-View Graph Learning for EHR Prediction

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

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

QB-Highlights: Quality-Guided Budgeted Highlight Detection in Videos with Dense Query-Relevant Moments

QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems

RadarMAE: Injecting Physical Inductive Biases into Masked Autoencoders for Advanced Radar Object Detection

RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis

Random features for Grassmannian kernel approximation with bounded rank-one projections

Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

Rank-Constrained Adaptation for Reliable Real-World Performance

RAPDrive: Shared-Latent Hybrid Decoding for Reasoning and Planning in Autonomous Driving

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs

ReasoningShield: Safety Moderation over Reasoning Traces of Large Reasoning Models

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

RecMem: Recurrent Memory Compression for Long-Sequence Recommendation

Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models

Reconsidering Positional Supervision in Masked Diffusion Language Model Training

Reconstructing the Vocal Tract with Differentiable Acoustic Simulation

Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data

RedVLA: Physical Red Teaming for Vision-Language-Action Models

Refactoring Code Through Library Design

Refining Compositional Diffusion for Reliable Long-Horizon Planning

ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry

Regret-Optimal Wasserstein-Robust Regression

ReGuidance: Diffusion Steering with Strong Latent Initializations Solves Hard Inverse Problems

Reinforced Fast Weights via Next-Sequence Prediction

REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning

Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering

RepoZero: Can LLMs Generate a Code Repository from Scratch?

ResKV: Residual-based Channel-wise Unstructured Pruning for KV Cache Compression

Resolvent Ellipsoid for Minty Set Inclusions

Resolving AdaBoost Cycling with LLMs: A Computer-Assisted Counterexample

Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?

Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation

Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review

Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures

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 Modeling for Multi-Agent Orchestration

Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation

Riemannian Admissibility Flow for Offline-to-Online Safe Reinforcement Learning

RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video

RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation

Risk-Controlled Post-Processing of Decision Policies

RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents

RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades

ROAD: Rule-Grounded Context-Aware Open-World Driver Anomaly Detection

Robust PAC Learning of Concurrent Stochastic Games

Roll2Depth: Zero-Shot Metric Depth Estimation Exploiting Camera's Rolling Shutter Effect

RSPReg: Reliability-aware Structural Prototype Learning for Point Cloud Registration

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs

Rubato: Transcribing Piano Music with Timestamps

Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup

RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering

Safeguarding Mutual Correction in Source-Free Domain Adaptation via Cut Statistics

SamaDICE: Safe Multi-Agent Reinforcement Learning with Stationary Distribution Correction Estimation

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

ScAn-Bench: Evaluating Scaling Analysis Methodology

SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning

Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning

Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models

Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery

Selective Off-Policy Reference Tuning with Plan Guidance

Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL

Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation

Self-Improving World Modelling with Latent Actions

Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment

Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity

Sequential Probability Assignment against Smoothed Adversaries with Unknown Base Measure

Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality

Shared-Noise Mechanisms for Verifiable Differentially Private Counting

Sharper Regret Bounds for Shampoo

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity

SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study

SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation

SimpleEvol: Efficient Intelligence Conversion via Less Human Prior in Automated Heuristic Design

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization

SimpliHuMoN: Simplifying Human Motion Prediction

Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty

SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards

SituRecBench: Evaluating Frontier Models as Situated Recommendation Assistants in 3D Environments

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

SkipSR: Faster Super-Resolution with Token Skipping

SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation

SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation

SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning

SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data

SNACK: A Sequential Notation Framework for Probabilistic Graph Generation

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer

Source-Causal Control of Historical Context in Longitudinal Radiology Report Generation

SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting

Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling

Spectral Insights from the Unconstrained Feature Model for Neural Multi-Output Regression

Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards

Speculative Self-Distillation enables Efficient Knowledge Internalization

Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views

Stable and Granular Policy Optimization for Generative Recommendation

StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation

Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning

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

SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization

Steer2Edit: From Activation Steering to Component-Level Editing

Stochastic Heat Diffusion Models

STRABLE: Benchmarking Tabular Machine Learning with Strings

Strategic Causal Policy Learning: Welfare, Safety, and Fairness Thresholds

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models

Structural Causal Bottleneck Models

Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning

Structured Coupling for Flow Matching

Structured Transforms for Low-Overhead Quantization of Language Models

Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment

Substrata: Know What You Don't Know

SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy

Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing

Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs

SurgReasoner: Surgical Reasoning Segmentation with Dynamic Difficulty-Aware Reinforcement Learning

Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs

Survival Transformers for Longitudinal Data Analysis: Application to Atrial Fibrillation Risk from ECG

SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D Classification

SWE-Crafter: Scaling Executable Multilingual Software Engineering Data with Meta-Skill Agents

SwitchLingua V2: Agent-Driven Code-Switching via Digital Clones

Symmetry Guarantees Statistic Recovery in Variational Inference

Symplectic Parallel Scan: A Neural Hamiltonian Framework for Accelerated Scientific Simulation

SynthHair: Leveraging MetaHumans for a High-Quality 4K Hair Matting Dataset

TailCon: Mitigating Tail Signal Erosion through Memory Consolidation for Long-Tailed Recognition

TailFix: Mitigating Error Accumulation and Correcting Tail Deterioration in Long-Horizon Forecasting

TALES: Text-Adventure Learning Environment Suite

Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence

Tapes Together Strong: The Co-evolution of Computation and Cooperation

Target-Aware Nuisance Shaping for Object Detection

Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language

TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents

Text-Vision Co-Instructed Image Editing

TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs

The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning

The Denoising Wrapper: A Modular Post-Processing Framework for Noisy First-Order Optimizers

The Era of Agentic Organization: Learning to Organize with Language Models

The Fault in Our Metrics: Revisiting Generative Model Evaluation with Chamfer Distance

The Fractured Interlingua: Geometric Bottlenecks in Cross-Lingual Knowledge Editing

The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy

The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at Scale

The Key to Going Linear: Analysis-Driven Transformer Linearization

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge

The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction

The Scaling Laws of Skills in LLM Agent Systems

TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval

Time-Sensitive Anytime-Valid Testing

Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation

Tool Verification for Test-Time Reinforcement Learning

TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving

TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design

Total Variation Distance Estimation in Autoregressive Models

Towards Characterizing Scientific Image Utility and Upgradability

Toward Semantically-Consistent Tuning-Free Customization for Rectified Flow Transformers

Towards Generalist Graph-Level Anomaly Detection

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling

Towards Generalizable Partially Relevant Video Retrieval

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Towards Principled Efficient Rollout Allocation in Test-Time Training

Towards Realistic Conversational Multimodal Instruction Following

Towards Scalable Egocentric HOI for Humanoids: Benchmarking Whole-Body Dexterous Interaction with Tactile Prediction

Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways

Towards Universal Black-box Attacks on Graph Neural Networks

TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization

TPRL: Adaptive Visual Token Pruning in LVLMs via Language-Guided Reinforcement Learning

TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking

Tracing Psychometric Inference in Large Language Models

TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos

TrAction: Action Recognition with Sparse Trajectories

Training-Free Task Vectors for LLM Behavioral Control

Training Language Models to Explain Their Own Computations

Training Quality Determines Efficiency Boundaries in Test-Time Reasoning

Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning

TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment

TReDS: Trajectory-Grounded Requirement-Capability Modeling for Training Distribution Shaping in Tool-Interactive Tasks

Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling Bandits

Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH

Tree Training: Efficient LLM Training on Tree-Structured Trajectories

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

Tropical Gaussian Anticoncentration: Settling Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games

Trust What Matters: Language-Conditioned Evidence Routing for Video-IMU Action Question Answering

TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving

Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning

Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task

Uncertainty Quantification of Least Squares Estimator for Generalized Orthogonal Procrustes Problems

Understanding and Mitigating Under-Confidence in GNNs from the Final Layer

Understanding Sample Efficiency in Predictive Coding

Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles

Understanding the Surprising Generalization Properties of Tabular Foundation Models

Unified Forensic Preference Learning for Generalizable Synthetic Image Detection

Unified Noise Steering for Efficient Human-Guided VLA Adaptation

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation

UniMoE-World: A Unified Mixture-of-Experts Architecture for Scalable Multi-Control Video Generation World Modeling

UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception

Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning

Universal and Efficient Computation with 2D Attention

Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

Unveiling Entropy-Performance Decoupling in Agentic RL for Tool-Integrated Reasoning

UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression

V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception

VAMIRec: Value-Aware Memory Intervention for Continual Recommendation

Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy Evaluation

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence

Visual-ERM: Reward Modeling for Visual Equivalence

Visual Harness: Grounding Multimodal Reasoning in Physics Engines

Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models

Visual Reinforcement Fine-Tuning via Bootstrapped Medical Reasoning

VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs

VL-DocIR: A Benchmark for Vision-Based Long Document Retrieval

VLM$^3$: Vision Language Models Are Native 3D Learners

Volatility-Whitened Probabilistic Residual Modeling for Long-Term Time Series Forecasting

VoluCore: Spanning Teacher Representations with Volumetric Coresets for Data-Efficient LLM Distillation

Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding

VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on

VVTRec: Radio Interferometric Reconstruction through Visual and Textual Modality Enrichment

Walking Through 3D Spaces: Spatial Routing for Referring 3D Gaussian Splatting Segmentation

Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games

WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos

What Does a Sparse Autoencoder Feature Do? A Weight-Based Account

What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment

"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts

What Kind of Diffusion Models Do We Need in Online Reinforcement Learning?

What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment

What Should Remain After Forgetting? Rethinking LLM Unlearning as Predictive Posterior Correction

What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching

When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework

When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment

When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG

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 do Prophets Profit in Prediction Markets?

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search

When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory

When to Adopt Model Updates

When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation

Where Should Society Draw the Line? A Social Choice Approach to Collective Consent

Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition

Winfree Oscillatory Neural Network

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

Working with AI: Measuring the Applicability of Generative AI to Occupations

WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation

WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification

WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States

Zeroth-Order Stackelberg Control in Combinatorial Congestion Games

ZO-F2: Low-variance Fisher preconditioner via bilinear estimation for zeroth-order optimization

μLM: Rethinking Sub-100M Language Models through Memory-First Design

Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair

Auditing Closed-Loop Learning in Recurrent Neural Networks: Reproduction, Robustness, and Generalization

A Reproduction Study of Weight-Based Mechanistic Interpretability in Bilinear MLPs

Evaluating the evidence trace of NeurIPS 2025 contributions with agentic code auditing

Reproducibility study of FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering

[Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning

WAREX: Web Agent Reliability Evaluation on Existing Benchmarks

Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension

Opening Up a New Layer: A Deeper Look into "Interpreting CLIP with Hierarchical Sparse Autoencoders"

[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL

Reproducibility study of "Bilinear MLPs enable weight-based mechanistic interpretability"

Revisiting "Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing"

Revisiting B2T: Discovering and Mitigating Visual Biases through Keyword Explanations

XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher

Revisiting RegressionMSR: A Reproducibility Study

(ends 8:00 PM)