Skip to yearly menu bar Skip to main content


Show Detail
Schedule Sun Mon Tue Wed Thu Fri Sat Sun
Timezone: America/Los_Angeles
 
Filter Rooms:  

MON 1 DEC
noon
Registration Desk
(ends 6:00 PM)

TUE 2 DEC
7:30 a.m.
Registration Desk
(ends 6:00 PM)
8 a.m.
Affinity Workshop:
Women in Machine Learning
(ends 5:00 PM)
8:30 a.m.
Expo Talk Panel:
Telling Stories at Scale: Multimodal ML in the Global Media Landscape
(ends 9:30 AM)
Expo Talk Panel:
Toward General Full Autonomy: Open Research Challenges in Scalable Self-Driving
(ends 9:30 AM)
Expo Talk Panel:
Beyond Benchmarks: Rethinking Reasoning in Language Models
(ends 9:30 AM)
Expo Talk Panel:
Foundational Generative Recommendations for E-Commerce
(ends 9:30 AM)
Expo Talk Panel:
From Research to Markets: Applying Cutting-Edge Machine Learning in Quantitative Finance
(ends 9:30 AM)
Expo Talk Panel:
Multimodal Data Foundation at Industry-Scale
(ends 9:30 AM)
Expo Talk Panel:
Data Scout: “From Prompt to Corpus: Accelerating Domain-Specific Data Collection with LLMGuided Discovery”
(ends 9:30 AM)
Expo Talk Panel:
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
(ends 9:30 AM)
9 a.m.
Break:
Coffee Break
(ends 10:00 AM)
Affinity Workshop:
LatinX in AI
(ends 5:00 PM)
9:30 a.m.
Tutorial:
Foundations of Tensor/Low-Rank Computations for AI
(ends 12:00 PM)
Tutorial:
Human-AI Alignment: Foundations, Methods, Practice, and Challenges
(ends 12:00 PM)
Tutorial:
Planning in the Era of Language Models
(ends 12:00 PM)
Tutorial:
Model Merging: Theory, Practice and Applications
(ends 12:00 PM)
Tutorial:
New Frontiers of Hyperparameter Optimization: Recent advances and open challenges in theory and practice
(ends 12:00 PM)
Tutorial:
Explain AI Models: Methods and Opportunities in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
(ends 1:30 PM)
Tutorial:
Energy and Power as First-Class ML Design Metrics
(ends 12:00 PM)
noon
Expo Demonstration:
Multimodal AI Forensic Search for Video Surveillance
(ends 3:00 PM)
Expo Demonstration:
Efficient LiDAR Processing with AI Models Leveraging Heterogeneous Compute
(ends 3:00 PM)
Expo Demonstration:
BeeAI
(ends 3:00 PM)
Expo Demonstration:
Parallel generation with verification on device
(ends 3:00 PM)
Expo Demonstration:
Soft Prompts for On-Device Content Moderation
(ends 3:00 PM)
Expo Demonstration:
Generating group photos of multiple people from text and reference images
(ends 3:00 PM)
Expo Demonstration:
Reasoning through Multimodal End-to-End Decision Transformer Networks and Vision Language Action (VLA) models
(ends 3:00 PM)
Expo Demonstration:
Disaggregated LLM Serving on AI Accelerators
(ends 3:00 PM)
Expo Demonstration:
SwiftEdit: Fast Text-guided Image Editing via One-step Diffusion on a Mobile Device
(ends 3:00 PM)
Expo Demonstration:
Mobile Video Diffusion Transformers
(ends 3:00 PM)
Expo Demonstration:
Pushing the boundaries of chemical synthesis with RetroChimera
(ends 3:00 PM)
Expo Demonstration:
AI or Human
(ends 3:00 PM)
Expo Demonstration:
PRIME Guardrails in Action: A Live Demonstration of an Agentic, Multi-Layered Safety Framework for Generative AI
(ends 3:00 PM)
Expo Demonstration:
ALICE: Agentic Logic for Incident and Codebug Elimination
(ends 3:00 PM)
Expo Workshop:
Creative and Protective AI for Music and Entertainment
(ends 1:30 PM)
Expo Workshop:
Large-Scale Real-World Physical AI Systems
(ends 1:30 PM)
Expo Demonstration:
LLM-Powered Intelligent Data Engineering: From Workflow Design to Ingestion andQuality Assurance
(ends 3:00 PM)
Expo Workshop:
Checkmate: Fine-tune your own small language model for real-time chess reasoning and gameplay on AWS Trainium
(ends 1:30 PM)
Expo Workshop:
Workshop on multimodal Superintelligence
(ends 1:30 PM)
Expo Demonstration:
ContextForge
(ends 3:00 PM)
Expo Demonstration:
Interpretable AI for Risk-Based Human Rights Assessment in Global Supply Chains
(ends 3:00 PM)
Exhibitor Spot Talks - Session 1 [12:00-6:00]
Talks 12:00-6:00
Exhibitor Talk - Simular
Recycling the World Computer: Fault-Tolerant LLM Training on Idle GPU Capacity
Half Is Heroic: Rewarding Non-Answers for Responsible AI Decision-Making
Auto-SWE-Bench: Scalable, Real-World Benchmarks for LLM Coding Evaluation
Exhibitor Talk - Optiver
Exhibitor Talk - TD Bank Group - Layer6 AI
Exhibitor Talk - Sony
Rights Management Capabilities and Enforcement for AI Music
Exploring Pathways into Quantitative Research
Semantic Parsing at Bloomberg
ATLAS: AdapTive-LeArning Speculator System for Real-Time LLM Inference Acceleration with Together AI
Entropy by Design: Synthetic Data at Scale
Exhibitor Talk - Cohere
Exhibitor Talk - Microsoft
Agentic AI: Exploring Evolution and Evaluation
Exhibitor Talk - D. E. Shaw Research
Measuring Emergent Behavior in AI Agents - Weights & Biases
Measuring Enterprise Agents - Production Readiness Index and Evaluation Environment
Exhibitor Talk - Lambda
Exhibitor Talk - Scale AI
Exhibitor Talk - MathWorks
AI for Code: From Autocompletion to Autonomous Agents
From Agent Soup to Proper Software Design: Putting the Developer Back in Control of Generative AI with Mellea
Exhibitor Talk - Lenovo
From RLHF to RL Reality: Teaching AI to Think Inside the Enterprise
Exhibitor Talk - WRITER
Exhibitor Talk - Rennaissance Philanthropy
Algorithmic Trading with Large-Scale Deep Learning
Automated Curation of Foundation-Scale Pretraining Datasets
Databricks Presents a New IDP Benchmark
Distributed Diffusion Training
The State of Open Source AI and a Look Into the Future
(ends 6:00 PM)
Expo Demonstration:
Build verifiable apps using Generative AI and Automated Reasoning
(ends 3:00 PM)
Expo Workshop:
CausalFairness: An Open-Source Python Library for Causal Fairness Analysis
(ends 1:30 PM)
Expo Demonstration:
Learning to Steer LLMs with AI Steerability 360 and In-Context Explainability 360
(ends 3:00 PM)
Expo Workshop:
Introduction to Generative Computing
(ends 1:30 PM)
Break:
Hosted Lunch
(ends 1:30 PM)
Expo Demonstration:
Who Needs Attention Anyway? Real-Time Control from Learned State Geometry
(ends 3:00 PM)
Expo Workshop:
Exploring Trust and Reliability in LLM Evaluation
(ends 1:30 PM)
1 p.m.
Affinity Workshop:
New in ML
(ends 5:00 PM)
Affinity Workshop:
Muslims in ML
(ends 5:30 PM)
1:30 p.m.
Tutorial:
Foundations of Imitation Learning: From Language Modeling to Continuous Control
(ends 4:00 PM)
Tutorial:
Scale Test-Time Compute on Modern Hardware
(ends 3:00 PM)
Tutorial:
Autoregressive Models Beyond Language
(ends 3:00 PM)
Tutorial:
Recent Developments in Geometric Machine Learning: Foundations, Models, and More
(ends 3:00 PM)
Tutorial:
Theoretical Insights on Training Instability in Deep Learning
(ends 3:00 PM)
Tutorial:
The Science of Benchmarking: What’s Measured, What’s Missed, and What’s Next
(ends 3:00 PM)
Tutorial:
Data Privacy, Memorization, & Legal Implications in Generative AI: A Practical Guide
(ends 3:00 PM)
4 p.m.
Expo Talk Panel:
Recent developments in embodied AI
(ends 5:00 PM)
Expo Talk Panel:
Distributed Orthonormal Updates for Large-Scale Training
(ends 5:00 PM)
Expo Talk Panel:
Ling 2.0 and Ling-1T: Scaling Knowledge-Enhanced Large Language Models for Reasoning and Efficiency
(ends 5:00 PM)
Expo Talk Panel:
Agentic AI/RL
(ends 5:00 PM)
Expo Talk Panel:
Neural Arms Race: Authenticity, Infringement Analysis, and Attribution in the Age of AI Music
(ends 5:00 PM)
Expo Talk Panel:
Building an AI Ecosystem for Multiscale Biological Discovery
(ends 5:00 PM)
Break:
Coffee Break
(ends 4:30 PM)
Expo Talk Panel:
Building Foundational Models for Robotics at Tesla
(ends 5:00 PM)
5:30 p.m.
Remarks:
Welcome Remarks
(ends 6:00 PM)
6 p.m.
Affinity Poster Session:
Affinity Joint Poster Session
(ends 9:00 PM)
Reception:
Welcome Reception
(ends 8:00 PM)

WED 3 DEC
7:30 a.m.
Registration Desk
(ends 6:00 PM)
8 a.m.
Break:
Coffee Break
(ends 8:30 AM)
8:30 a.m.
San Diego Invited Talk:
Rich Sutton_The Oak Architecture: A Vision of SuperIntelligence from Experience
Rich Sutton
(ends 9:30 AM)
9:30 a.m.
Exhibitor Spot Talks - Session 2 [9:30-4:45]
Talks 9:30-4:42
Arm AI Acceleration in Action: ExecuTorch + ONNX on Mobile and Edge
Exhibitor Talk - Open AI
Deep Learning Integration Across the Proprietary Trading Pipeline
Exhibitor Talk - io.net
Dolphin: A Large-Scale ASR Model for Eastern Languages
AI for Creativity
Building Enterprise AI to Transform Productivity: Lessons from Atlassian
Bridging Research & Reality - Applied AI, Lessons from CommBank on Generative Interfaces to Fine-Tuning
Exhibitor Talk - Yokogawa Digital Corporation
Scaling Data Quality in the Era of LLMs: A Quality Framework
Exploring Diffusion Transformer Designs via Grafting
Exhibitor Talk - Uber AI Solutions
Behind SWE-rebench: infrastructure to build massive datasets of SWE tasks
ML for drug discovery at Genesis Molecular AI
Agentic Full-Stack Benchmarking for Knowledge Work
Exhibitor Talk - Voltage Park
Exhibitor Talk - MBZUAI/IFM
T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
Exhibitor Talk - Qualcomm
Personalized Dental Care: 3D generative models for biomimetic dental restorations
Exhibitor Talk - Tesla
Exhibitor Talk - Upwork
Exhibitor Talk - Astrus
Exhibitor Talk - DRW
(ends 4:45 PM)
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral Session 1A [10:00-11:00]
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
(ends 11:00 AM)
Oral Session 1B [10:00-11:00]
Optimal Mistake Bounds for Transductive Online Learning
High-Dimensional Calibration from Swap Regret
Does Stochastic Gradient really succeed for bandits?
(ends 11:00 AM)
Oral Session 1C [10:00-11:00]
Adjoint Schrödinger Bridge Sampler
Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation
Class-wise Balancing Data Replay for Federated Class-Incremental Learning
(ends 11:00 AM)
Oral Session 1D [10:00-11:00]
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
(ends 11:00 AM)
Oral Session 1E [10:00-11:00]
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
Perception Encoder: The best visual embeddings are not at the output of the network
Interactive Cross-modal Learning for Text-3D Scene Retrieval
(ends 11:00 AM)
11 a.m.
Creative AI Session 1 [11:00-2:00]
Chairs: Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian
s 11:00-2:00
[11:00] AI as intermediary in modern-day ritual: An immersive, interactive production of the roller disco musical Xanadu at UCLA
[11:00] AI is Misled by GenAI: Stylistic Bias in Automated Assessment of Creativity in Large Language Models
[11:00] CoTextor: Training-Free Modular Multilingual Text Editing via Layered Disentanglement and Depth-Aware Fusion
[11:00] Digital Plankton
[11:00] Echoes of Humanity: Exploring the Perceived Humanness of AI Music
[11:00] EmoNest: Crafting Emotionally-Adaptive Experiences with Generative AI
[11:00] EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration
[11:00] Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
[11:00] How Foundation Models are Reshaping Non-Invasive Brain–Computer Interfaces: A Case for Novel Human Expression and Alignment
[11:00] Interactive Artistic Text-To-Voice: Tungnaá and Bla Blavatar vs Jaap Blonk
[11:00] Large-Scale Training Data Attribution for Music Generative Models via Unlearning
[11:00] Melody Slot Machine III for Automatic Fingering Saxophone using Servomotors
[11:00] Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems
[11:00] Plan Before You Write: Improve LLM writing by planning
[11:00] Real-Time Intuitive AI Drawing System for Collaboration: Enhancing Human Creativity through Formal and Contextual Intent Integration
[11:00] Sound Clouds: Exploring ambient intelligence in public spaces to elicit deep human experience of awe, wonder, and beauty
[11:00] Stroke Patches: Customizable Artistic Image Styling Using Regression
[11:00] Surface Tension
[11:00] Synthaesthetic Art: Human-Machine Creative Collaboration
[11:00] The Anemoia Device: A Tangible AI System for the Co-creation of Synthetic Memories through Scent
[11:00] The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity
[11:00] The Stochastic Parrot: a physical AI Cohabitant
[11:00] The Sublime Ordinary: A Tool for Analysing Temporal City Soundscapes
(ends 2:00 PM)
San Diego Poster Session 1 [11:00-2:00]
Posters 11:00-2:00
$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
Absence Bench: Language Models Can’t See What’s Missing
Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
Accelerating Optimization via Differentiable Stopping Time
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
A Circular Argument: Does RoPE need to be Equivariant for Vision?
AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
Activated LoRA: Fine-tuned LLMs for Intrinsics
Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory
Active Test-time Vision-Language Navigation
ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
Activity Pruning for Efficient Spiking Neural Networks
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link Prediction
Adaptive Inference-Time Scaling via Cyclic Diffusion Search
AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Adjoint Schrödinger Bridge Sampler
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction
Adversary Aware Optimization for Robust Defense
Aeolus: A Multi-structural Flight Delay Dataset
Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance
AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering
Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation
A Latent Multilayer Graphical Model For Complex, Interdependent Systems
Alias-Free ViT: Fractional Shift Invariance via Linear Attention
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression
ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
An Adaptive Quantum Circuit of Dempster's Rule of Combination for Uncertain Pattern Classification
AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation
An Investigation of Memorization Risk in Healthcare Foundation Models
AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models
Anti-Aliased 2D Gaussian Splatting
APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
Approximately Aligned Decoding
A Pre-training Framework for Relational Data with Information-theoretic Principles
A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design
A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
Assignments for Congestion-Averse Agents: Seeking Competitive and Envy-Free Solutions
A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy
Asymmetric Duos: Sidekicks Improve Uncertainty
Asymptotic Theory of Geometric and Adaptive $k$-Means Clustering
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
Atom of Thoughts for Markov LLM Test-Time Scaling
Audio Super-Resolution with Latent Bridge Models
Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
AutoHood3D: A Multi‑Modal Benchmark for Automotive Hood Design and Fluid–Structure Interaction
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Backdoor Mitigation via Invertible Pruning Masks
Balanced Active Inference
Balancing Multimodal Training Through Game-Theoretic Regularization
BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents
Benchmarking Large Language Models with Integer Sequence Generation Tasks
Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models
Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
Beyond the Average: Distributional Causal Inference under Imperfect Compliance
Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing
Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning
Bio-Inspired Image Restoration
Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
Block-Biased Mamba for Long-Range Sequence Processing
BlockDecoder: Boosting ASR Decoders with Context and Merger Modules
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
Bootstrap Off-policy with World Model
Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport
Boundary-Value PDEs Meet Higher-Order Differential Topology-aware GNNs
BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
Brain-Like Processing Pathways Form in Models With Heterogeneous Experts
Brain-like Variational Inference
Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
Cameras as Relative Positional Encoding
Can Diffusion Models Disentangle? A Theoretical Perspective
Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
Caption This, Reason That: VLMs Caught in the Middle
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
Causal Explanation-Guided Learning for Organ Allocation
Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models
ChemPile: A 250 GB Diverse and Curated Dataset for Chemical Foundation Models
CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering
Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects
CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm
Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback
Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections
Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models
Compress & Cache: Vision token compression for efficient generation and retrieval
Compress Large Language Models via Collaboration Between Learning and Matrix Approximation
Computable universal online learning
Computational Budget Should Be Considered in Data Selection
Computation and Memory-Efficient Model Compression with Gradient Reweighting
Concept Incongruence: An Exploration of Time and Death in Role Playing
Confidence-Aware With Prototype Alignment for Partial Multi-label Learning
Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation
Conformal Prediction for Causal Effects of Continuous Treatments
Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
Confounding Robust Deep Reinforcement Learning: A Causal Approach
ConfTuner: Training Large Language Models to Express Their Confidence Verbally
Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning
Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
Constrained Discrete Diffusion
Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
Constructing an Optimal Behavior Basis for the Option Keyboard
Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
Contextual Thompson Sampling via Generation of Missing Data
Continual Knowledge Adaptation for Reinforcement Learning
Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
Continuous Domain Generalization
Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data
Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares
COOPERA: Continual Open-Ended Human-Robot Assistance
Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning
Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
Coresets for Clustering Under Stochastic Noise
Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
Counterfactual Evolution of Multimodal Datasets via Visual Programming
Counterfactual Implicit Feedback Modeling
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design
CroPe: Cross-Modal Semantic Compensation Adaptation for All Adverse Scene Understanding
Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
Cross-Modal Representational Knowledge Distillation for Enhanced Spike-informed LFP Modeling
CRRL: Learning Channel-invariant Neural Representations for High-performance Cross-day Decoding
CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
Curious Causality-Seeking Agents Learn Meta Causal World
CVGL: Causal Learning and Geometric Topology
CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays
D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
Data Fusion for Partial Identification of Causal Effects
DataRater: Meta-Learned Dataset Curation
DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components
DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting
Demystifying Network Foundation Models
Demystifying Spectral Feature Learning for Instrumental Variable Regression
Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling
DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration
Dense Associative Memory with Epanechnikov Energy
DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting
Deployment Efficient Reward-Free Exploration with Linear Function Approximation
DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization
DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos
DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
Differentiable extensions with rounding guarantees for combinatorial optimization over permutations
Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
DINGO: Constrained Inference for Diffusion LLMs
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptation
Distribution Learning Meets Graph Structure Sampling
DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudes
DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
Does Representation Guarantee Welfare?
Does Stochastic Gradient really succeed for bandits?
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
Do-PFN: In-Context Learning for Causal Effect Estimation
DoseSurv: Predicting Personalized Survival Outcomes under Continuous-Valued Treatments
Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization
DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models
Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
DualMPNN: Harnessing Structural Alignments for High-Recovery Inverse Protein Folding
Dual-Path Temporal Decoder for End-to-End Multi-Object Tracking
DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation
DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference
D-VST: Diffusion Transformer for Pathology-Correct Tone-Controllable Cross-Dye Virtual Staining of Whole Slide Images
DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
DyMoDreamer: World Modeling with Dynamic Modulation
DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders
Dynamic View Synthesis as an Inverse Problem
DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation
EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes
EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
Effective Neural Approximations for Geometric Optimization Problems
Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
Efficient Data Selection at Scale via Influence Distillation
Efficient Fairness-Performance Pareto Front Computation
Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates
Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
Efficient Part-level 3D Object Generation via Dual Volume Packing
Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
Efficient Randomized Experiments Using Foundation Models
Efficient Representativeness-Aware Coreset Selection
Efficient Spectral Control of Partially Observed Linear Dynamical Systems
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
Eliciting Reasoning in Language Models with Cognitive Tools
Embodied Cognition Augmented End2End Autonomous Driving
Emergence of Linear Truth Encodings in Language Models
EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge
E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Empowering Decision Trees via Shape Function Branching
End-to-End Vision Tokenizer Tuning
Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling
EngiBench: A Framework for Data-Driven Engineering Design Research
Enhancing Consistency of Flow-Based Image Editing through Kalman Control
Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
Enhancing Tactile-based Reinforcement Learning for Robotic Control
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning
Epistemic Uncertainty for Generated Image Detection
Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
Escaping Collapse: The Strength of Weak Data for Large Language Model Training
Estimating cognitive biases with attention-aware inverse planning
Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning
EUGens: Efficient, Unified and General Dense Layers
Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth
Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps
Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias
Evolutionary Prediction Games
Evolving and Regularizing Meta-Environment Learner for Fine-Grained Few-Shot Class-Incremental Learning
Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
ExAct: A Video-Language Benchmark for Expert Action Analysis
Execution Guided Line-by-Line Code Generation
Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
Exploration via Feature Perturbation in Contextual Bandits
Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining
Extracting task-relevant preserved dynamics from contrastive aligned neural recordings
Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
Fair Continuous Resource Allocation with Equality of Impact
Fairness-aware Bayes Optimal Functional Classification
Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models
Fast Inference for Augmented Large Language Models
Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms
Fast Training of Large Kernel Models with Delayed Projections
Federated Continual Learning via Orchestrating Multi-Scale Expertise
Federated Multi-armed Bandits with Efficient Bit-Level Communications
FedLPA: Local Prior Alignment for Heterogeneous Federated Generalized Category Discovery
FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition
FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies
Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations
FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
FIGRDock: Fast Interaction-Guided Regression for Flexible Docking
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
Fine-grained List-wise Alignment for Generative Medication Recommendation
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning
First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
FLAME: Fast Long-context Adaptive Memory for Event-based Vision
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
For Better or for Worse, Transformers Seek Patterns for Memorization
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
Formal Models of Active Learning from Contrastive Examples
FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
Fractional Diffusion Bridge Models
Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
Frequency-Aware Token Reduction for Efficient Vision Transformer
From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
From Sequence to Structure: Uncovering Substructure Reasoning in Transformers
FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
FuncGenFoil: Airfoil Generation and Editing Model in Function Space
Generalizable Hand-Object Modeling from Monocular RGB Images via 3D Gaussians
Generalizable, real-time neural decoding with hybrid state-space models
Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
Generalization Bounds for Rank-sparse Neural Networks
Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection
Generating Computational Cognitive models using Large Language Models
Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings
Generative Model Inversion Through the Lens of the Manifold Hypothesis
Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders
GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
Geometry-Aware Edge Pooling for Graph Neural Networks
Geometry of Decision Making in Language Models
GeoRemover: Removing Objects and Their Causal Visual Artifacts
GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Glance2Gaze: Efficient Vision-Language Models from Glance Fusion to Gaze Compression
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks
GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
Graph Your Own Prompt
Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure
GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
Group-Level Data Selection for Efficient Pretraining
GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling
Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment
Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation
Head Pursuit: Probing Attention Specialization in Multimodal Transformers
HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference
High-Dimensional Calibration from Swap Regret
HOComp: Interaction-Aware Human-Object Composition
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
Holistic Order Prediction in Natural Scenes
How Benchmark Prediction from Fewer Data Misses the Mark
How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
How to Train Your LLM Web Agent: A Statistical Diagnosis
Hybrid Latent Reasoning via Reinforcement Learning
HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies
Imitation Learning with Temporal Logic Constraints
Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
Improved Balanced Classification with Theoretically Grounded Loss Functions
IMPROVED LEARNING THEORY FOR KERNEL DISTRIBUTION REGRESSION WITH TWO-STAGE SAMPLING
Improved Training Technique for Shortcut Models
Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
Improving Deep Learning for Accelerated MRI With Data Filtering
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
Incomplete Multi-view Deep Clustering with Data Imputation and Alignment
In-Context Compositional Learning vis Sparse Coding Transformer
In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
Increasing the Utility of Synthetic Images through Chamfer Guidance
Incremental Sequence Classification with Temporal Consistency
Individual Fairness In Strategic Classification
IneqSearch: Hybrid Reasoning for Olympiad Inequality Proofs
Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular Optimization
Inference-Time Reward Hacking in Large Language Models
Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
Infinite Neural Operators: Gaussian processes on functions
Information Retrieval Induced Safety Degradation in AI Agents
Information-Theoretic Reward Decomposition for Generalizable RLHF
Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes
InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
Instance-Optimality for Private KL Distribution Estimation
Integration Matters for Learning PDEs with Backwards SDEs
Interactive Cross-modal Learning for Text-3D Scene Retrieval
Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features
In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
IRRISIGHT: A Large-Scale Multimodal Dataset and Scalable Pipeline to Address Irrigation and Water Management in Agriculture
It’s Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation
Jacobian-Based Interpretation of Nonlinear Neural Encoding Model
JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics
JAFAR: Jack up Any Feature at Any Resolution
Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning
Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling
KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference
KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
Learn2Mix: Training Neural Networks Using Adaptive Data Integration
Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning
Learned Prefix Caching for Efficient LLM Inference
Learning 3D Persistent Embodied World Models
Learning-Augmented Algorithms for $k$-median via Online Learning
Learning-Augmented Facility Location Mechanisms for the Envy Ratio Objective
Learning-Augmented Online Bipartite Fractional Matching
Learning CAD Modeling Sequences via Projection and Part Awareness
Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems
Learning from Demonstrations via Capability-Aware Goal Sampling
Learning Interestingness in Automated Mathematical Theory Formation
Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards
Learning Provably Improves the Convergence of Gradient Descent
Learning Repetition-Invariant Representations for Polymer Informatics
Learning to cluster neuronal function
Learning to Instruct for Visual Instruction Tuning
Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting
Less is More: Improving LLM Alignment via Preference Data Selection
Let Brain Rhythm Shape Machine Intelligence for Connecting Dots on Graphs
Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
Linear Attention for Efficient Bidirectional Sequence Modeling
LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery
LittleBit: Ultra Low-Bit Quantization via Latent Factorization
LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
LLM-PySC2: Starcraft II learning environment for Large Language Models
LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives
Long-tailed Recognition with Model Rebalancing
Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
LoRA-EnVar: Parameter-Efficient Hybrid Ensemble Variational Assimilation for Weather Forecasting
LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers
LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks
Low Rank Gradients and Where to Find Them
MagCache: Fast Video Generation with Magnitude-Aware Cache
MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective
MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
Marginal-Nonuniform PAC Learnability
Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise
MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives
MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
Memory-Efficient Training with In-Place FFT Implementation
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
Meta CLIP 2: A Worldwide Scaling Recipe
Meta-World+: An Improved, Standardized, RL Benchmark
MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models
MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction
MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
Mitigating Semantic Collapse in Partially Relevant Video Retrieval
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
ML4CFD Competition: Results and Retrospective Analysis
MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
MobileODE: An Extra Lightweight Network
MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions
Modeling the Economic Impacts of AI Openness Regulation
Model Merging in Pre-training of Large Language Models
Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient Backpropagation
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery
MoleBridge: Synthetic Space Projecting with Discrete Markov Bridges
Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
Monotone and Separable Set Functions: Characterizations and Neural Models
MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
More of the Same: Persistent Representational Harms Under Increased Representation
MOSDT: Self-Distillation-Based Decision Transformer for Multi-Agent Offline Safe Reinforcement Learning
Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
Multi-Agent Collaboration via Evolving Orchestration
Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration
Multi-Token Prediction Needs Registers
Multivariate Dynamic Mediation Analysis under a Reinforcement Learning Framework
Multivariate Latent Recalibration for Conditional Normalizing Flows
MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans
NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
Native Segmentation Vision Transformers
Near-Exponential Savings for Population Mean Estimation with Active Learning
Nearly-Linear Time and Massively Parallel Algorithms for $k$-anonymity
NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs
Neural Atlas Graphs for Dynamic Scene Decomposition and Editing
Neural Fractional Attention Differential Equations
Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models
Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go
NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods
New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
Non-Convex Tensor Recovery from Tube-Wise Sensing
NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes
ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction
Object Concepts Emerge from Motion
OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement
Off-policy Reinforcement Learning with Model-based Exploration Augmentation
OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states
Omni-Mol: Multitask Molecular Model for Any-to-any Modalities
Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
One Filters All: A Generalist Filter For State Estimation
One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time
On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
On scalable and efficient training of diffusion samplers
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
On the creation of narrow AI: hierarchy and nonlocality of neural network skills
On the Existence and Complexity of Core-Stable Data Exchanges
On the rankability of visual embeddings
On Traceability in $\ell_p$ Stochastic Convex Optimization
Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization
Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
Optimal Mistake Bounds for Transductive Online Learning
ORBIT - Open Recommendation Benchmark for Reproducible Research with Hidden Tests
ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Panoptic Captioning: An Equivalence Bridge for Image and Text
PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination
PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards
Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection
Path-Enhanced Contrastive Learning for Recommendation
PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
PDPO: Parametric Density Path Optimization
Perception Encoder: The best visual embeddings are not at the output of the network
Permissioned LLMs: Enforcing Access Control in Large Language Models
Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning
Personalized Federated Conformal Prediction with Localization
PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
PhysDiff-VTON: Cross-Domain Physics Modeling and Trajectory Optimization for Virtual Try-On
Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
PhysX-3D: Physical-Grounded 3D Asset Generation
PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models
Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning
PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
Point Cloud Synthesis Using Inner Product Transforms
PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models
Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
Precise Information Control in Long-Form Text Generation
Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems
Predicting Empirical AI Research Outcomes with Language Models
Preference Distillation via Value based Reinforcement Learning
Preference Learning with Lie Detectors can Induce Honesty or Evasion
Preventing Shortcuts in Adapter Training via Providing the Shortcuts
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
Privacy Reasoning in Ambiguous Contexts
Private Evolution Converges
Private Set Union with Multiple Contributions
Probabilistic Reasoning with LLMs for Privacy Risk Estimation
Probabilistic Stability Guarantees for Feature Attributions
Probabilistic Token Alignment for Large Language Model Fusion
Probing Equivariance and Symmetry Breaking in Convolutional Networks
Probing Neural Combinatorial Optimization Models
ProDAG: Projected Variational Inference for Directed Acyclic Graphs
PROFIT: A Specialized Optimizer for Deep Fine Tuning
Protocols for Verifying Smooth Strategies in Bandits and Games
Provable Gradient Editing of Deep Neural Networks
Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
PRSformer: Disease Prediction from Million-Scale Individual Genotypes
Puppeteer: Rig and Animate Your 3D Models
Purest Quantum State Identification
Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation
QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification
Quantifying Generalisation in Imitation Learning
Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
R$^2$ec: Towards Large Recommender Models with Reasoning
RADAR: Benchmarking Language Models on Imperfect Tabular Data
Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platfrom for Embodied Intelligence
Real-Time Execution of Action Chunking Flow Policies
Reasoning as an Adaptive Defense for Safety
Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Rectified CFG++ for Flow Based Models
Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA
Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance
Reliably detecting model failures in deployment without labels
Remarkable Robustness of LLMs: Stages of Inference?
Reparameterized LLM Training via Orthogonal Equivalence Transformation
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
Restricted Global-Aware Graph Filters Bridging GNNs and Transformer for Node Classification
Results of the Big ANN: NeurIPS’23 competition
Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality
Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation
Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
Reverse-Annealed Sequential Monte Carlo for Efficient Bayesian Optimal Experiment Design
Reverse Diffusion Sequential Monte Carlo Samplers
Reverse Engineering Human Preferences with Reinforcement Learning
Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
Reward Reasoning Models
Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry
RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
Risk-Averse Total-Reward Reinforcement Learning
RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
RoboScape: Physics-informed Embodied World Model
RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness
Robust Estimation Under Heterogeneous Corruption Rates
Robust Label Proportions Learning
RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting
RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping
Root Cause Analysis of Outliers with Missing Structural Knowledge
Rotary Masked Autoencoders are Versatile Learners
SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater
SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
Scalable and adaptive prediction bands with kernel sum-of-squares
Scalable In-context Ranking with Generative Models
ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets
Scaling Offline RL via Efficient and Expressive Shortcut Models
Scaling Physical Reasoning with the PHYSICS Dataset
ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection
SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation
scGeneScope: A Treatment-Matched Single Cell Imaging and Transcriptomics Dataset and Benchmark for Treatment Response Modeling
Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks
SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
Searching Latent Program Spaces
Secure and Confidential Certificates of Online Fairness
Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models
Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
Self-Adapting Language Models
Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection
Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models
Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens
Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training
Semantic-guided Diverse Decoding for Large Language Model
Semantic Representation Attack against Aligned Large Language Models
Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
SentinelKilnDB: A Large-Scale Dataset and Benchmark for OBB Brick Kiln Detection in South Asia Using Satellite Imagery
Sequence Modeling with Spectral Mean Flows
Sequential Attention-based Sampling for Histopathological Analysis
S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
ShapeEmbed: a self-supervised learning framework for 2D contour quantification
ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation
ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
Single-Step Operator Learning for Conditioned Time-Series Diffusion Models
Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
Size-adaptive Hypothesis Testing for Fairness
Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis
SkyLadder: Better and Faster Pretraining via Context Window Scheduling
Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
SmartCache: Context-aware Semantic Cache for Efficient Multi-turn LLM Inference
SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning
Social World Model-Augmented Mechanism Design Policy Learning
SOMBRL: Scalable and Optimistic Model-Based RL
SONAR: Long-Range Graph Propagation Through Information Waves
SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration
SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering
SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking
Spectral Analysis of Representational Similarity with Limited Neurons
SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography
Split conformal classification with unsupervised calibration
Split Gibbs Discrete Diffusion Posterior Sampling
SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
STACI: Spatio-Temporal Aleatoric Conformal Inference
Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals
STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology
STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data
Statistical Inference for Decentralized Federated Learning
Statistical Inference under Performativity
STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models
STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
Strategyproof Reinforcement Learning from Human Feedback
StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
Structural Causal Bandits under Markov Equivalence
Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
Sum Estimation under Personalized Local Differential Privacy
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
Support  Vector  Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
SWE-smith: Scaling Data for Software Engineering Agents
Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning
SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
Synergistic Tensor and Pipeline Parallelism
Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics
TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
TAI3: Testing Agent Integrity in Interpreting User Intent
TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models
Taming Adversarial Constraints in CMDPs
Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Taxonomy of reduction matrices for Graph Coarsening
Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
Tensor Product Attention Is All You Need
Test-Time Adaptation by Causal Trimming
The Adaptive Complexity of Minimizing Relative Fisher Information
The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
The Emergence of Abstract Thought in Large Language Models Beyond Any Language
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination
The Rich and the Simple: On the Implicit Bias of Adam and SGD
The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
The Temporal Graph of Bitcoin Transactions
The Underappreciated Power of Vision Models for Graph Structural Understanding
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Thompson Sampling for Multi-Objective Linear Contextual Bandit
Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
Tight Bounds for Maximum Weight Matroid Independent Set and Matching in the Zero Communication Model
TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
Token Embeddings Violate the Manifold Hypothesis
TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
ToolRL: Reward is All Tool Learning Needs
To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds
Towards A Translative Model of Sperm Whale Vocalization
Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis
Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs
Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs
Towards Robust Uncertainty Calibration for Composed Image Retrieval
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
Towards Understanding Transformers in Learning Random Walks
Training Language Models to Generate Quality Code with Program Analysis Feedback
Training Robust Graph Neural Networks by Modeling Noise Dependencies
Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
Transition Matching: Scalable and Flexible Generative Modeling
TreeFinder: A US-Scale Benchmark Dataset for Individual Tree Mortality Monitoring Using High-Resolution Aerial Imagery
Tree-Sliced Entropy Partial Transport
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming
TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition
TTRL: Test-Time Reinforcement Learning
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
Ultrametric Cluster Hierarchies: I Want ‘em All!
UMoE: Unifying Attention and FFN with Shared Experts
Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
Uncertainty-Sensitive Privileged Learning
Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix
Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
Understanding protein function with a multimodal retrieval-augmented foundation model
Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
Unified Transferability Metrics for Time Series Foundation Models
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks
UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
Validating LLM-as-a-Judge Systems under Rating Indeterminacy
Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings
Variational Polya Tree
VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image
VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video
Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
Video Perception Models for 3D Scene Synthesis
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Vision-centric Token Compression in Large Language Model
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation
Vision Transformers Don't Need Trained Registers
Visual Instruction Bottleneck Tuning
VisualLens: Personalization through Task-Agnostic Visual History
VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model
VividFace: A Robost and High-Fidelity Video Face Swapping Framework
VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization
Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
Wasserstein Transfer Learning
WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
What Do Latent Action Models Actually Learn?
What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
What Makes a Reward Model a Good Teacher? An Optimization Perspective
What Really is a Member? Discrediting Membership Inference via Poisoning
What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
Which Algorithms Have Tight Generalization Bounds?
Whole-Body Conditioned Egocentric Video Prediction
Who Reasons in the Large Language Models?
Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
WMCopier: Forging Invisible Watermarks on Arbitrary Images
Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications
WorldMem: Long-term Consistent World Simulation with Memory
WorldModelBench: Judging Video Generation Models As World Models
WritingBench: A Comprehensive Benchmark for Generative Writing
xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
ZeroSep: Separate Anything in Audio with Zero Training
Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks
(ends 2:00 PM)
noon
Expo Workshop:
On Device/Edge AI
(ends 1:30 PM)
Expo Workshop:
Multi-Agent Systems in Industry: From Research to Real-World Impact
(ends 1:30 PM)
Expo Workshop:
Using the Virtual Cell Platform to Accelerate Machine Learning in Biology
(ends 1:30 PM)
Expo Workshop:
AI Assistants in the Wild: Agents, Adaptation, and Memory-Augmented Deployment
(ends 1:30 PM)
1 p.m.
Break:
Hosted Lunch
(ends 2:30 PM)
1:30 p.m.
Affinity Workshop:
Indigenous in AI/ML
(ends 5:30 PM)
2 p.m.
Test Of Time:
Test of Time Award
(ends 2:30 PM)
2:30 p.m.
San Diego Invited Talk:
Are We Having the Wrong Nightmares About AI?
Zeynep Tufekci
(ends 3:30 PM)
3:30 p.m.
Oral Session 2A [3:30-4:30]
Agnostic Active Learning Is Always Better Than Passive Learning
Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
(ends 4:30 PM)
Oral Session 2B [3:30-4:30]
PhySense: Sensor Placement Optimization for Accurate Physics Sensing
TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability
OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
(ends 4:30 PM)
Oral Session 2C [3:30-4:30]
A multiscale analysis of mean-field transformers in the moderate interaction regime
The emergence of sparse attention: impact of data distribution and benefits of repetition
From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
(ends 4:30 PM)
Oral Session 2D [3:30-4:30]
PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
(ends 4:30 PM)
Oral Session 2E [3:30-4:30]
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
(ends 4:30 PM)
4:30 p.m.
Expo Talk Panel:
Juries, Not Judges! Industry-Scale Evaluation of Trustworthy AI via Dynamic LLM Panels
(ends 5:30 PM)
Expo Talk Panel:
The Co-X Framework: Versatile AI Agents for Automating and Augmenting Professional Workflows
(ends 5:30 PM)
Expo Talk Panel:
Cosmos World Foundation Model Platform for Physical AI
(ends 5:30 PM)
Break:
Coffee Break
(ends 5:30 PM)
Expo Talk Panel:
Frontier Open-Weight Models: Building Transparent, Secure, and Sovereign AI
(ends 5:30 PM)
Creative AI Session 2 [4:30-7:30]
Chairs: Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian
s 4:30-7:30
[4:30] Assembloid Agency: Unreal Engine API for brain-on-a-chip platforms
[4:30] Best Friends Forever
[4:30] Brushes in Motion: Vector Guided Strokes for Computational Painting
[4:30] Cultural Alien Sampler: Open-ended Art Generation Balancing Originality and Coherence
[4:30] Go witheFlow: Real-time Emotion Driven Audio Effects Modulation
[4:30] Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition
[4:30] Knolling Bot: Teaching Robots the Human Notion of Tidiness
[4:30] Learning to Move with Style: Few-Shot Cross-Modal Style Transfer for Creative Robot Motion Generation
[4:30] LLMscape
[4:30] LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition
[4:30] LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition
[4:30] MCP-Driven Parametric Modeling: Integrating LLM Agents into Architectural and Landscape Design Workflows
[4:30] Music Arena: Live Evaluation for Text-to-Music
[4:30] Musings on AI Muses: Support for Human Creativity
[4:30] My AI Agent Feels Gray on Her Period
[4:30] Painting with Paintings
[4:30] Panel-by-Panel Souls: A Performative Workflow for Expressive Faces in AI-Assisted Manga Creation
[4:30] ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
[4:30] Prompt-Character Divergence: A Responsibility Compass for Human-AI Creative Collaboration
[4:30] ‘Studies for’ : A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model
[4:30] Visualizing Our Changing Earth: A Creative AI Framework for Democratizing Environmental Storytelling Through Satellite Imagery
[4:30] yammer
(ends 7:30 PM)
San Diego Poster Session 2 [4:30-7:30]
Posters 4:30-7:30
$i$MIND: Insightful Multi-subject Invariant Neural Decoding
$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion
3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
3D Interaction Geometric Pre-training for Molecular Relational Learning
3DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
3D Visual Illusion Depth Estimation
3EED: Ground Everything Everywhere in 3D
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
A Black-Box Debiasing Framework for Conditional Sampling
Accelerating data-driven algorithm selection for combinatorial partitioning problems
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
A duality framework for analyzing random feature and two-layer neural networks
Adversarial Robustness of Nonparametric Regression
A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments
A Few Moments Please: Scalable Graphon Learning via Moment Matching
AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications
Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation
AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark
Agnostic Active Learning Is Always Better Than Passive Learning
A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
AlignedGen: Aligning Style Across Generated Images
Aligning Transformers with Continuous Feedback via Energy Rank Alignment
Alignment of Large Language Models with Constrained Learning
All You Need is One: Capsule Prompt Tuning with a Single Vector
AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections
A multiscale analysis of mean-field transformers in the moderate interaction regime
Analogy-based Multi-Turn Jailbreak against Large Language Models
An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks
APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning
Approximating Shapley Explanations in Reinforcement Learning
A Principled Path to Fitted Distributional Evaluation
ARM: Adaptive Reasoning Model
ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
ASGO: Adaptive Structured Gradient Optimization
Ask a Strong LLM Judge when Your Reward Model is Uncertain
A Stable Whitening Optimizer for Efficient Neural Network Training
Asymptotically exact variational flows via involutive MCMC kernels
A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
Attention Mechanism, Max-Affine Partition, and Universal Approximation
Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
A Unified Approach to Submodular Maximization Under Noise
A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random
A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
Avoiding exp(R) scaling in RLHF through Preference-based Exploration
BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning
Bandit and Delayed Feedback in Online Structured Prediction
BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
Bayesian Concept Bottleneck Models with LLM Priors
Better Estimation of the Kullback--Leibler Divergence Between Language Models
Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
Beyond Prediction: Managing the Repercussions of Machine Learning Applications
Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
Beyond Scores: Proximal Diffusion Models
Bézier Splatting for Fast and Differentiable Vector Graphics Rendering
Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints
Bilevel Network Learning via Hierarchically Structured Sparsity
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
Bipolar Self-attention for Spiking Transformers
BitMark: Watermarking Bitwise Autoregressive Image Generative Models
BLEUBERI: BLEU is a surprisingly effective reward for instruction following
Block Coordinate Descent for Neural Networks Provably Finds Global Minima
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem
BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model
BrainODE: Neural Shape Dynamics for Age- and Disease-aware Brain Trajectories
Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity
Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
Bringing SAM to new heights: leveraging elevation data for tree crown segmentation from drone imagery
Buffer layers for Test-Time Adaptation
Building 3D Representations and Generating Motions From a Single Image via Video-Generation
C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
Calibrating Translation Decoding with Quality Estimation on LLMs
CamSAM2: Segment Anything Accurately in Camouflaged Videos
Can Agent Fix Agent Issues?
Can Dependencies Induced by LLM-Agent Workflows Be Trusted?
Can Large Language Models Master Complex Card Games?
Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers
CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization
CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models
CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference
CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization
CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation
Chain of Execution Supervision Promotes General Reasoning in Large Language Models
Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
Characterization and Learning of Causal Graphs from Hard Interventions
CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction
Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
CLEAR: Command Level Annotated Dataset for Ransomware Detection
CLEVER: A Curated Benchmark for Formally Verified Code Generation
ClinBench: A Standardized Multi-Domain Framework for Evaluating Large Language Models in Clinical Information Extraction
C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
CogPhys: Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological Sensing
CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization
COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
Competitive Advantage Attacks to Decentralized Federated Learning
Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
Composition and Alignment of Diffusion Models using Constrained Learning
ComRank: Ranking Loss for Multi-Label Complementary Label Learning
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Conditional Forecasts and Proper Scoring Rules for Reliable and Accurate Performative Predictions
Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation
ConnectomeBench: Can LLMs proofread the connectome?
Constrained Diffusers for Safe Planning and Control
Constrained Optimization From a Control Perspective via Feedback Linearization
Constrained Posterior Sampling: Time Series Generation with Hard Constraints
Contextual Online Pricing with (Biased) Offline Data
Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation
Continuous Concepts Removal in Text-to-image Diffusion Models
Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization
Continuous Subspace Optimization for Continual Learning
Contrastive Self-Supervised Learning As Neural Manifold Packing
Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification
Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models
CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
Corrector Sampling in Language Models
CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection
Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
C-SEO Bench: Does Conversational SEO Work?
Curly Flow Matching for Learning Non-gradient Field Dynamics
Curriculum Abductive Learning
Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization
Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation
Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
Decoupled Entropy Minimization
DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction
Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
Deep Continuous-Time State-Space Models for Marked Event Sequences
Deep learning for continuous-time stochastic control with jumps
Deep Nonlinear Sufficient Dimension Reduction
DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models
Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
Differentiable Hierarchical Visual Tokenization
Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
Differentiation Through Black-Box Quadratic Programming Solvers
Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
Diffusion Federated Dataset
Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
Dimension-adapted Momentum Outscales SGD
Dimensional Collapse in VQVAEs: Evidence and Remedies
Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
DINO-Foresight: Looking into the Future with DINO
DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data
Direct Alignment with Heterogeneous Preferences
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
Discrete Neural Flow Samplers with Locally Equivariant Transformer
Disentangled Representation Learning via Modular Compositional Bias
DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging
Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation
Distillation Robustifies Unlearning
Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks
Distributional LLM-as-a-Judge
Distributionally Robust Performative Optimization
Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
DMWM: Dual-Mind World Model with Long-Term Imagination
Do Language Models Use Their Depth Efficiently?
Don't be lazy: CompleteP enables compute-efficient deep transformers
Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization
DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams
Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
DUO: No Compromise to Accuracy Degradation
Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph
Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention
DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio
Efficient Adaptive Experimentation with Noncompliance
Efficient Adaptive Federated Optimization
Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
Efficiently Scaling LLM Reasoning Programs with Certaindex
Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design
Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
EgoBlind: Towards Egocentric Visual Assistance for the Blind
EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation
ELDET: Early-Learning Distillation with Noisy Labels for Object Detection
Eluder dimension: localise it!
Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
Emerging Risks from Embodied AI Require Urgent Policy Action
EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition
EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis
Energy Landscape-Aware Vision Transformers: Layerwise Dynamics and Adaptive Task-Specific Training via Hopfield States
Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
Enhancing CLIP Robustness via Cross-Modality Alignment
Enhancing Contrastive Learning with Variable Similarity
Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
Entropic Time Schedulers for Generative Diffusion Models
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
Event-Driven Dynamic Scene Depth Completion
Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline
Exact Expressive Power of Transformers with Padding
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
Explainable Reinforcement Learning from Human Feedback to Improve Alignment
Explaining the Law of Supply and Demand via Online Learning
Exploring Landscapes for Better Minima along Valleys
Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
Exploring the Design Space of Diffusion Bridge Models
Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants
Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
Fairshare Data Pricing via Data Valuation for Large Language Models
FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction
Fast exact recovery of noisy matrix from few entries: the infinity norm approach
FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
Fast Zeroth-Order Convex Optimization with Quantum Gradient Methods
FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
Feedback Guidance of Diffusion Models
Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models
Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises
FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
Flow Field Reconstruction with Sensor Placement Policy Learning
FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network
FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
FreeInv: Free Lunch for Improving DDIM Inversion
FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
FRN: Fractal-Based Recursive Spectral Reconstruction Network
From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging
From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models
From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization
FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
Fully Dynamic Algorithms for Chamfer Distance
Functional data analysis for multivariate distributions through Wasserstein slicing
Future Link Prediction Without Memory or Aggregation
Gate to the Vessel: Residual Experts Restore What SAM Overlooks
GauSAM: Contour‑Guided 2D Gaussian Fields for Multi‑Scale Medical Image Segmentation with Segment Anything
Gaussian Processes for Shuffled Regression
Generalization vs Specialization under Concept Shift
Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning
Generalized Contrastive Learning for Universal Multimodal Retrieval
General-Reasoner: Advancing LLM Reasoning Across All Domains
Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks
Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting
Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms
Generative RLHF-V: Learning Principles from Multi-modal Human Preference
Generative Trajectory Stitching through Diffusion Composition
GenSpace: Benchmarking Spatially-Aware Image Generation
GeoClip: Geometry-Aware Clipping for Differentially Private SGD
Geometric Mixture Models for Electrolyte Conductivity Prediction
Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains
GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
Go With the Flow: Fast Diffusion for Gaussian Mixture Models
Gradient Multi-Normalization for Efficient LLM Training
GradMetaNet: An Equivariant Architecture for Learning on Gradients
GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
Greedy Sampling Is Provably Efficient For RLHF
GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
GTR-Loc: Geospatial Text Regularization Assisted Outdoor LiDAR Localization
Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions
GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
Hamiltonian Neural PDE Solvers through Functional Approximation
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity
Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning
Hierarchical Shortest-Path Graph Kernel Network
HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction
High-Order Flow Matching: Unified Framework and Sharp Statistical Rates
HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
How many measurements are enough? Bayesian recovery in inverse problems with general distributions
How Memory in Optimization Algorithms Implicitly Modifies the Loss
How to Scale Second-Order Optimization
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
IF-Guide: Influence Function-Guided Detoxification of LLMs
iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning
Image Editing As Programs with Diffusion Models
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Impartial Selection with Predictions
Improved Algorithms for Fair Matroid Submodular Maximization
Improved Bounds for Swap Multicalibration and Swap Omniprediction
Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits
Improved Scaling Laws in Linear Regression via Data Reuse
Improving Video Generation with Human Feedback
INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Incentivizing LLMs to Self-Verify Their Answers
Incentivizing Truthful Language Models via Peer Elicitation Games
In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
Information-Driven Design of Imaging Systems
Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
InstructRestore: Region-Customized Image Restoration with Human Instructions
Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding
Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation
Interactive Anomaly Detection for Articulated Objects via Motion Anticipation
Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics
IntrinsiX: High-Quality PBR Generation using Image Priors
InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
Isotropic Noise in Stochastic and Quantum Convex Optimization
Is Your Diffusion Model Actually Denoising?
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance
Joint Modeling of fMRI and EEG Imaging Using Ordinary Differential Equation-Based Hypergraph Neural Networks
Joint Relational Database Generation via Graph-Conditional Diffusion Models
KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
Kernel conditional tests from learning-theoretic bounds
Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration
Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
Kernel von Mises Formula of the Influence Function
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
KL Penalty Control via Perturbation for Direct Preference Optimization
Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
KSP: Kolmogorov-Smirnov metric-based Post-Hoc Calibration for Survival Analysis
Kuramoto Orientation Diffusion Models
KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
Language Modeling by Language Models
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?
Latent Principle Discovery for Language Model Self-Improvement
Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
LaViDa: A Large Diffusion Model for Vision-Language Understanding
LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts
LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks
Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
Learning Generalizable Shape Completion with SIM(3) Equivariance
Learning Gradient Boosted Decision Trees with Algorithmic Recourse
Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm
Learning Neural Exposure Fields for View Synthesis
Learning Parameterized Skills from Demonstrations
Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks
Learning to Control Free-Form Soft Swimmers
Learning to Generalize: An Information Perspective on Neural Processes
Learning to Integrate Diffusion ODEs by Averaging the Derivatives
Learning to Rank for In-Context Example Retrieval
Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction
Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions
Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
Length Generalization via Auxiliary Tasks
Listening to the Brain: Multi-Band sEEG Auditory Reconstruction via Dynamic Spatio-Temporal Hypergraphs
Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding
LLM Query Scheduling with Prefix Reuse and Latency Constraints
LLMs Encode Harmfulness and Refusal Separately
Localist Topographic Expert Routing: A Barrel Cortex-Inspired Modular Network for Sensorimotor Processing
Localizing Knowledge in Diffusion Transformers
Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation
Lost in Transmission: When and Why LLMs Fail to Reason Globally
Low-Rank Graphon Learning for Networks
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
LuxDiT: Lighting Estimation with Video Diffusion Transformer
Lyapunov-Stable Adaptive Control for Multimodal Concept Drift
Machine Unlearning under Overparameterization
Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction
Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space
Many LLMs Are More Utilitarian Than One
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Masked Diffusion Models as Energy Minimization
Massive Sound Embedding Benchmark (MSEB)
MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
Maximizing the Value of Predictions in Control: Accuracy Is Not Enough
Measuring AI Ability to Complete Long Software Tasks
Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation
MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation
MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation
MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
Meta-learning how to Share Credit among Macro-Actions
Meta-Learning Objectives for Preference Optimization
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning
metaTextGrad: Automatically optimizing language model optimizers
MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward
Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap
Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
MiNT: Multi-Network Transfer Benchmark for Temporal Graph Learning
MIRA: Medical Time Series Foundation Model for Real-World Health Data
Missing Data Imputation by Reducing Mutual Information with Rectified Flows
Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
MI-TRQR: Mutual Information-Based Temporal Redundancy Quantification and Reduction for Energy-Efficient Spiking Neural Networks
MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation
Mixture-of-Experts Meets In-Context Reinforcement Learning
ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs
MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models
MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
MoCha: Towards Movie-Grade Talking Character Generation
Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving
Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
ModuLM: Enabling Modular and Multimodal Molecular Relational Learning with Large Language Models
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention
Monoculture or Multiplicity: Which Is It?
MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation
MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation
MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration
Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics
MultiScale Contextual Bandits for Long Term Objectives
Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data
Multitask Learning with Stochastic Interpolants
Native-Resolution Image Synthesis
Natural Gradient VI: Guarantees for Non-Conjugate Models
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games
Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets
Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
Nested Learning: The Illusion of Deep Learning Architectures
Network two-sample test for block models
Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem
Neural Correlates of Serial Dependence: Synaptic Short-term Plasticity Orchestrates Repulsion and Attraction
Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
Non-stationary Bandit Convex Optimization: A Comprehensive Study
No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
Normalize Filters! Classical Wisdom for Deep Vision
Object-centric 3D Motion Field for Robot Learning from Human Videos
OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
ODG: Occupancy Prediction Using Dual Gaussians
Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
OligoGym: Curated Datasets and Benchmarks for Oligonucleotide Drug Discovery
OmniBench: Towards The Future of Universal Omni-Language Models
Omnidirectional 3D Scene Reconstruction from Single Image
OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild
Once Upon an Input: Reasoning via Per-Instance Program Synthesis
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
On Learning Verifiers and Implications to Chain-of-Thought Reasoning
Online Optimization for Offline Safe Reinforcement Learning
Online robust locally differentially private learning for nonparametric regression
OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
Online Time Series Forecasting with Theoretical Guarantees
Online Two-Stage Submodular Maximization
On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
On the Coexistence and Ensembling of Watermarks
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
On the Convergence of Single-Timescale Actor-Critic
On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
On the SAC-BL Algorithm for Anomaly Detection
On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels
On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
OpenBox: Annotate Any Bounding Boxes in 3D
OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data
OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges
Optimal Graph Clustering without Edge Density Signals
Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics
Optimization Inspired Few-Shot Adaptation for Large Language Models
Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
Out-of-Distribution Generalized Graph Anomaly Detection with Homophily-aware Environment Mixup
OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
PairEdit: Learning Semantic Variations for Exemplar-based Image Editing
PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms
PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
Parsimonious Predictions for Strategyproof Scheduling
Partial Physics Informed Diffusion Model for Ocean Chlorophyll Concentration Reconstruction
Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
PaTH Attention: Position Encoding via Accumulating Householder Transformations
Pay Attention to Small Weights
PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
Performative Validity of Recourse Explanations
Periodic Skill Discovery
Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
PhySense: Sensor Placement Optimization for Accurate Physics Sensing
PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation
Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
Position: Benchmarking is Broken - Don't Let AI be Its Own Judge
Position: Towards Bidirectional Human-AI Alignment
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
Precise Asymptotics and Refined Regret of Variance-Aware UCB
Prediction-Powered Causal Inferences
Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
Preference-Guided Diffusion for Multi-Objective Offline Optimization
Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
Pre-Trained Policy Discriminators are General Reward Models
PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
Prior Forgetting and In-Context Overfitting
Privacy amplification by random allocation
Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
Private Training Large-scale Models with Efficient DP-SGD
Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing
Probing Hidden Knowledge Holes in Unlearned LLMs
Problem-Parameter-Free Decentralized Bilevel Optimization
Procurement Auctions with Predictions: Improved Frugality for Facility Location
Product Distribution Learning with Imperfect Advice
ProfiX: Improving Profile-Guided Optimization in Compilers with Graph Neural Networks
Provable Watermarking for Data Poisoning Attacks
Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
PSMBench: A Benchmark and Dataset for Evaluating LLMs Extraction of Protocol State Machines from RFC Specifications
QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
Quantifying Uncertainty in the Presence of Distribution Shifts
Quantization-Free Autoregressive Action Transformer
Quantum Doubly Stochastic Transformers
Quantum Speedups for Minimax Optimization and Beyond
RayFusion: Ray Fusion Enhanced Collaborative Visual Perception
RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion
R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
Reconciling Geospatial Prediction and Retrieval via Sparse Representations
Rectifying Shortcut Behaviors in Preference-based Reward Learning
ReDi: Rectified Discrete Flow
Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
Regularized least squares learning with heavy-tailed noise is minimax optimal
ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding
Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
REMI: Reconstructing Episodic Memory During Internally Driven Path Planning
Removing Concepts from Text-to-Image Models with Only Negative Samples
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
REOrdering Patches Improves Vision Models
REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
Repo2Run: Automated Building Executable Environment for Code Repository at Scale
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
RePO: Understanding Preference Learning Through ReLU-Based Optimization
Representational Difference Explanations
Representation Consistency for Accurate and Coherent LLM Answer Aggregation
Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis
Rescaled Influence Functions: Accurate Data Attribution in High Dimension
ReSim: Reliable World Simulation for Autonomous Driving
RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages
RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
Rethinking Evaluation of Infrared Small Target Detection
Rethinking Residual Distribution in Locate-then-Edit Model Editing
Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs
Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
Revisiting Agnostic Boosting
Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees
Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds
Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction
Risk Bounds For Distributional Regression
RNNs perform task computations by dynamically warping neural representations
RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data
Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
Robust learning of halfspaces under log-concave marginals
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
ROGR: Relightable 3D Objects using Generative Relighting
RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net
ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
ROSE: Remove Objects with Side Effects in Videos
RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
Safe and Stable Control via Lyapunov-Guided Diffusion Models
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
SALS: Sparse Attention in Latent Space for KV Cache Compression
SAM2Flow: Interactive Optical Flow Estimation with Dual Memory for in vivo Microcirculation Analysis
Sampling by averaging: A multiscale approach to score estimation
Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
SAS: Simulated Attention Score
Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
Scalable Evaluation and Neural Models for Compositional Generalization
Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
Scalable inference of functional neural connectivity at submillisecond timescales
Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
Scale-invariant attention
Scaling and context steer LLMs along the same computational path as the human brain
Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks
Scaling Image Geo-Localization to Continent Level
Scaling Up Parameter Generation: A Recurrent Diffusion Approach
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection
SeasonBench-EA: A Multi-Source Benchmark for Seasonal Prediction and Numerical Model Post-Processing in East Asia
Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
SegMASt3R: Geometry Grounded Segment Matching
Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting
SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
Self-Challenging Language Model Agents
Self-diffusion for Solving Inverse Problems
Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
Self Iterative Label Refinement via Robust Unlabeled Learning
Self-Refining Language Model Anonymizers via Adversarial Distillation
Self-Verifying Reflection Helps Transformers with CoT Reasoning
seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
Sequentially Auditing Differential Privacy
SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data
Set-LLM: A Permutation-Invariant LLM
Setting $\varepsilon$ is not the Issue in Differential Privacy
ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
Shape it Up! Restoring LLM Safety during Finetuning
SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism
Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings
Sherlock: Self-Correcting Reasoning in Vision-Language Models
ShiQ: Bringing back Bellman to LLMs
Show-o2: Improved Native Unified Multimodal Models
SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting
Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation
Simple Distillation for One-Step Diffusion Models
SimpleStrat: Diversifying Language Model Generation with Stratification
Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
Single-pass Adaptive Image Tokenization for Minimum Program Search
SING: SDE Inference via Natural Gradients
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
Skill-Driven Neurosymbolic State Abstractions
Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators
Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints
SMMILE: An expert-driven benchmark for multimodal medical in-context learning
SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation
Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling
Smoothed Agnostic Learning of Halfspaces over the Hypercube
Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
Smooth Regularization for Efficient Video Recognition
Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations
SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
Solving Inequality Proofs with Large Language Models
Solving Inverse Problems with FLAIR
Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation
SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
SPARTAN: A Sparse Transformer World Model Attending to What Matters
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks
Spiking Neural Networks Need High-Frequency Information
SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding
SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL
SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes
Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
State-Covering Trajectory Stitching for Diffusion Planners
Statistical Inference for Gradient Boosting Regression
Statistics Caching Test-Time Adaptation for Vision-Language Models
Steering When Necessary: Flexible Steering Large Language Models with Backtracking
Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding
Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Strategic Hypothesis Testing
Streaming Attention Approximation via Discrepancy Theory
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
Subgraph Federated Learning via Spectral Methods
SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series
TabDPT: Scaling Tabular Foundation Models on Real Data
Tackling Biased Evaluators in Dueling Bandits
Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
Taming generative video models for zero-shot optical flow extraction
TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
The Best Instruction-Tuning Data are Those That Fit
The Burden of Interactive Alignment with Inconsistent Preferences
The emergence of sparse attention: impact of data distribution and benefits of repetition
The Impact of Coreset Selection on Spurious Correlations and Group Robustness
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
The Parameterized Complexity of Computing the VC-Dimension
The Persistence of Neural Collapse Despite Low-Rank Bias
The Price of Opportunity Fairness in Matroid Allocation Problems
The Rise of Parameter Specialization for Knowledge Storage in Large Language Models
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
Thinkless: LLM Learns When to Think
Think Only When You Need with Large Hybrid-Reasoning Models
Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining
Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
Tight Generalization Bounds for Large-Margin Halfspaces
Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity
Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series
Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography
Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
TopER: Topological Embeddings in Graph Representation Learning
Torch-Uncertainty: Deep Learning Uncertainty Quantification
Toward Interpretable Evaluation Measures for Time Series Segmentation
Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations
Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models
Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
Towards Fully FP8 GEMM LLM Training at Scale
Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes
Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset
Towards Provable Emergence of In-Context Reinforcement Learning
Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology
Towards Robust Zero-Shot Reinforcement Learning
Towards Self-Refinement of Vision-Language Models with Triangular Consistency
Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation
Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models
TRACE: Contrastive learning for multi-trial time series data in neuroscience
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
Training-Free Efficient Video Generation via Dynamic Token Carving
Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
Training-Free Safe Denoisers for Safe Use of Diffusion Models
Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models
Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree
Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
Transferring Causal Effects using Proxies
TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability
Tree of Preferences for Diversified Recommendation
True Impact of Cascade Length in Contextual Cascading Bandits
T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning
UFM: A Simple Path towards Unified Dense Correspondence with Flow
UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss
UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights
UMA: A Family of Universal Models for Atoms
Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data
Understanding Adam Requires Better Rotation Dependent Assumptions
Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness
Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
Under the Shadow: Exploiting Opacity Variation for Fine-grained Shadow Detection
Unified Reinforcement and Imitation Learning for Vision-Language Models
Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization
Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems
Universal Few-shot Spatial Control for Diffusion Models
UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge
Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
Unlocking Multimodal Mathematical Reasoning via Process Reward Model
Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised Learning
Unveiling Concept Attribution in Diffusion Models
UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits
V-CECE: Visual Counterfactual Explanations via Conceptual Edits
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
Versatile Transferable Unlearnable Example Generator
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
VIKING: Deep variational inference with stochastic projections
Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning
VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It
Vision Transformers with Self-Distilled Registers
VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution
VLMs can Aggregate Scattered Training Patches
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion
VMDT: Decoding the Trustworthiness of Video Foundation Models
VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
Wavelet Canonical Coherence for Nonstationary Signals
WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models
When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding
Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
Why Do Some Language Models Fake Alignment While Others Don't?
Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion
Why Popular MOEAs are Popular: Proven Advantages in Approximating the Pareto Front
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
YEAST: Yet Another Sequential Test
Zebra-Llama: Towards Extremely Efficient Hybrid Models
Zero-shot World Models via Search in Memory
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
zip2zip: Inference-Time Adaptive Tokenization via Online Compression
(ends 7:30 PM)
7 p.m.
Reception:
Muslims in ML Reception
(ends 9:00 PM)

THU 4 DEC
7:30 a.m.
Registration Desk
(ends 6:00 PM)
8 a.m.
Break:
Coffee Break
(ends 8:30 AM)
8:30 a.m.
San Diego Invited Talk:
The Art of (Artificial) Reasoning
Yejin Choi
(ends 9:30 AM)
9 a.m.
Affinity Workshop:
Queer in AI
(ends 5:00 PM)
9:30 a.m.
Exhibitor Spot Talks - Session 3 [9:30-4:45]
Talks 9:30-4:42
Optimizing AI Efficiency from Silicon to Model
EMM-1: Expanding embedding space to be multimodal and multilingual
Exhibitor Talk - NEC
Towards reference models for Engineering Abstract
How GM builds Practical AI for the Physical World
Modular Agents and Orchestrated Coordination using Open Agentic Protocols: Foundations for the Next Wave of Agentic AI
Reasoning in Motion: How Agents Learn to Think
Takes two to Tangle: showcasing an experimentation platform with the focus on collaboration and ease of editing
LFM2: Efficient and effective on-device multimodal foundation models.
Exhibitor Talk - NTT
Exhibitor Talk - Biohub Network
Exhibitor Talk - Flow Traders
Exhibitor Talk - Thomson Reuters
ATOM: RBC’s proprietary AI Foundation Model for Financial Services
Exhibitor Talk - Intuit
Exhibitor Talk - Datadog
Exhibitor Talk - Boson.AI
Unify Vector and Relational Search for Smarter, Faster Applications
Semantic latent variables inference for improved generative modeling
Empowering Financial Services with Trustworthy Frontier AI at Wells Fargo
Exhibitor Talk - Lightning AI
Scaling Agentic AI with Compute Orchestration and Local Runners
Building an Open Agentic Future
How to make your AI models faster, smaller, cheaper, greener?
(ends 4:45 PM)
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral Session 3A [10:00-11:00]
Identifiability of Deep Polynomial Neural Networks
Depth-Bounds for Neural Networks via the Braid Arrangement
Learning Linear Attention in Polynomial Time
(ends 11:00 AM)
Oral Session 3B [10:00-11:00]
ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts
Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
(ends 11:00 AM)
Oral Session 3C [10:00-11:00]
Auto-Compressing Networks
Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
(ends 11:00 AM)
Oral Session 3D [10:00-11:00]
State Entropy Regularization for Robust Reinforcement Learning
A Clean Slate for Offline Reinforcement Learning
Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
(ends 11:00 AM)
Oral Session 3E [10:00-11:00]
Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
More effort is needed to protect pedestrian privacy in the era of AI
Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"
(ends 11:00 AM)
11 a.m.
San Diego Poster Session 3 [11:00-2:00]
Posters 11:00-2:00
$\mu$PC: Scaling Predictive Coding to 100+ Layer Networks
$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
3D Human Pose Estimation with Muscles
A$^3$E: Towards Compositional Model Editing
A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference
Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
Accelerating Feature Conformal Prediction via Taylor Approximation
Accelerating Parallel Diffusion Model Serving with Residual Compression
Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space
Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
A Clean Slate for Offline Reinforcement Learning
A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
A compressive-expressive communication framework for compositional representations
A Controllable Examination for Long-Context Language Models
A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
Adaptive Latent-Space Constraints in Personalized Federated Learning
Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction
Additive Models Explained: A Computational Complexity Approach
A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
AdvPrefix: An Objective for Nuanced LLM Jailbreaks
A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models
AGI-Elo: How Far Are We From Mastering A Task?
Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
AI-Generated Video Detection via Perceptual Straightening
AI-Researcher: Autonomous Scientific Innovation
Aligning Text-to-Image Diffusion Models to Human Preference by Classification
AliO: Output Alignment Matters in Long-Term Time Series Forecasting
Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection
AlphaFold Database Debiasing for Robust Inverse Folding
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
Ambient Proteins - Training Diffusion Models on Noisy Structures
AmorLIP: Efficient Language-Image Pretraining via Amortization
Amortized Sampling with Transferable Normalizing Flows
Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
Analyzing the Power of Chain of Thought through Memorization Capabilities
An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
Anatomically inspired digital twins capture hierarchical object representations in visual cortex
A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
Angular Steering: Behavior Control via Rotation in Activation Space
Anytime-valid, Bayes-assisted, Prediction-Powered Inference
A Physics-preserved Transfer Learning Method for Differential Equations
A Practical Guide for Incorporating Symmetry in Diffusion Policy
ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
Are Large Language Models Sensitive to the Motives Behind Communication?
ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
A solvable model of learning generative diffusion: theory and insights
A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
A Sustainable AI Economy Needs Data Deals That Work for Generators
Asymptotic theory of SGD with a general learning-rate
AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
Attention-based clustering
Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA
A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning
Auto-Compressing Networks
AutoData: A Multi-Agent System for Open Web Data Collection
Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection
Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling
AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web
Balancing Gradient and Hessian Queries in Non-Convex Optimization
BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation
BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks
Benign Overfitting in Single-Head Attention
Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
Beyond Last-Click: An Optimal Mechanism for Ad Attribution
Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification
Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics
Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
BrainFlow: A Holistic Pathway of Dynamic Neural System on Manifold
Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language Modeling
BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals
BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
Bridging the Gap Between Cross-Domain Theory and Practical Application: A Case Study on Molecular Dissolution
C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing
Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
Can NeRFs "See" without Cameras?
Causal Climate Emulation with Bayesian Filtering
Causal LLM Routing: End-to-End Regret Minimization from Observational Data
CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies
CF-VLM：CounterFactual Vision-Language Fine-tuning
CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research
Channel Matters: Estimating Channel Influence for Multivariate Time Series
Characterizing control between interacting subsystems with deep Jacobian estimation
Characterizing the Expressivity of Fixed-Precision Transformer Language Models
ChatbotID: Identifying Chatbots with Granger Causality Test
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code
Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing
ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
Clustering via Hedonic Games: New Concepts and Algorithms
C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
Codifying Character Logic in Role-Playing
CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification
Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks
Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration
Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics
ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning
Compositional Reasoning with Transformers, RNNs, and Chain of Thought
Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers
Conditional Diffusion Anomaly Modeling on Graphs
Conformal Online Learning of Deep Koopman Linear Embeddings
Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization
Connecting Neural Models Latent Geometries with Relative Geodesic Representations
Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations
ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks
Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
ConTextTab: A Semantics-Aware Tabular In-Context Learner
Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time
Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
Continuous Diffusion Model for Language Modeling
Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees
ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts
Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration
Controlled Visual Hallucination via Thalamus-Driven Decoupling Network for Domain Adaptation of Black-Box Predictors
Controlling The Spread of Epidemics on Networks with Differential Privacy
ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation
Correlated Low-Rank Adaptation for ConvNets
Cost-aware LLM-based Online Dataset Annotation
Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
Counterfactual Image Editing with Disentangled Causal Latent Space
Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
Cross City Traffic Flow Generation via Retrieval Augmented Diffusion Model
CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL
CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning
Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation
CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
DAMamba: Vision State Space Model with Dynamic Adaptive Scan
DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
Data-Driven Performance Guarantees for Classical and Learned Optimizers
Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
DataSIR: A Benchmark Dataset for Sensitive Information Recognition
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
DAVE: Diagnostic benchmark for Audio Visual Evaluation
DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing
DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real Transfer
Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
DeltaFormer: Unlock the state space of Transformer
DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
Delving into Large Language Models for Effective Time-Series Anomaly Detection
Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer
Dense SAE Latents Are Features, Not Bugs
DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
Depth-Bounds for Neural Networks via the Braid Arrangement
Depth-Supervised Fusion Network for Seamless-Free Image Stitching
Detecting High-Stakes Interactions with Activation Probes
DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
DGCBench: A Deep Graph Clustering Benchmark
Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
Differentially Private Quantiles with Smaller Error
Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
DIFFSSR: Stereo Image Super-resolution Using Differential Transformer
Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
Diffusion on Demand: Selective Caching and Modulation for Efficient Generation
Dimensionality Mismatch Between Brains and Artificial Neural Networks
DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
Disentangling Hyperedges through the Lens of Category Theory
Disentangling misreporting from genuine adaptation in strategic settings: a causal approach
Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept Atoms
Distance-informed Neural Processes
Distilling LLM Agent into Small Models with Retrieval and Code Tools
Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection
DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing
DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT
DyFlow: Dynamic Workflow Framework for Agentic Reasoning
Dynamic Algorithm for Explainable $k$-medians Clustering under $\ell_p$ Norm
Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
Dynamic Focused Masking for Autoregressive Embodied Occupancy Prediction
Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
EchoShot: Multi-Shot Portrait Video Generation
EditInfinity: Image Editing with Binary-Quantized Generative Models
Effects of Dropout on Performance in Long-range Graph Learning Tasks
Efficient Quadratic Corrections for Frank-Wolfe Algorithms
Efficient Rectified Flow for Image Fusion
Efficient semantic uncertainty quantification in language models via diversity-steered sampling
Efficient Training of Minimal and Maximal Low-Rank Recurrent Neural Networks
Efficient Verified Unlearning For Distillation
Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models
Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
Emergence and scaling laws in SGD learning of shallow neural networks
Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
Enhancing Graph Classification Robustness with Singular Pooling
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators
EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network
Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
Estimation of Treatment Effects in Extreme and Unobserved Data
Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting
EuroSpeech: A Multilingual Speech Corpus
Evaluating Program Semantics Reasoning with Type Inference in System $F$
EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation
EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
Explaining and Mitigating Crosslingual Tokenizer Inequities
Exploiting Dynamic Sparsity in Einsum
Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior
Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
Exploring Structural Degradation in Dense Representations for Self-supervised Learning
Exponential Convergence Guarantees for Iterative Markovian Fitting
EyeBench: Predictive Modeling from Eye Movements in Reading
FACE: Faithful Automatic Concept Extraction
FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
Fairness-aware Anomaly Detection via Fair Projection
Fairness-Regularized Online Optimization with Switching Costs
FAIR Universe HiggsML Uncertainty Dataset and Competition
FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing
FEAT: Free energy Estimators with Adaptive Transport
FedEL: Federated Elastic Learning for Heterogeneous Devices
FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning
Feedback-Aware MCTS for Goal-Oriented Information Seeking
Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization
FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
Fisher meets Feynman: score-based variational inference with a product of experts
Fixed-Point RNNs: Interpolating from Diagonal to Dense
FlashBias: Fast Computation of Attention with Bias
Flash Invariant Point Attention
Flat Channels to Infinity in Neural Loss Landscapes
Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
Flattening Hierarchies with Policy Bootstrapping
Flexible inference for animal learning rules using neural networks
Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
Flexible MOF Generation with Torsion-Aware Flow Matching
FlowFeat: Pixel-Dense Embedding of Motion Profiles
FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training
Flux4D: Flow-based Unsupervised 4D Reconstruction
Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation
Fortifying Time Series: DTW-Certified Robust Anomaly Detection
Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition
Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning
FP4 All the Way: Fully Quantized Training of Large Language Models
FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
From Bytes to Ideas: Language Modeling with Autoregressive U-Nets
From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos
From Pose to Muscle: Multimodal Learning for Piano Hand Muscle Electromyography
From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps
From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
Gains: Fine-grained Federated Domain Adaptation in Open Set
GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation
GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
Generalized Top-k Mallows Model for Ranked Choices
Generalizing while preserving monotonicity in comparison-based preference learning models
Generative Pre-trained Autoregressive Diffusion Transformer
Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
GlobalTomo: A global dataset for physics-ML seismic wavefield modeling and FWI
Glocal Information Bottleneck for Time Series Imputation
GOATex: Geometry & Occlusion-Aware Texturing
GoRA: Gradient-driven Adaptive Low Rank Adaptation
GPO: Learning from Critical Steps to Improve LLM Reasoning
Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
Gradient-Guided Epsilon Constraint Method for Online Continual Learning
Graph Alignment via Birkhoff Relaxation
Graph Data Selection for Domain Adaptation: A Model-Free Approach
GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic Algorithms
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection
GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis
Heterogeneous Adversarial Play in Interactive Environments
Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell data
HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
Horizon Reduction Makes RL Scalable
How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
Human-assisted Robotic Policy Refinement via Action Preference Optimization
Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems
Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary
Hybrid Latent Representations for PDE Emulation
Hyperbolic Dataset Distillation
Hypergraph-Enhanced Contrastive Learning for Multi-View Clustering with Hyper-Laplacian Regularization
HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities
IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning
IBGS: Image-Based Gaussian Splatting
Identifiability of Deep Polynomial Neural Networks
Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Image Stitching in Adverse Condition: A Bidirectional-Consistency Learning Framework and Benchmark
Impact of Layer Norm on Memorization and Generalization in Transformers
Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach
Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
Improved Robust Estimation for Erdős-Rényi Graphs: The Sparse Regime and Optimal Breakdown Point
Improving Decision Trees through the Lens of Parameterized Local Search
Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
Improving Formal Reasoning of Transformer with State Stack
Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning
Improving Monte Carlo Tree Search for Symbolic Regression
Improving Regret Approximation for Unsupervised Dynamic Environment Generation
Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
Improving Time Series Forecasting via Instance-aware Post-hoc Revision
Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
Inference-time Alignment in Continuous Space
Inference-Time Hyper-Scaling with KV Cache Compression
InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Influence Guided Context Selection for Effective Retrieval-Augmented Generation
InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
Information-Theoretic Discrete Diffusion
Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
Instant4D: 4D Gaussian Splatting in Minutes
Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
Interpretable Global Minima of Deep ReLU Neural Networks on Sequentially Separable Data
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models
Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis
IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
Is Grokking a Computational Glass Relaxation?
Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model
KAIROS: Scalable Model-Agnostic Data Valuation
Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
Knowledge Distillation Detection for Open-weights Models
KScope: A Framework for Characterizing the Knowledge Status of Language Models
KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities
Language Models (Mostly) Know When to Stop Reading
Language Ranker: A Lightweight Ranking framework for LLM Decoding
Large Language Models as End-to-end Combinatorial Optimization Solvers
Large Language Models Miss the Multi-agent Mark
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing
Learnable Sampler Distillation for Discrete Diffusion Models
Learning Counterfactual Outcomes Under Rank Preservation
Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics
Learning Dense Hand Contact Estimation from Imbalanced Data
Learning Expandable and Adaptable Representations for Continual Learning
Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
Learning from Delayed Feedback in Games via Extra Prediction
Learning in Compact Spaces with Approximately Normalized Transformer
Learning Interactive World Model for Object-Centric Reinforcement Learning
Learning Linear Attention in Polynomial Time
Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
Learning Multi-Source and Robust Representations for Continual Learning
Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free
Learning “Partner-Aware” Collaborators in Multi-Party Collaboration
Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach
Learning Skill-Attributes for Transferable Assessment in Video
Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
Learning to Factorize Spatio-Temporal Foundation Models
Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
Learning to Generate Human-Human-Object Interactions from Textual Descriptions
Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks
Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
Let a Neural Network be Your Invariant
Leveraging Conditional Dependence for Efficient World Model Denoising
LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
Linearization Explains Fine-Tuning in Large Language Models
LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans
LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models
LLM Layers Immediately Correct Each Other
LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation
LLM Safety Alignment is Divergence Estimation in Disguise
Local-Global Associative Frames for Symmetry-Preserving Crystal Structure Modeling
LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
Look-Ahead Reasoning on Learning Platforms
Looking Into the Water by Unsupervised Learning of the Surface Shape
MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
Mamba Modulation: On the Length Generalization of Mamba Models
MaNGO — Adaptable Graph Network Simulators via Meta-Learning
Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
MathArena: Evaluating LLMs on Uncontaminated Math Competitions
Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training
Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
Mellow: a small audio language model for reasoning
Memorization in Graph Neural Networks
Memory-Enhanced Neural Solvers for Routing Problems
MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees
Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
Metritocracy: Representative Metrics for Lite Benchmarks
Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans
MIHC: Multi-View Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction
Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
Minimax Adaptive Online Nonparametric Regression over Besov spaces
MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning
Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference
MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking
MMPB: It’s Time for Multi-Modal Personalization
Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors
Modeling Neural Activity with Conditionally Linear Dynamical Systems
MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
Monitoring Risks in Test-Time Adaptation
MoonCast: High-Quality Zero-Shot Podcast Generation
MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation
More effort is needed to protect pedestrian privacy in the era of AI
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation
MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Multi-Class Support Vector Machine with Differential Privacy
Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare
Multilevel neural simulation-based inference
Multimodal Causal Reasoning for UAV Object Detection
Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables
Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
MUniverse: A Simulation and Benchmarking Suite for Motor Unit Decomposition
MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering
MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
Neural Entropy
Neural Evolution Strategy for Black-box Pareto Set Learning
Neurons as Detectors of Coherent Sets in Sensory Dynamics
Neurosymbolic Diffusion Models
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
Non-equilibrium Annealed Adjoint Sampler
Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shift with Unlabeled Data
Non-Line-of-Sight 3D Reconstruction with Radar
Non-rectangular Robust MDPs with Normed Uncertainty Sets
Non-Stationary Structural Causal Bandits
Non-Uniform Multiclass Learning with Bandit Feedback
Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
NUTS: Eddy-Robust Reconstruction of Surface Ocean Nutrients via Two-Scale Modeling
OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels
Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
OmniSVG: A Unified Scalable Vector Graphics Generation Model
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation
On Agnostic PAC Learning in the Small Error Regime
OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
One-Step Diffusion-Based Image Compression with Semantic Distillation
One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
On Fairness of Unified Multimodal Large Language Model for Image Generation
Online Feedback Efficient Active Target Discovery in Partially Observable Environments
Online Portfolio Selection with ML Predictions
Online Strategic Classification With Noise and Partial Feedback
On the Edge of Memorization in Diffusion Models
On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks
On the Hardness of Conditional Independence Testing In Practice
On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting
On the Loss of Context Awareness in General Instruction Fine-tuning
On the sample complexity of semi-supervised multi-objective learning
On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection
OpenCUA: Open Foundations for Computer-Use Agents
OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
Optimal Adjustment Sets for Nonparametric Estimation of Weighted Controlled Direct Effect
Optimal Best Arm Identification under Differential Privacy
Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff
Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints
Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMs
Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
Parameter Dynamics of Online Machine Learning and Test-time Adaptation
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
Partial Correlation Network Estimation by Semismooth Newton Methods
Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
Path-specific effects for pulse-oximetry guided decisions in critical care
Per-Architecture Training-Free Metric Optimization for Neural Architecture Search
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing
Photography Perspective Composition: Towards Aesthetic Perspective Recommendation
Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
PID-controlled Langevin Dynamics for Faster Sampling on Generative Models
PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting
Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
Planning with Quantized Opponent Models
PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series
PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Policy Optimized Text-to-Image Pipeline Design
PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors
Polyline Path Masked Attention for Vision Transformer
Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance
Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
Position: Require Frontier AI Labs To Release Small "Analog" Models
Power Lines: Scaling laws for weight decay and batch size in LLM pre-training
Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
Predicting Functional Brain Connectivity with Context-Aware Deep Neural Networks
Preference-driven Knowledge Distillation for Few-shot Node Classification
PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
Principled Long-Tailed Generative Modeling via Diffusion Models
Private Statistical Estimation via Truncation
Private Zeroth-Order Optimization with Public Data
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
Progress Reward Model for Reinforcement Learning via Large Language Models
Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
Prompt-guided Disentangled Representation for Action Recognition
Prompting as Scientific Inquiry
Protein Design with Dynamic Protein Vocabulary
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
Provable Scaling Laws for the Test-Time Compute of Large Language Models
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Pseudo-Riemannian Graph Transformer
PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks
Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
PyraMotion: Attentional Pyramid-Structured Motion Integration for Co-Speech 3D Gesture Synthesis
Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
Quantifying Cross-Modality Memorization in Vision-Language Models
Quantifying Elicitation of Latent Capabilities in Language Models
Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations
QuARI: Query Adaptive Retrieval Improvement
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
QUT-DV25: A Dataset for Dynamic Analysis of Next-Gen Software Supply Chain Attacks
R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO
RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis
Random Forest Autoencoders for Guided Representation Learning
Random Search Neural Networks for Efficient and Expressive Graph Learning
Rao-Blackwellised Reparameterisation Gradients
Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow
RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases
Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"
Real-World Reinforcement Learning of Active Perception Behaviors
Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation
Reconstruction and Secrecy under Approximate Distance Queries
Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning
REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive Dataset
Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
Reinforcement Learning with Action Chunking
Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach
Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
Rethinking Approximate Gaussian Inference in Classification
Rethinking Tokenized Graph Transformers for Node Classification
Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
RF-Agent: Automated Reward Function Design via Language Agent Tree Search
RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching
RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
RLVR-World: Training World Models with Reinforcement Learning
Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
Robust Explanations of Graph Neural Networks via Graph Curvatures
Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
Robust Minimax Boosting with Performance Guarantees
Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets
Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
SAFE: Multitask Failure Detection for Vision-Language-Action Models
SafeVid: Toward Safety Aligned Video Large Multimodal Models
SAINT: Sequence-Aware Integration for Spatial Transcriptomics Multi-View Clustering
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
Sampling 3D Molecular Conformers with Diffusion Transformers
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
Scalable Exploration via Ensemble++
Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
Scalable Policy-Based RL Algorithms for POMDPs
Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
Scaling Embedding Layers in Language Models
Scaling Laws for Optimal Data Mixtures
Scaling Speculative Decoding with Lookahead Reasoning
SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies
Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers
SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision
Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective
Seg-VAR:Image Segmentation with Visual Autoregressive Modeling
Sekai: A Video Dataset towards World Exploration
Selective Learning for Deep Time Series Forecasting
Selective Omniprediction and Fair Abstention
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential
Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis
SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors
SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval
SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification
ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
SHGR: A Generalized Maximal Correlation Coefficient
Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Sign-In to the Lottery: Reparameterizing Sparse Training
Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis
Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful
Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
Smooth Quadratic Prediction Markets
SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era.
Soft Task-Aware Routing of Experts for Equivariant Representation Learning
Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes
Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models
SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling
Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited
Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
Spectral Analysis of Diffusion Models with Application to Schedule Design
Spectral Conditioning of Attention Improves Transformer Performance
Spectral Estimation with Free Decompression
Spectral Learning for Infinite-Horizon Average-Reward POMDPs
SpiderSolver: A Geometry-Aware Transformer for Solving PDEs on Complex Geometries
Spike-timing-dependent Hebbian learning as noisy gradient descent
SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
STAR: A Benchmark for Astronomical Star Fields Super-Resolution
STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
State Entropy Regularization for Robust Reinforcement Learning
StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case
Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
SteerConf: Steering LLMs for Confidence Elicitation
Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
Strategic Classification with Non-Linear Classifiers
Stratify or Die: Rethinking Data Splits in Image Segmentation
Streaming Stochastic Submodular Maximization with On-Demand User Requests
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
SuperCLIP: CLIP with Simple Classification Supervision
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
System-Embedded Diffusion Bridge Models
TabArena: A Living Benchmark for Machine Learning on Tabular Data
Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation
TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics
Tail-Optimized Caching for LLM Inference
Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
Temporal-Difference Variational Continual Learning
Test3R: Learning to Reconstruct 3D at Test Time
Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
Text to Sketch Generation with Multi-Styles
The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
The Leaderboard Illusion
The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning
The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
The Primacy of Magnitude in Low-Rank Adaptation
The Structure of Relation Decoding Linear Operators in Large Language Models
Think before Recommendation: Autonomous Reasoning-enhanced Recommender
Thinker: Learning to Think Fast and Slow
Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
Thompson Sampling in Function Spaces via Neural Operators
Thought Communication in Multiagent Collaboration
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
Time-Embedded Algorithm Unrolling for Computational MRI
Timely Clinical Diagnosis through Active Test Selection
Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Topology-Aware Conformal Prediction for Stream Networks
Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper
Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation
Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis
Toward Relative Positional Encoding in Spiking Transformers
Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery
Towards General Continuous Memory for Vision-Language Models
Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors
Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
Towards Understanding Camera Motions in Any Video
Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks
Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning
Training a Scientific Reasoning Model for Chemistry
Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
Training-Free Constrained Generation With Stable Diffusion Models
Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks
Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression
Transferring Linear Features Across Language Models With Model Stitching
TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
Traversal Verification for Speculative Tree Decoding
TreeGen: A Bayesian Generative Model for Hierarchies
Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detection
TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation
Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion
UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
UFT: Unifying Supervised and Reinforcement Fine-Tuning
Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling
Uncertainty Estimation by Flexible Evidential Deep Learning
Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
Understanding Contrastive Learning via Gaussian Mixture Models
Understanding Data Influence in Reinforcement Finetuning
Understanding Differential Transformer Unchains Pretrained Self-Attentions
Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
Unified all-atom molecule generation with neural fields
UniFoil: A Universal Dataset of Airfoils in Transitional and Turbulent Regimes for Subsonic and Transonic Flows
Unifying Proportional Fairness in Centroid and Non-Centroid Clustering
UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization
UniTok: a Unified Tokenizer for Visual Generation and Understanding
Universal Causal Inference in a Topos
Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
Unsupervised Trajectory Optimization for 3D Registration in Serial Section Electron Microscopy using Neural ODEs
Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization
Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random
Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model
Unveiling Transformer Perception by Exploring Input Manifolds
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
VarFlow: Proper Scoring-Rule Diffusion Distillation via Energy Matching
Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation
Variational Learning Finds Flatter Solutions at the Edge of Stability
Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action
Variational Supervised Contrastive Learning
VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning
VERA: Variational Inference Framework for Jailbreaking Large Language Models
Vertical Federated Feature Screening
VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
Video-R1: Reinforcing Video Reasoning in MLLMs
Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
Video World Models with Long-term Spatial Memory
ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models
VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification
WebDancer: Towards Autonomous Information Seeking Agency
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
We Should Chart an Atlas of All the World's Models
What are you sinking? A geometric approach on attention sink
What Can RL Bring to VLA Generalization? An Empirical Study
What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
When and how can inexact generative models still sample from the data manifold?
When Are Concepts Erased From Diffusion Models?
When Can Model-Free Reinforcement Learning be Enough for Thinking?
When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions
Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts
Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
Why Do Multi-Agent LLM Systems Fail?
WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild
Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You
World Models Should Prioritize the Unification of Physical and Social Dynamics
Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models
You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering
Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention
Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling
Zeroth-Order Optimization Finds Flat Minima
(ends 2:00 PM)
Creative AI Session 3 [11:00-2:00]
Chairs: Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian
s 11:00-2:00
[11:00] 8bit-GPT: Exploring Human-AI Interaction on Obsolete Macintosh Operating Systems
[11:00] A(I)nimism: Re-enchanting the World Through AI-Mediated Object Interaction
[11:00] Artism: AI-Driven Dual-Engine System for Art Generation and Critique
[11:00] ArtPeer: Artistic Alignment via Reflection-based Prompt Evolution with Simulated Artist
[11:00] AugTwins
[11:00] CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
[11:00] Encoding Values: Injecting Morality into Machines via Prompt-Conditioned Moral Frames
[11:00] Experiencing of Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art
[11:00] Exploring Human-AI Conceptual Alignment through the Prism of Chess
[11:00] Gaze to the Stars: AI and Public Art from Personal Affect and Collective Empathy
[11:00] Gaze to the Stars: AI, Storytelling and Public Art
[11:00] Human-AI Co-Development of a Geometric Algorithm for Infinite Shuriken Artwork Design Generation
[11:00] Large Language Label
[11:00] Live Music Models
[11:00] MambaKit: Towards Modular Intelligence - Cognitive Scaffolding in Next-Generation Drum Synthesis
[11:00] Neural Palate Kueh
[11:00] Opt-In Art: Learning Art Styles Only from Few Examples
[11:00] Pareiduo: A Human–LLM Dialogue in Sand
[11:00] Possible You: AI-Generated Digital Twins as Creative Mirrors for Future Self Modeling
[11:00] princi/pal: A Moral Dilemma Tamagotchi Game
[11:00] ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems
[11:00] Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud
[11:00] Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art
[11:00] Supporting Creative Ownership through Deep Learning-Based Music Variation
(ends 2:00 PM)
1 p.m.
Break:
Hosted Lunch
(ends 2:30 PM)
2:30 p.m.
San Diego Invited Talk:
On the Science of “Alien Intelligences”: Evaluating Cognitive Capabilities in Babies, Animals, and AI
Melanie Mitchell
(ends 3:30 PM)
3:30 p.m.
Oral Session 4A [3:30-4:30]
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Superposition Yields Robust Neural Scaling
(ends 4:30 PM)
Oral Session 4B [3:30-4:30]
In Search of Adam’s Secret Sauce
Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
(ends 4:30 PM)
Oral Session 4C [3:30-4:30]
MaxSup: Overcoming Representation Collapse in Label Smoothing
Advancing Expert Specialization for Better MoE
Learning to Learn with Contrastive Meta-Objective
(ends 4:30 PM)
Oral Session 4D [3:30-4:30]
Exploring Diffusion Transformer Designs via Grafting
Deep Compositional Phase Diffusion for Long Motion Sequence Generation
Mean Flows for One-step Generative Modeling
(ends 4:30 PM)
Oral Session 4E Position Paper Track Panels [3:30-4:30]
Position Paper Panel: Machine Unlearning and Privacy
Position Paper Panel: Conference Critique
(ends 4:30 PM)
4:30 p.m.
Break:
Coffee Break
(ends 5:30 PM)
San Diego Poster Session 4 [4:30-7:30]
Posters 4:30-7:30
$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
Accident Anticipation via Temporal Occurrence Prediction
Accurate and Efficient Low-Rank Model Merging in Core Space
Accurately Predicting Protein Mutational Effects via a Hierarchical Many-Body Attention Network
AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities
A CLT for Polynomial GNNs on Community-Based Graphs
Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
Activation-Guided Consensus Merging for Large Language Models
AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
Adaptive Data-Borrowing for Improving Treatment Effect Estimation using External Controls
Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation
Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition
A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
Adjusted Count Quantification Learning on Graphs
Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
Advancing Expert Specialization for Better MoE
Advancing Interpretability of CLIP Representations with Concept Surrogate Model
Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
A Generalist Intracortical Motor Decoder
A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
A Geometrical Analysis of Kernel Ridge Regression and its Applications
A Geometric Analysis of PCA
Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
AI Debate Aids Assessment of Controversial Claims
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows
ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Aligning Compound AI Systems via System-level DPO
Align Your Flow: Scaling Continuous-Time Flow Map Distillation
All that structure matches does not glitter
Ambient Diffusion Omni: Training Good Models with Bad Data
A-Mem: Agentic Memory for LLM Agents
A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
Amortized Variational Transdimensional Inference
Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process
An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds
Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
Anchor-based Maximum Discrepancy for Relative Similarity Testing
An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
Antidistillation Sampling
Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses
A Partition Cover Approach to Tokenization
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
A Plug-and-Play Query Synthesis Active Learning Framework for Neural PDE Solvers
Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
ARIA: Training Language Agents with Intention-driven Reward Aggregation
ASDSV: Multimodal Generation Made Efficient with Approximate Speculative Diffusion and Speculative Verification
A Signed Graph Approach to Understanding and Mitigating Oversmoothing
A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization
A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation
Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds
Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules
Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks
A Temporal Difference Method for Stochastic Continuous Dynamics
Attention (as Discrete-Time Markov) Chains
Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings
Attribution-Driven Adaptive Token Pruning for Transformers
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
AutoEdit: Automatic Hyperparameter Tuning for Image Editing
AutoJudge: Judge Decoding Without Manual Annotation
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
Axial Neural Networks for Dimension-Free Foundation Models
Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
Balanced Conic Rectified Flow
Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning
Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble
BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading
Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation
Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
Bernstein–von Mises for Adaptively Collected Data
Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis
Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation
Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
BioCG: Constrained Generative Modeling for Biochemical Interaction Prediction
BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks
Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
Blackbox Model Provenance via Palimpsestic Membership Inference
BlurDM: A Blur Diffusion Model for Image Deblurring
BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLM
Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains
Bridging the gap to real-world language-grounded visual concept learning
Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
CALM: Culturally Self-Aware Language Models
CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
CAMO: Convergence-Aware Multi-Fidelity Bayesian Optimization
Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
Can We Infer Confidential Properties of Training Data from LLMs?
CarbonGlobe: A Global-Scale, Multi-Decade Dataset and Benchmark for Carbon Forecasting in Forest Ecosystems
CARE: Decoding-Time Safety Alignment via Rollback and Introspection Intervention
Causal Discovery over Clusters of Variables in Markovian Systems
Causally Reliable Concept Bottleneck Models
CellVerse: Do Large Language Models Really Understand Cell Biology?
Chain-of-Model Learning for Language Model
Chain-of-Retrieval Augmented Generation
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
Checklists Are Better Than Reward Models For Aligning Language Models
ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions
Class conditional conformal prediction for multiple inputs by p-value aggregation
Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation
CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates
Combining Cost Constrained Runtime Monitors for AI Safety
Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games
Complexity Scaling Laws for Neural Models using Combinatorial Optimization
Composing Linear Layers from Irreducibles
Compositional Monte Carlo Tree Diffusion for Extendable Planning
Concentration and excess risk bounds for imbalanced classification with synthetic oversampling
ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text
Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
Consistency Conditions for Differentiable Surrogate Losses
Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
Constrained Best Arm Identification
Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
Continual Release Moment Estimation with Differential Privacy
Continuous Thought Machines
Contribution of task-irrelevant stimuli to drift of neural representations
Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
Convergence Rates of Constrained Expected Improvement
Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
Correcting misinterpretations of additive models
Correlation Dimension of Autoregressive Large Language Models
COS3D: Collaborative Open-Vocabulary 3D Segmentation
Cost-Aware Contrastive Routing for LLMs
CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
CoUn: Empowering Machine Unlearning via Contrastive Learning
Counterfactual reasoning: an analysis of in-context emergence
Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization
CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic
Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
CrypticBio: A Large Multimodal Dataset for Visually Confusing Species
CSGO: Content-Style Composition in Text-to-Image Generation
Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization
DAAC: Discrepancy-Aware Adaptive Contrastive Learning for Medical Time series
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
Dataset Distillation for Pre-Trained Self-Supervised Vision Models
DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space
DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting
Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
DecompNet: Enhancing Time Series Forecasting Models with Implicit Decomposition
Decomposing motor units through elimination for real-time intention driven assistive neurotechnology
DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis
Deep Compositional Phase Diffusion for Long Motion Sequence Generation
Deep Legendre Transform
Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences
Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Deno-IF: Unsupervised Noisy Visible and Infrared Image Fusion Method
Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection
Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding
DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces
DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy
DGH: Dynamic Gaussian Hair
DiffBreak: Is Diffusion-Based Purification Robust?
Differentially Private Gomory-Hu Trees
Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
Diffusion Transformers as Open-World Spatiotemporal Foundation Models
Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling
Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search
Distances for Markov chains from sample streams
Distributional Autoencoders Know the Score
Distributionally Robust Feature Selection
Diversity-Aware Policy Optimization for Large Language Model Reasoning
DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
Document Summarization with Conformal Importance Guarantees
Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
DPA: A one-stop metric to measure bias amplification in classification datasets
DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs
DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints
DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance
Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
Dynamic Shadow Unveils Invisible Semantics for Video Outpainting
Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning
DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
DynaPhArM: Adaptive and Physics-Constrained Modeling for Target-Drug Complexes with Drug-Specific Adaptations
Dyn-O: Building Structured World Models with Object-Centric Representations
E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
EA3D: Online Open-World 3D Object Extraction from Streaming Videos
Each Complexity Deserves a Pruning Policy
EconGym: A Scalable AI Testbed with Diverse Economic Tasks
EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting
EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
Efficient Bayesian Experiment Design with Equivariant Networks
Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
Efficient Low Rank Attention for Long-Context Inference in Large Language Models
Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks
Efficient Multimodal Dataset Distillation via Generative Models
EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
Elastic ViTs from Pretrained Models without Retraining
Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
Emergent Temporal Correspondences from Video Diffusion Transformers
Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation
Enforcing convex constraints in Graph Neural Networks
Enhancing 3D Reconstruction for Dynamic Scenes
Enhancing Bioactivity Prediction via Spatial Emptiness Representation of Protein-ligand Complex and Union of Multiple Pockets
Enhancing Deep Batch Active Learning for Regression with Imperfect Data Guided Selection
Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation
Entropy-Calibrated Label Distribution Learning
EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Error Forcing in Recurrent Neural Networks
Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
Estimating Model Performance Under Covariate Shift Without Labels
Estimation and Inference in Distributional Reinforcement Learning
Estimation of Stochastic Optimal Transport Maps
EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death
Evaluating multiple models using labeled and unlabeled data
Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
Exploring Diffusion Transformer Designs via Grafting
Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
Exploring the Translation Mechanism of Large Language Models
Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
Factorio Learning Environment
Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
Fair Deepfake Detectors Can Generalize
FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
Fast constrained sampling in pre-trained diffusion models
FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
Faster Generic Identification in Tree-Shaped Structural Causal Models
Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities
FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
FHGS: Feature-Homogenized Gaussian Splatting
Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining
Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW
Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features
Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360° Firefighting Video
FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
FlashMD: long-stride, universal prediction of molecular dynamics
FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
FlexOLMo: Open Language Models for Flexible Data Use
FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
Flow Equivariant Recurrent Neural Networks
FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
FlowRefiner: A Robust Traffic Classification Framework against Label Noise
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
FORLA: Federated Object-centric Representation Learning with Slot Attention
Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge
Foundations of Top-$k$ Decoding for Language Models
Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation
Fréchet Geodesic Boosting
From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications
From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging
From Euler to AI: Unifying Formulas for Mathematical Constants
From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes
From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Fully Spiking Neural Networks for Unified Frame-Event Object Tracking
Functional Complexity-adaptive Temporal Tensor Decomposition
Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Gatekeeper: Improving Model Cascades Through Confidence Tuning
Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization
Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span
GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS Fusion
Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
Generalizable Insights for Graph Transformers in Theory and Practice
Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
Generalizing Experience for Language Agents with Hierarchical MetaFlows
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
Generating and Checking DNN Verification Proofs
Generative Caching for Structurally Similar Prompts and Responses
Generative Distribution Embeddings
Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions
Geometric Imbalance in Semi-Supervised Node Classification
Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm
Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies
GMV: A Unified and Efficient Graph Multi-View Learning Framework
GoalLadder: Incremental Goal Discovery with Vision-Language Models
GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
Graph Neural Network Based Action Ranking for Planning
Graph-Theoretic Insights into Bayesian Personalized Ranking for Recommendation
GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction
GRIP: A Graph-Based Reasoning Instruction Producer
GSPN-2: Efficient Parallel Sequence Modeling
GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
Guiding LLM Decision-Making with Fairness Reward Models
GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries
Hadamax Encoding: Elevating Performance in Model-Free Atari
Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks
HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions
Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
Heterogeneous Diffusion Structure Inference for Network Cascade
Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints
Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
Hierarchical Implicit Neural Emulators
Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
How Particle System Theory Enhances Hypergraph Message Passing
HPSERec: A Hierarchical Partitioning and Stepwise Enhancement Framework for Long-tailed Sequential Recommendation
HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning
HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location
HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup
Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
ImgEdit: A Unified Image Editing Dataset and Benchmark
Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
Implicit Generative Property Enhancer
Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning
Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
Incentivizing Time-Aware Fairness in Data Sharing
Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion
In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning
IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants
Individually Fair Diversity Maximization
Individual Regret in Cooperative Stochastic Multi-Armed Bandits
Inference with correlated priors using sisters cells
InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination
Informed Correctors for Discrete Diffusion Models
In Search of Adam’s Secret Sauce
In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain
InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition
Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation
Interpretable Next-token Prediction via the Generalized Induction Head
Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions
Introducing FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark
Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
IR-OptSet: An Optimization-Sensitive Dataset for Advancing LLM-Based IR Optimizer
Is Artificial Intelligence Generated Image Detection a Solved Problem?
Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
Just One Layer Norm Guarantees Stable Extrapolation
KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing
Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning
KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
Knee-Deep in C-RASP: A Transformer Depth Hierarchy
Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias
Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
Large Language Models as Model Organisms for Human Associative Learning
Large Language Models Think Too Fast To Explore Effectively
LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
Last Iterate Convergence in Monotone Mean Field Games
Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
Latent Chain-of-Thought for Visual Reasoning
Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
Latent Space Factorization in LoRA
Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity
LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing
Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields
Learning and Planning Multi-Agent Tasks via an MoE-based World Model
Learning-Augmented Online Bidding in Stochastic Settings
Learning-Augmented Streaming Algorithms for Correlation Clustering
Learning Differential Pyramid Representation for Tone Mapping
Learning Dynamics of RNNs in Closed-Loop Environments
Learning from Interval Targets
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks
Learning Juntas under Markov Random Fields
Learning Shared Representations from Unpaired Data
Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification
Learning Task-Agnostic Representations through Multi-Teacher Distillation
Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models
Learning to Condition: A Neural Heuristic for Scalable MPE Inference
Learning to Learn with Contrastive Meta-Objective
Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
Learning with Statistical Equality Constraints
Learning World Models for Interactive Video Generation
Least squares variational inference
Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting
Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
Let LRMs Break Free from Overthinking via Self-Braking Tuning
Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
Let the LLM Stick to Its Strengths: Learning to Route Economical LLM
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
Lifelong Safety Alignment for Language Models
Lifelong Test-Time Adaptation via Online Learning in Tracked Low-Dimensional Subspace
Linearly Constrained Diffusion Implicit Models
Linear Mixture Distributionally Robust Markov Decision Processes
Linear Transformers Implicitly Discover Unified Numerical Algorithms
LinPrim: Linear Primitives for Differentiable Volumetric Rendering
LLM Unlearning via Neural Activation Redirection
LMFusion: Adapting Pretrained Language Models for Multimodal Generation
L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
Locality in Image Diffusion Models Emerges from Data Statistics
Locally Optimal Private Sampling: Beyond the Global Minimax
LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
Low-degree evidence for computational transition of recovery rate in stochastic block model
LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language Models
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
macOSWorld: A Multilingual Interactive Benchmark for GUI Agents
Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
MAP Estimation with Denoisers: Convergence Rates and Guarantees
Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
MAT-Agent: Adaptive Multi-Agent Training Optimization
MaxSup: Overcoming Representation Collapse in Label Smoothing
Mean Flows for One-step Generative Modeling
Measuring and Guiding Monosemanticity
Mechanism Design for LLM Fine-tuning with Multiple Reward Models
MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks
MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
Median Selection with Noisy and Structural Information
Memory by accident: a theory of learning as a byproduct of network stabilization
Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning
Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations
Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
Mitigating Occlusions in Virtual Try-On via A Simple-Yet-Effective Mask-Free Framework
Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
MIX: A Multi-view Time-Frequency Interactive Explanation Framework for Time Series Classification
Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
mmWalk: Towards Multi-modal Multi-view Walking Assistance
MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation
Model Editing for Vision Transformers
Model-Informed Flows for Bayesian Inference
Modelling the control of offline processing with reinforcement learning
ModHiFi: Identifying High Fidelity predictive components for Model Modification
MolVision: Molecular Property Prediction with Vision Language Models
Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing
MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis
MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game
Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration
Multi-Agent Reinforcement Learning with Communication-Constrained Priors
Multi-head Temporal Latent Attention
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans
Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
Multi-Objective One-Shot Pruning for Large Language Models
Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning
Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
Multivariate Time Series Anomaly Detection with Idempotent Reconstruction
MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
NEED: Cross-Subject and Cross-Task Generalization for Video and Image Reconstruction from EEG Signals
Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
NEP: Autoregressive Image Editing via Next Editing Token Prediction
Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction
Neural Mutual Information Estimation with Vector Copulas
Neural Networks Generalize on Low Complexity Data
Neural Tangent Knowledge Distillation for Optical Convolutional Networks
NeurIPS should lead scientific consensus on AI policy
NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
NeuSymEA: Neuro-symbolic Entity Alignment via Variational Inference
Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
No Experts, No Problem: Avoidance Learning from Bad Demonstrations
Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Nonlinear Laplacians: Tunable principal component analysis under directional prior information
NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input
No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
Normalization in Attention Dynamics
Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
Object-Centric Concept-Bottlenecks
Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
Offline Actor-Critic for Average Reward MDPs
OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding
OmniGen-AR: AutoRegressive Any-to-Image Generation
OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
One for All: Universal Topological Primitive Transfer for Graph Structure Learning
On Evaluating LLM Alignment by Evaluating LLMs as Judges
On Extending Direct Preference Optimization to Accommodate Ties
On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
On Inductive Biases That Enable Generalization in Diffusion Transformers
Online Experimental Design With Estimation-Regret Trade-off Under Network Interference
Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion
Online Locally Differentially Private Conformal Prediction via Binary Inquiries
Online Prediction with Limited Selectivity
Online Segment Any 3D Thing as Instance Tracking
On Logic-based Self-Explainable Graph Neural Networks
On the Entropy Calibration of Language Models
On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
On the Sample Complexity Bounds of Bilevel Reinforcement Learning
On the Sample Complexity of Differentially Private Policy Optimization
On topological descriptors for graph products
OOD Detection with Relative Angles
Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
Orient Anything V2: Unifying Orientation and Rotation Understanding
Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
Orochi: Versatile Biomedical Image Processor
Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data
Overcoming Challenges of Long-Horizon Prediction in Driving World Models
Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
Pairwise Calibrated Rewards for Pluralistic Alignment
PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation
PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling
Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis
PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows
PIVNO: Particle Image Velocimetry Neural Operator
PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting
Plasticity as the Mirror of Empowerment
Plug-and-Play Context Feature Reuse for Efficient Masked Generation
PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
PoE-World: Compositional World Modeling with Products of Programmatic Experts
Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
PoLAR: Polar-Decomposed Low-Rank Adapter Representation
Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
Policy learning “without” overlap: Pessimism and generalized empirical Bernstein’s inequality
PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations
Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
Position: Bridge the Gaps between Machine Unlearning and AI Regulation
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
Practical Bayes-Optimal Membership Inference Attacks
Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
Preference Optimization by Estimating the Ratio of the Data Distribution
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
Preserving Task-Relevant Information Under Linear Concept Removal
Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number
Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving
Private Continual Counting of Unbounded Streams
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
Program Synthesis via Test-Time Transduction
Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
Prompt Tuning Decision Transformers with Structured and Scalable Bandits
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
Protein Inverse Folding From Structure Feedback
Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift
PUATE: Efficient ATE Estimation from Treated (Positive) and Unlabeled Units
PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning
Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference
Quantum Visual Fields with Neural Amplitude Encoding
Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights
QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays
RAPTR: Radar-based 3D Pose Estimation using Transformer
Rare Text Semantics Were Always There in Your Diffusion Transformer
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal Outputs
Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation
Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Reasoning Models Sometimes Output Illegible Chains of Thought
ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
Rectified Point Flow: Generic Point Cloud Pose Estimation
Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians
Regional Explanations: Bridging Local and Global Variable Importance
Reinforcement Learning Teachers of Test Time Scaling
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
Relieving the Over-Aggregating Effect in Graph Transformers
Remasking Discrete Diffusion Models with Inference-Time Scaling
Replicable Online pricing
REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
Resounding Acoustic Fields with Reciprocity
ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
Rethinking Losses for Diffusion Bridge Samplers
Rethinking PCA Through Duality
Rethinking Scale-Aware Temporal Encoding for Event-based Object Detection
RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis
Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
Revisiting Orbital Minimization Method for Neural Operator Decomposition
Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening
Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN
Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
Riemannian Consistency Model
RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data
Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains
RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
Robust and Computation-Aware Gaussian Processes
Robust Hallucination Detection in LLMs via Adaptive Token Selection
Robust Regression of General ReLUs with Queries
Robust Sampling for Active Statistical Inference
Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models
ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
RvLLM: LLM Runtime Verification with Domain Knowledge
S$^2$NN: Sub-bit Spiking Neural Networks
Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
Safety Pretraining: Toward the Next Generation of Safe AI
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
Sample-Adaptivity Tradeoff in On-Demand Sampling
Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
Scaffolding Dexterous Manipulation with Vision-Language Models
Scalable Best-of-N Selection for Large Language Models via Self-Certainty
Scalable Fingerprinting of Large Language Models
Scalable Signature Kernel Computations via Local Neumann Series Expansions
Scalable Valuation of Human Feedback through Provably Robust Model Alignment
Scaling Diffusion Transformers Efficiently via $\mu$P
Scaling Language-centric Omnimodal Representation Learning
Scaling Laws For Scalable Oversight
Scaling Law with Learning Rate Annealing
Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures
SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction
SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI
SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning
SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents
Self-Improving Embodied Foundation Models
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
Self-Supervised Learning of Graph Representations for Network Intrusion Detection
Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology
Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image Classification
Shaping Sequence Attractor Schema in Recurrent Neural Networks
SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
Sharp Matrix Empirical Bernstein Inequalities
Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse
Simple and Effective Specialized Representations for Fair Classifiers
Simple and Efficient Heterogeneous Temporal Graph Neural Network
Simple and Optimal Sublinear Algorithms for Mean Estimation
Simulation-Based Inference for Adaptive Experiments
Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
Simultaneous Swap Regret Minimization via KL-Calibration
SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks
SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry
Solver-Free Decision-Focused Learning for Linear Optimization Problems
SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics
Solving Partial Differential Equations via Radon Neural Operator
Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
Space Group Equivariant Crystal Diffusion
SparseDiT: Token Sparsification for Efficient Diffusion Transformer
Spatially-aware Weights Tokenization for NeRF-Language Models
SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
Spectral Convolutional Conditional Neural Process
SpectraLDS: Provable Distillation for Linear Dynamical Systems
SPFL: Sequential updates with Parallel aggregation for Enhanced Federated Learning under Category and Domain Shifts
Spik-NeRF: Spiking Neural Networks for Neural Radiance Fields
SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
SPRO: Improving Image Generation via Self-Play
Squared families are useful conjugate priors
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
Stability and Oracle Inequalities for Optimal Transport Maps between General Distributions
Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
Stable Port-Hamiltonian Neural Networks
Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models
Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
Stochastic Process Learning via Operator Flow Matching
Stochastic Shortest Path with Sparse Adversarial Costs
Stop the Nonconsensual Use of Nude Images in Research
Straight-Line Diffusion Model for Efficient 3D Molecular Generation
Streaming Federated Learning with Markovian Data
STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
Structure-Aware Spectral Sparsification via Uniform Edge Sampling
Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models
Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
Subsampled Ensemble Can Improve Generalization Tail Exponentially
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Superposition Yields Robust Neural Scaling
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
Switchable Token-Specific Codebook Quantization For Face Image Compression
SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
Synthetic-powered predictive inference
System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
Teaching Language Models to Reason with Tools
Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control
The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
The Flood Complex: Large-Scale Persistent Homology on Millions of Points
The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
Theoretical Insights into In-context Learning with Unlabeled Data
The Structural Complexity of Matrix-Vector Multiplication
The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
Thresholds for sensitive optimality and Blackwell optimality in stochastic games
Tight analyses of first-order methods with error feedback
TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE
Titans: Learning to Memorize at Test Time
Topology-aware Graph Diffusion Model with Persistent Homology
TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving
Towards 3D Objectness Learning in an Open World
Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study
Towards Pre-trained Graph Condensation via Optimal Transport
Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
Towards Reliable Identification of Diffusion-based Image Manipulations
Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions
TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
Training-free Detection of AI-generated images via Cropping Robustness
Training Language Models to Reason Efficiently
Transductive Conformal Inference for Full Ranking
Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
Transformers for Mixed-type Event Sequences
Transformers Learn Faster with Semantic Focus
Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
Treatment Effect Estimation for Optimal Decision-Making
Tree-Guided Diffusion Planner
T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
Truthful Aggregation of LLMs with an Application to Online Advertising
Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Two Heads are Better than One: Simulating Large Transformers with Small Ones
UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations
UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation
Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification
Uncertainty-Guided Exploration for Efficient AlphaZero Training
Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback
Understanding and Enhancing Mask-Based Pretraining towards Universal Representations
Understanding Bias Terms in Neural Representations
Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem
Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models
Unified 2D-3D Discrete Priors for Noise-Robust and Calibration-Free Multiview 3D Human Pose Estimation
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets
Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching
Universally Invariant Learning in Equivariant GNNs
UniViT: Unifying Image and Video Understanding in One Vision Encoder
Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
Valid Inference with Imperfect Synthetic Data
Value-Guided Search for Efficient Chain-of-Thought Reasoning
Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness
VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
VideoMAR: Autoregressive Video Generation with Continuous Tokens
VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
Vision Function Layer in Multimodal LLMs
Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Vocabulary-Guided Gait Recognition
Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY
What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses
When Models Don’t Collapse: On the Consistency of Iterative MLE
Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games
Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
WKV-sharing embraced random shuffle RWKV high-order modeling for pan-sharpening
World-aware Planning Narratives Enhance Large Vision-Language Model Planner
WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
YOLOv12: Attention-Centric Real-Time Object Detectors
You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network
ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
ZeroPatcher: Training-free Sampler for Video Inpainting and Editing
Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework
Zero-Shot Performance Prediction for Probabilistic Scaling Laws
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
(ends 7:30 PM)
Creative AI Session 4 [4:30-7:30]
Chairs: Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian
s 4:30-7:30
[4:30] An Inference Zoo for Real-Time Media Arts: Avendish as a Bridge Between AI and Creative Environments
[4:30] Artificial "Authentic" Intelligence: Can AI Systems Embody and Evolve Cultural Heritage? A Case Study of "Cyber Subin" and Thai Traditional Dance
[4:30] "Artificial Spectator" Developing AI Audiences for Watching AI-Generated Films: A Speculative Exploration on the Future of Media and AI
[4:30] Between Reality and AI Hallucinations: Reimagining the Sacred Soundscape of Ming Rituals
[4:30] BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart
[4:30] Blankscope: Real-time Bridging of Human Perception with AI Imagination
[4:30] Craving Checkpoint: An Interactive Fridge Lock for Mindful Eating
[4:30] Creative Synthesis of Kinematic Mechanisms
[4:30] From Movement Memories to Robotic Dialogue: A Language-Mediated Pipeline for Somatic Machine Translation
[4:30] Green Topics, Deep Roots: Energy-Aware Topic Modelling of Multilingual Nigerian Lyrics
[4:30] "Jutters''
[4:30] Little Martians: From Desert Clay to Generative Agents
[4:30] MCP2OSC: Parametric Control by Natural Language
[4:30] Pocket Ink - Heaven’s mandate: a hyper-individualized tangible card game platform in the Age of AI
[4:30] Roulettective: Repurposing a Vintage Slide Projector into an AI-Driven Physical Detective Game
[4:30] Scene-Aware Urban Design: A Human–AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language Models
[4:30] SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow
[4:30] Superradiance
[4:30] Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models
[4:30] The Glitching Therapist: Performing the Limits of AI Empathy
[4:30] TinyTim: a family of language models for divergent generation
[4:30] (Un)Natural Language
[4:30] Writing in Symbiosis: Mapping Human Creative Agency in the AI Era
(ends 7:30 PM)
7 p.m.

FRI 5 DEC
7:30 a.m.
Registration Desk
(ends 6:00 PM)
8 a.m.
Break:
Coffee Break
(ends 8:30 AM)
8:30 a.m.
San Diego Invited Talk:
From Benchmarks to Problems - A Perspective on Problem Finding in AI
Kyunghyun Cho
(ends 9:30 AM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral Session 5A [10:00-11:00]
EvoLM: In Search of Lost Language Model Training Dynamics
Large Language Diffusion Models
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
(ends 11:00 AM)
Oral Session 5B [10:00-11:00]
WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training
NOVA: A Benchmark for Rare Anomaly Localization and Clinical Reasoning in Brain MRI
(ends 11:00 AM)
Oral Session 5C [10:00-11:00]
High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
Memory Mosaics at scale
(ends 11:00 AM)
Oral Session 5D [10:00-11:00]
InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
PlayerOne: Egocentric World Simulator
BEDLAM2.0: Synthetic humans and cameras in motion
(ends 11:00 AM)
Oral Session 5E [10:00-11:00]
Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
(ends 11:00 AM)
11 a.m.
San Diego Poster Session 5 [11:00-2:00]
Posters 11:00-2:00
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
4KAgent: Agentic Any Image to 4K Super-Resolution
A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
Accelerating Diffusion LLMs via Adaptive Parallel Decoding
Accelerating Model-Free Optimization via Averaging of Cost Samples
AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems
Activation-Informed Merging of Large Language Models
Active Measurement: Efficient Estimation at Scale
AdaptGrad: Adaptive Sampling to Reduce Noise
Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
Adaptive Data Analysis for Growing Data
Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search
Adaptive Fission: Post-training Encoding for Low-latency Spike Neural Networks
Adaptively Coordinating with Novel Partners via Learned Latent Strategies
Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling
Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning
A Differential and Pointwise Control Approach to Reinforcement Learning
ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Adversarial generalization of unfolding (model-based) networks
Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning
Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity
A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging
Aha! - Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
A Hierarchy of Graphical Models for Counterfactual Inferences
A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
AION-1: Omnimodal Foundation Model for Astronomical Sciences
AI Testing Should Account for Sophisticated Strategic Behaviour
Alchemist: Turning Public Text-to-Image Data into Generative Gold
A learnability analysis on neuro-symbolic learning
Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models
Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
Aligning Text to Image in Diffusion Models is Easier Than You Think
ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
A Minimalist Example of Edge-of-Stability and Progressive Sharpening
Among Us: A Sandbox for Measuring and Detecting Agentic Deception
A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals
Anchored Diffusion Language Model
An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph
Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
Anomaly Detection by an Ensemble of Random Pairs of Hyperspheres
A Novel General Framework for Sharp Lower Bounds in Succinct Stochastic Bandits
Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers
Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
A Provable Approach for End-to-End Safe Reinforcement Learning
ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting
A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks
Ascent Fails to Forget
A Semantic Parsing Framework for End-to-End Time Normalization
A Single-Swap Local Search Algorithm for k-Means of Lines
Association-Focused Path Aggregation for Graph Fraud Detection
Asymmetric Dual-Lens Video Deblurring
A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
Audio-Sync Video Generation with Multi-Stream Temporal Control
A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
A Unified Framework for the Transportability of Population-Level Causal Measures
A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
Autoencoding Random Forests
Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
Balancing Performance and Costs in Best Arm Identification
Bandit Guided Submodular Curriculum for Adaptive Subset Selection
Bayes optimal learning of attention-indexed models
BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
BEDLAM2.0: Synthetic humans and cameras in motion
Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
Best-of-N Jailbreaking
Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation
Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training
Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
BlockScan: Detecting Anomalies in Blockchain Transactions
BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-Identification
Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
Boundary-to-Region Supervision for Offline Safe Reinforcement Learning
BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
Breaking AR’s Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
Breaking the Discretization Barrier of Continuous Physics Simulation Learning
Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
Breaking the Order Barrier: Off-Policy Evaluation for Confounded POMDPs
Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks
Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
Bubbleformer: Forecasting Boiling with Transformers
BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization
BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes
C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning
CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency Discrimination
CAMILA: Context-Aware Masking for Image Editing with Language Alignment
CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind
Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
Cascaded Language Models for Cost-Effective Human–AI Decision-Making
Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door Intervention
Causal Mixture Models: Characterization and Discovery
CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration
Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors
CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search
Class-wise Balancing Data Replay for Federated Class-Incremental Learning
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
CLIMB: Class-imbalanced Learning Benchmark on Tabular Data
CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation
CMoB: Modality Valuation via Causal Effect for Balanced Multimodal Learning
Compact Memory for Continual Logistic Regression
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
ComPO: Preference Alignment via Comparison Oracles
Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
Computational Efficiency under Covariate Shift in Kernel Ridge Regression
Concept-Guided Interpretability via Neural Chunking
Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
Conditional Panoramic Image Generation via Masked Autoregressive Modeling
Conditioning Matters: Training Diffusion Policies is Faster Than You Think
Conformal Information Pursuit for Interactively Guiding Large Language Models
Conformal Prediction for Time-series Forecasting with Change Points
Contextual Dynamic Pricing with Heterogeneous Buyers
Continual Multimodal Contrastive Learning
Continuous Simplicial Neural Networks
Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
Contrastive Representations for Temporal Reasoning
Controlling Thinking Speed in Reasoning Models
Convergent Functions, Divergent Forms
Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning
Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
Coupling Generative Modeling and an Autoencoder with the Causal Bridge
CPO: Condition Preference Optimization for Controllable Image Generation
CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
Credal Prediction based on Relative Likelihood
CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling
Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect
CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
Crucible: Quantifying the Potential of Control Algorithms through LLM Agents
CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing
Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
Data-Adaptive Exposure Thresholds under Network Interference
Data-Dependent Regret Bounds for Constrained MABs
Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models
Dataset Distillation of 3D Point Clouds via Distribution Matching
DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models
Decoding Causal Structure: End-to-End Mediation Pathways Inference
Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation
Decomposing stimulus-specific sensory neural information via diffusion models
DeepHalo: A Neural Choice Model with Controllable Context Effects
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs
DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
Demystifying Language Model Forgetting with Low-rank Example Associations
Density Ratio-Free Doubly Robust Proxy Causal Learning
Depth-Width Tradeoffs for Transformers on Graph Tasks
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding
DermaCon-IN: A Multiconcept-Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research
Detecting Generated Images by Fitting Natural Image Distributions
DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
Differentiable Constraint-Based Causal Discovery
Differentiable Cyclic Causal Discovery Under Unmeasured Confounders
Differentiable Decision Tree via "ReLU+Argmin" Reformulation
Differentiable Generalized Sliced Wasserstein Plans
Differentiable Structure Learning and Causal Discovery for General Binary Data
Differentially Private Relational Learning with Entity-level Privacy Guarantees
Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
DiffLiG: Diffusion-enhanced Liquid Graph with Attention Propagation for Grid-to-Station Precipitation Correction
Diffusion Beats Autoregressive in Data-Constrained Settings
Diffusion Classifiers Understand Compositionality, but Conditions Apply
Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting
Diffusion Generative Modeling on Lie Group Representations
Diffusion Models Meet Contextual Bandits
Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
Dimension-free Score Matching and Time Bootstrapping for Diffusion Models
Discovering Data Structures: Nearest Neighbor Search and Beyond
Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
Disentangling Latent Shifts of In-Context Learning with Weak Supervision
Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation
Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
Distributed mediation analysis with communication efficiency
Distributional Adversarial Attacks and Training in Deep Hedging
Distributional Training Data Attribution: What do Influence Functions Sample?
Diversifying Parallel Ergodic Search: A Signature Kernel Evolution Strategy
Diversity-oriented Deep Multi-modal Clustering
Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings
Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
DQVis Dataset: Natural Language to Biomedical Visualization
DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
DroneAudioset: An Audio Dataset for Drone-based Search and Rescue
Dual-Comb Ghost Imaging with Transformer-Based Reconstruction for Optical Fiber Endomicroscopy
Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization
Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation
DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism
E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models
Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
Efficient Last-Iterate Convergence in Solving Extensive-Form Games
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference
Efficient RAW Image Deblurring with Adaptive Frequency Modulation
Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
Elastic Robust Unlearning of Specific Knowledge in Large Language Models
ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals
Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
Embeddings as Probabilistic Equivalence in Logic Programs
Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
Emergent Risk Awareness in Rational Agents under Resource Constraints
Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping
End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWs
Energy-based generator matching: A neural sampler for general state space
Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark
Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering
Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
ENMA: Tokenwise Autoregression for Continuous Neural PDE Operators
Entropy Rectifying Guidance for Diffusion and Flow Models
EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models
Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
Erasing Conceptual Knowledge from Language Models
Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
Event-based HDR Structured Light
EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation
Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
EvoLM: In Search of Lost Language Model Training Dynamics
Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits
EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
Exploring and Leveraging Class Vectors for Classifier Editing
Exploring the limits of strong membership inference attacks on large language models
Exploring the Noise Robustness of Online Conformal Prediction
Exponential Dynamic Energy Network for High Capacity Sequence Memory
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Extrapolation by Association: Length Generalization Transfer In Transformers
FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
FairDD: Fair Dataset Distillation
FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
Faithful Group Shapley Value
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
Fantastic Bugs and Where to Find Them in AI Benchmarks
Fast Data Attribution for Text-to-Image Models
Faster Algorithms for Structured John Ellipsoid Computation
Faster Fixed-Point Methods for Multichain MDPs
Faster Video Diffusion with Trainable Sparse Attention
FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis
Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning
FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
Feature-aware Modulation for Learning from Temporal Tabular Data
Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling
FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
FedFree: Breaking Knowledge-sharing Barriers through Layer-wise Alignment in Heterogeneous Federated Learning
FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization
FEEDBACK FRICTION: LLMs Struggle to Fully Incorporate External Feedback
Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems
Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds
FIPER: Factorized Features for Robust Image Super-Resolution and Compression
Fix False Transparency by Noise Guided Splatting
FlashMoE: Fast Distributed MoE in a Single Kernel
Flatten Graphs as Sequences: Transformers are Scalable Graph Generators
Flick: Empowering Federated Learning with Commonsense Knowledge
FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
Focus-Then-Reuse: Fast Adaptation in Visual Perturbation Environments
FoGE: Fock Space inspired encoding for graph prompting
Forecasting in Offline Reinforcement Learning for Non-stationary Environments
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
Fourier Analysis Network
FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents
From Black-box to Causal-box: Towards Building More Interpretable Models
From Indicators to Insights: Diversity-Optimized for Medical Series-Text Decoding via LLMs
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models
From Synapses to Dynamics: Obtaining Function from Structure in a Connectome Constrained Model of the Head Direction Circuit
Fuse2Match: Training-Free Fusion of Flow, Diffusion, and Contrastive Models for Zero-Shot Semantic Matching
Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent
Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
Generalizing Verifiable Instruction Following
Generating Creative Chess Puzzles
Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations
Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
Generating Physically Sound Designs from Text and a Set of Physical Constraints
Generative Graph Pattern Machine
Generative Perception of Shape and Material from Differential Motion
GenIR: Generative Visual Feedback for Mental Image Retrieval
GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion
Geometric Algebra-Enhanced Bayesian Flow Network for RNA Inverse Design
Geometric Learning with Positively Decomposable Kernels
GeoVideo: Introducing Geometric Regularization into Video Generation Model
GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals
GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design
Global Minimizers of Sigmoid Contrastive Loss
GLVD: Guided Learned Vertex Descent
GMM-based VAE model with Normalising Flow for effective stochastic segmentation
GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
Graph Diffusion that can Insert and Delete
Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
Graphs Help Graphs: Multi-Agent Graph Socialized Learning
Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry
Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges
Greed is Good: A Unifying Perspective on Guided Generation
GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
GRIT: Teaching MLLMs to Think with Images
Group-in-Group Policy Optimization for LLM Agent Training
Guided Diffusion Sampling on Function Spaces with Applications to PDEs
GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting
HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class
Harnessing the Universal Geometry of Embeddings
HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
HEIR: Learning Graph-Based Motion Hierarchies
HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis
High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
High Dynamic Range Imaging with Time-Encoding Spike Camera
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
High Resolution UDF Meshing via Iterative Networks
HoliTom: Holistic Token Merging for Fast Video Large Language Models
HoT-VI: Reparameterizable Variational Inference for Capturing Instance-Level High-Order Correlations
How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
How Far Are We from Optimal Reasoning Efficiency?
How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
How to build a consistency model: Learning flow maps via self-distillation
How Well Can Differential Privacy Be Audited in One Run?
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering
HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning
HYPRL: Reinforcement Learning of Control Policies for Hyperproperties
HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context Illumination
IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation
Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation
ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
Image Super-Resolution with Guarantees via Conformalized Generative Models
Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
Imagined Autocurricula
Improved Approximation Algorithms for Chromatic and Pseudometric-Weighted Correlation Clustering
Improved Representation Steering for Language Models
Improving Model-Based Reinforcement Learning by Converging to Flatter Minima
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal Inference
In-Context Learning Strategies Emerge Rationally
Inductive Domain Transfer In Misspecified Simulation-Based Inference
Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
Inference-Time Personalized Alignment with a Few User Preference Queries
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
Interpreting vision transformers via residual replacement model
Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
Inverse Methods for Missing Data Imputation
Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems
Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemble Generation
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding
K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
Kinaema: a recurrent sequence model for memory and pose in motion
Kinetics: Rethinking Test-Time Scaling Law
KLASS: KL-Guided Fast Inference in Masked Diffusion Models
Knot So Simple: A Minimalistic Environment for Spatial Reasoning
Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
Knowledge Distillation of Uncertainty using Deep Latent Factor Model
Know Thyself by Knowing Others: Learning Neuron Identity from Population Context
Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
Language Models Can Predict Their Own Behavior
Language Models can Self-Improve at State-Value Estimation for Better Search
LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search
Large Language Diffusion Models
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration
LBMKGC: Large Model-Driven Balanced Multimodal Knowledge Graph Completion
Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
Learning a Cross-Modal Schrödinger Bridge for Visual Domain Generalization
Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data
Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting
Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering
Learning Human-Object Interaction as Groups
Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
Learning normalized image densities via dual score matching
Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics
Learning Robust Spectral Dynamics for Temporal Domain Generalization
Learning Stochastic Multiscale Models
Learning to Clean: Reinforcement Learning for Noisy Label Correction
Learning to Insert for Constructive Neural Vehicle Routing Solver
Learning to price with resource constraints: from full information to machine-learned prices
Learning to Zoom with Anatomical Relations for Medical Structure Detection
Leaving No OOD Instance Behind: Instance-Level OOD Fine-Tuning for Anomaly Segmentation
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
Less Greedy Equivalence Search
Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied Learning
Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation
LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
List-Level Distribution Coupling with Applications to Speculative Decoding and Lossy Compression
LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering
Local Learning for Covariate Selection in Nonparametric Causal Effect Estimation with Latent Variables
Logic.py: Bridging the Gap between LLMs and Constraint Solvers
Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning
LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant
Low Precision Streaming PCA
Low-Rank Head Avatar Personalization with Registers
Machine Unlearning via Task Simplex Arithmetic
MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
Markov Persuasion Processes: Learning to Persuade From Scratch
Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks
Martingale Posterior Neural Networks for Fast Sequential Decision Making
Mask Image Watermarking
MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
Measure-Theoretic Anti-Causal Representation Learning
MedSG-Bench: A Benchmark for Medical Image Sequences Grounding
MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
MemEIC: A Step Toward Continual and Compositional Knowledge Editing
Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Memory Mosaics at scale
MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Merlin L48 Spectrogram Dataset
MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo
MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
MixSignGraph: A Sign Sequence is Worth Mixed Graphs of Nodes
Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform
MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
MMaDA: Multimodal Large Diffusion Language Models
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
Model Provenance Testing for Large Language Models
MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
Momentum Multi-Marginal Schrödinger Bridge Matching
MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
MoRIC: A Modular Region-based Implicit Codec for Image Compression
🎧MOSPA: Human Motion Generation Driven by Spatial Audio
Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
MR. Video: MapReduce as an Effective Principle for Long Video Understanding
MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
Multi-agent Markov Entanglement
Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
Multimodal Negative Learning
Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
Multiresolution Analysis and Statistical Thresholding on Dynamic Networks
Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
NavBench: Probing Multimodal Large Language Models for Embodied Navigation
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
Neural Attention Search
Neural Green’s Functions
NeuralSurv: Deep Survival Analysis with Bayesian Uncertainty Quantification
NeurIPT: Foundation Model for Neural Interfaces
New Parallel and Streaming Algorithms for Directed Densest Subgraph
NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic Lighting
NoBOOM: Chemical Process Datasets for Industrial Anomaly Detection
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
Non-Adaptive Adversarial Face Generation
Non-Clairvoyant Scheduling with Progress Bars
Non-Markovian Discrete Diffusion with Causal Language Models
Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation
Non-Stationary Lipschitz Bandits
Normal-Abnormal Guided Generalist Anomaly Detection
NOVA: A Benchmark for Rare Anomaly Localization and Clinical Reasoning in Brain MRI
Novel Exploration via Orthogonality
nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
Objective Soups: Multilingual Multi-Task Modeling for Speech Processing
Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking
OmniTry: Virtual Try-On Anything without Masks
One Head to Rule Them All: Amplifying LVLM Safety through a Single Critical Attention Head
One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
On Hierarchies of Fairness Notions in Cake Cutting: From Proportionality to Super Envy-Freeness
Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning
Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
Online Statistical Inference in Decision Making with Matrix Context
On Reasoning Strength Planning in Large Reasoning Models
On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
On the Hardness of Approximating Distributions with Tractable Probabilistic Models
On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls
On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
On the Relation between Rectified Flows and Optimal Transport
On Transferring Transferability: Towards a Theory for Size Generalization
On Union-Closedness of Language Generation
OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations
Open-World Drone Active Tracking with Goal-Centered Rewards
Opinion Maximization in Social Networks by Modifying Internal Opinions
OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information
Optimal Estimation of the Best Mean in Multi-Armed Bandits
Optimal kernel regression bounds under energy-bounded noise
Optimal Online Change Detection via Random Fourier Features
Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
Optimal Rates in Continual Linear Regression via Increasing Regularization
Optimal Spectral Transitions in High-Dimensional Multi-Index Models
Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
Optimizing Retrieval for RAG via Reinforced Contrastive Learning
Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
Oracle-Efficient Combinatorial Semi-Bandits
OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning
Order-Level Attention Similarity Across Language Models: A Latent Commonality
OrdShap: Feature Position Importance for Sequential Black-Box Models
Orientation Matters: Making 3D Generative Models Orientation-Aligned
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
PanTS: The Pancreatic Tumor Segmentation Dataset
PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
Parallel Scaling Law for Language Models
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Parameter-free Algorithms for the Stochastically Extended Adversarial Model
Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery
PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization
Pattern-Guided Adaptive Prior for Structure Learning
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach
Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
Perturbation Bounds for Low-Rank Inverse Approximations under Noise
PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection
Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
Physics-informed Neural Operator for Pansharpening
PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation
Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning
PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement
PlayerOne: Egocentric World Simulator
PLEIADES: Building Temporal Kernels with Orthogonal Polynomials
pLSTM: parallelizable Linear Source Transition Mark networks
Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching
Practical and Effective Code Watermarking for Large Language Models
Practical Kernel Selection for Kernel-based Conditional Independence Test
PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
Precise Diffusion Inversion: Towards Novel Samples and Few-Step Models
Prediction-Powered Semi-Supervised Learning with Online Power Tuning
Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
Predictive Preference Learning from Human Interventions
PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
Principled Data Augmentation for Learning to Solve Quadratic Programming Problems
Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
Private Geometric Median in Nearly-Linear Time
Private Hyperparameter Tuning with Ex-Post Guarantee
Probably Approximately Precision and Recall Learning
Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster
Promptable 3-D Object Localization with Latent Diffusion Models
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search
ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning
Provably Efficient Online RLHF with One-Pass Reward Modeling
PurpCode: Reasoning for Safer Code Generation
Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning
QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation
Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training
Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Quantitative convergence of trained neural networks to Gaussian processes
Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
RAST: Reasoning Activation in LLMs via Small-model Transfer
RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling
RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
Real-DRL: Teach and Learn in Reality
Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start
REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
Reasoning Models Better Express Their Confidence
Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning
ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
ReDit: Reward Dithering for Improved LLM Policy Optimization
Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
REFED: A Subject Real-time Dynamic Labeled EEG-fNIRS Synchronized Recorded Emotion Dataset
Refusal Direction is Universal Across Safety-Aligned Languages
Register and [CLS] tokens induce a decoupling of local and global features in large ViTs
Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
Regression Trees Know Calculus
Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
Reinforced Context Order Recovery for Adaptive Reasoning and Planning
ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
Replicable Distribution Testing
Replicable Online Learning
Residual Stream Analysis of Overfitting And Structural Disruptions
Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
Rethinking the Role of Verbatim Memorization in LLM Privacy
Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
Revising and Falsifying Sparse Autoencoder Feature Explanations
Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
Revolutionizing Training-Free NAS: Towards Efficient Automatic Proxy Discovery via Large Language Models
Reward-oriented Causal Representation Learning
Risk-aware Direct Preference Optimization under Nested Risk Measure
Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits
Robustly Learning Monotone Single-Index Models
Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
RrED: Black-box Unsupervised Domain Adaptation via Rectifying-reasoning Errors of Diffusion
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
Safety Depth in Large Language Models: A Markov Chain Perspective
SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function
Sampled Estimators For Softmax Must Be Biased
SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
Scaling can lead to compositional generalization
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
Scaling RL to Long Videos
Scaling Up Active Testing to Large Language Models
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
SceneForge: Enhancing 3D-text alignment with Structured Scene Compositions
SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting
SD-KDE: Score-Debiased Kernel Density Estimation
SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery
Seeing the Arrow of Time in Large Multimodal Models
Seeking and Updating with Live Visual Knowledge
SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
Self-Assembling Graph Perceptrons
Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks
Semi-infinite Nonconvex Constrained Min-Max Optimization
SensorLM: Learning the Language of Wearable Sensors
Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning
Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders
Sharp Gaussian approximations for Decentralized Federated Learning
SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction
SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation
Simulating Society Requires Simulating Thought
Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning
SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference
Sinusoidal Initialization, Time for a New Start
Sketched Gaussian Mechanism for Private Federated Learning
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
SnapMoGen: Human Motion Generation from Expressive Texts
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
Sound Logical Explanations for Mean Aggregation Graph Neural Networks
Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention
Sparse Image Synthesis via Joint Latent and RoI Flow
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
SpatialLM: Training Large Language Models for Structured Indoor Modeling
SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs
Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping
SpEx: A Spectral Approach to Explainable Clustering
Spike4DGS: Towards High-Speed Dynamic Scene Rendering with 4D Gaussian Splatting via a Spike Camera Array
SpikingVTG: A Spiking Detection Transformer for Video Temporal Grounding
SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path
Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
Stable Matching with Ties: Approximation Ratios and Learning
Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios
State Size Independent Statistical Error Bound for Discrete Diffusion Models
Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces
Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schr\"{o}dinger Bridge Estimation
STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
Steering Information Utility in Key-Value Memory for Language Model Post-Training
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
Stochastically Dominant Peer Prediction
Stochastic-Constrained Stochastic Optimization with Markovian Data
Stochastic Forward-Forward Learning through Representational Dimensionality Compression
Stochastic Gradients under Nuisances
Strategic Cost Selection in Participatory Budgeting
Strategic Costs of Perceived Bias in Fair Selection
StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
Structured Initialization for Vision Transformers
Structure Matters: Dynamic Policy Gradient
Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
System Prompt Optimization with Meta-Learning
Table as a Modality for Large Language Models
TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
TAPAS: Datasets for Learning the Learning with Errors Problem
Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations
Tensor-Parallelism with Partially Synchronized Activations
TESTING STATIONARITY AND CHANGE POINT DETECTION IN REINFORCEMENT LEARNING
Test Time Scaling for Neural Processes
Test-Time Scaling of Diffusion Models via Noise Trajectory Search
Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
Text-to-Code Generation for Modular Building Layouts in Building Information Modeling
TF-MAS: Training-free Mamba2 Architecture Search
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
The Complexity of Correlated Equilibria in Generalized Games
The Complexity of Finding Local Optima in Contrastive Learning
The Curse of Depth in Large Language Models
The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models
The Indra Representation Hypothesis
Theoretical Benefit and Limitation of Diffusion Language Model
Theoretical Guarantees for the Retention of Strict Nash Equilibria by Coevolutionary Algorithms
Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization
The quest for the GRAph Level autoEncoder (GRALE)
ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
The third pillar of causal analysis? A measurement perspective on causal representations
The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations
Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions
TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising
Tight Bounds for Answering Adaptively Chosen Concentrated Queries
Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
ToF-IP: Time-of-Flight Enhanced Sparse Inertial Poser for Real-time Human Motion Capture
Topology-Aware Learning of Tubular Manifolds via SE(3)-Equivariant Network on Ball B-Spline Curve
Toward Human Deictic Gesture Target Estimation
Towards Accurate Time Series Forecasting via Implicit Decoding
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
Towards Generalizable Detector for Generated Image
Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs
Towards Identifiability of Hierarchical Temporal Causal Representation Learning
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search
Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
Towards Predicting Any Human Trajectory In Context
Towards Principled Unsupervised Multi-Agent Reinforcement Learning
Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
Tracking and Understanding Object Transformations
Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
TRAP: Targeted Redirecting of Agentic Preferences
Tree-Based Premise Selection for Lean4
TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning
TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster
UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
Understanding and Rectifying Safety Perception Distortion in VLMs
Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning
Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition
UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection
UniTransfer: Video Concept Transfer via Progressive Spatio-Temporal Decomposition
Universal Sequence Preconditioning
Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
Unleashing Hour-Scale Video Training for Long Video-Language Understanding
Unlocking Dataset Distillation with Diffusion Models
Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception
VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
Valid Selection among Conformal Sets
Value Improved Actor Critic Algorithms
Variational Task Vector Composition
Variational Uncertainty Decomposition for In-Context Learning
Vector Quantization in the Brain: Grid-like Codes in World Models
Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
VideoLucy: Deep Memory Backtracking for Long Video Understanding
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
Vid-SME: Membership Inference Attacks against Large Video Understanding Models
VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction, Characterization and Recognition
ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning
Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions
VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection
VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
Wasserstein Convergence of Critically Damped Langevin Diffusions
Watermarking Autoregressive Image Generation
Wavy Transformer
WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
What Expressivity Theory Misses: Message Passing Complexity for GNNs
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
When majority rules, minority loses: bias amplification of gradient descent
When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization
Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions
Whose Instructions Count? Resolving Preference Bias in Instruction Fine-Tuning
Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
WISA: World simulator assistant for physics-aware text-to-video generation
XIFBench: Evaluating Large Language Models on Multilingual Instruction Following
Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts
ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
(ends 2:00 PM)
1 p.m.
Break:
Hosted Lunch
(ends 2:30 PM)
2 p.m.
Award:
Sejnowski-Hinton Award
(ends 2:30 PM)
2:30 p.m.
San Diego Invited Talk:
Demystifying depth: Principles of learning in deep neural networks
Andrew Saxe
(ends 3:30 PM)
3:30 p.m.
Oral Session 6A [3:30-4:30]
An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization
(ends 4:30 PM)
Oral Session 6B [3:30-4:30]
GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability
RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation
Discovering Opinion Intervals from Conflicts in Signed Graphs
(ends 4:30 PM)
Oral Session 6C [3:30-4:30]
Generalized Linear Mode Connectivity for Transformers
On Linear Mode Connectivity of Mixture-of-Experts Architectures
Learning (Approximately) Equivariant Networks via Constrained Optimization
(ends 4:30 PM)
Oral Session 6D [3:30-4:30]
A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
Learning long range dependencies through time reversal symmetry breaking
(ends 4:30 PM)
Oral Session 6E [3:30-4:30]
KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
MokA: Multimodal Low-Rank Adaptation for MLLMs
ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
(ends 4:30 PM)
4:30 p.m.
Break:
Coffee Break
(ends 5:30 PM)
San Diego Poster Session 6 [4:30-7:30]
Posters 4:30-7:30
$\text{G}^2\text{M}$: A Generalized Gaussian Mirror Method to Boost Feature Selection Power
$\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
3D Equivariant Visuomotor Policy Learning via Spherical Projection
4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
A Bayesian Approach to Contextual Dynamic Pricing using the Proportional Hazards Model with Discrete Price Data
A Beyond-Worst-Case Analysis of Greedy k-means++
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
Accelerated Evolving Set Processes for Local PageRank Computation
Accelerating 3D Molecule Generative Models with Trajectory Diagnosis
A Counterfactual Semantics for Hybrid Dynamical Systems
ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
Actor-Free Continuous Control via Structurally Maximizable Q-Functions
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
Adaptive Discretization for Consistency Models
Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
Adaptive Time Encoding for Irregular Multivariate Time-Series Classification
Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration
Adversarial Diffusion for Robust Reinforcement Learning
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
A geometric framework for momentum-based optimizers for low-rank training
Agnostic Continuous-Time Online Learning
A Gradient Guided Diffusion Framework for Chance Constrained Programming
Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
AlphaBeta is not as good as you think: a simple random games model for a better analysis of deterministic game-solving algorithms
Amortized Active Generation of Pareto Sets
A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection
A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
Analog Foundation Models
Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
An Effective Levelling Paradigm for Unlabeled Scenarios
An Ellipsoid Algorithm for Online Convex Optimization
AneuG-Flow: A Large-Scale Synthetic Dataset of Diverse Intracranial Aneurysm Geometries and Hemodynamics
Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals
An Information-theoretical Framework for Understanding Out-of-distribution Detection with Pretrained Vision-Language Models
An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
Approximate Domain Unlearning for Vision-Language Models
Approximation theory for 1-Lipschitz ResNets
A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding
AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science
Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra
Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
Attention on the Sphere
AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
Attention with Trained Embeddings Provably Selects Important Tokens
AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
Automated Model Discovery via Multi-modal & Multi-step Pipeline
Automatic Auxiliary Task Selection and Adaptive Weighting Boost Molecular Property Prediction
Automaton Constrained Q-Learning
AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
Availability-aware Sensor Fusion via Unified Canonical Space
Backward Conformal Prediction
Bag of Tricks for Inference-time Computation of LLM Reasoning
Behavior Injection: Preparing Language Models for Reinforcement Learning
Better Language Model Inversion by Compactly Representing Next-Token Distributions
Better Training Data Attribution via Better Inverse Hessian-Vector Products
Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
Beyond Benign Overfitting in Nadaraya-Watson Interpolators
Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial Complexes
Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models
BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
Boosting Adversarial Transferability with Spatial Adversarial Alignment
Bounds on the computational complexity of neurons due to dendritic morphology
BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts
Bridging Expressivity and Scalability with Adaptive Unitary SSMs
Bridging Theory and Practice in Link Representation with Graph Neural Networks
BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
CADMorph: Geometry‑Driven Parametric CAD Editing via a Plan–Generate–Verify Loop
CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs
Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
CAT: Content-Adaptive Image Tokenization
Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
Causal Discovery and Inference through Next-Token Prediction
Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
CG-SSL: Concept-Guided Self-Supervised Learning
CHASM: Unveiling Covert Advertisements on Chinese Social Media
ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs
CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections
ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement Learning
Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations
Collapsing Taylor Mode Automatic Differentiation
Color Conditional Generation with Sliced Wasserstein Guidance
Coloring Learning for Heterophilic Graph Representation
Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
Compositional Neural Network Verification via Assume-Guarantee Reasoning
Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
Compute-Optimal Scaling for Value-Based Deep RL
Conditional Distribution Compression via the Kernel Conditional Mean Embedding
Conditional Representation Learning for Customized Tasks
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
Conformal Linguistic Calibration: Trading-off between Factuality and Specificity
Confusion-Driven Self-Supervised Progressively Weighted Ensemble Learning for Non-Exemplar Class Incremental Learning
Connectome-Based Modelling Reveals Orientation Maps in the Drosophila Optic Lobe
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
Constrained Linear Thompson Sampling
ContextAgent: Context-Aware Proactive LLM Agents with Open-world Sensory Perceptions
Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis
Contextual Tokenization for Graph Inverted Indices
Continual Optimization with Symmetry Teleportation for Multi-Task Learning
Controllable Human-centric Keyframe Interpolation with Generative Prior
Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
Co-Regularization Enhances Knowledge Transfer in High Dimensions
Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers
Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems
Counterfactual Identifiability via Dynamic Optimal Transport
Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
Covariate-moderated Empirical Bayes Matrix Factorization
C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors
CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases
DeCaFlow: A deconfounding causal generative model
Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery
Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
Deep Learning with Plausible Deniability
Deep Tree Tensor Networks
DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
Degradation-Aware Dynamic Schrödinger Bridge for Unpaired Image Restoration
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
Dependency Parsing is More Parameter-Efficient with Normalization
Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation
DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
DiffE2E: Rethinking End-to-End Driving with a Hybrid Diffusion-Regression-Classification Policy
Differentially Private High-dimensional Variable Selection via Integer Programming
Differential Privacy on Fully Dynamic Streams
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models
Direct Fisher Score Estimation for Likelihood Maximization
DISC: Dynamic Decomposition Improves LLM Inference Scaling
DISCO: DISCrete nOise for Conditional Control in Text-to-Image Diffusion Models
DISCO: Disentangled Communication Steering for Large Language Models
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
Discovering Compositional Hallucinations in LVLMs
Discovering Opinion Intervals from Conflicts in Signed Graphs
Discovering Symbolic Partial Differential Equation by Abductive Learning
DisMo: Disentangled Motion Representations for Open-World Motion Transfer
Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
dKV-Cache: The Cache for Diffusion Language Models
Do different prompting methods yield a common task representation in language models?
Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation
Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models
Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
DOTA: Distributional Test-time Adaptation of Vision-Language Models
DOVTrack: Data-Efficient Open-Vocabulary Tracking
DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
DreamLight: Towards Harmonious and Consistent Image Relighting
DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Dropout Regularization Versus l2-Penalization in the Linear Model
DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules
Dynamic Diameter in High-Dimensions against Adaptive Adversary and Beyond
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
Dynamic Regret Reduces to Kernelized Static Regret
Dynamic Semantic-Aware Correlation Modeling for UAV Tracking
EDBench: Large-Scale Electron Density Data for Molecular Modeling
Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations
Efficient Large Language Model Inference with Neural Block Linearization
Efficiently Verifiable Proofs of Data Attribution
Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
Embedding Principle of Homogeneous Neural Network for Classification Problem
Embodied Crowd Counting
Emergence and Evolution of Interpretable Concepts in Diffusion Models