AIConfPaper
← All conferences

ICML 2026 Accepted Papers

The full list of 6,634 papers accepted at ICML 2026 (International Conference on Machine Learning). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Poster: 6,060Spotlight: 406Oral: 168
  1. Towards Diverse Scientific Hypothesis Search with Large Language ModelsPoster
  2. Towards Docking-oriented De Novo Ligand Design via Gradient InversionPoster
  3. Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered BackgroundPoster
  4. Towards Efficient LLMs Annealing with Principled Sample SelectionSpotlight
  5. Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought CompressionPoster
  6. Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-LearningPoster
  7. Towards Execution-Grounded Automated AI ResearchPoster
  8. Towards Fair Sequential Decision-Making: A Causal Decomposition ApproachOral
  9. Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel GenerationPoster
  10. Towards Fine-grained Robustness: Attention-guided Test-time Prompt Tuning for Vision-Language ModelsPoster
  11. Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context DiscrepancyPoster
  12. Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding AnalysisPoster
  13. Towards Functional Correctness of Large Code Models with Selective GenerationPoster
  14. Towards Generalizable EEG-to-fMRI Synthesis via a Unified, Context-Aware Prompting FrameworkPoster
  15. Towards Generative Graph Matching for Graph Edit Distance ComputationPoster
  16. Towards Hierarchy–Uniformity Equilibrium: Recovering Semantic Depth in Hypergraph Contrastive LearningOral
  17. Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive GroundingSpotlight
  18. Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMsOral
  19. Towards Multimodal Large Language Models with Both Training and Inference EfficiencyPoster
  20. Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM TrainingPoster
  21. Towards One-for-All Anomaly Detection for Tabular DataPoster
  22. Towards One-to-Many Temporal GroundingPoster
  23. Towards Optimal Robustness in Learning-Augmented PagingSpotlight
  24. Towards Parameter-Free Temporal Difference LearningPoster
  25. Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy OptimizationSpotlight
  26. Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action ModelsPoster
  27. Towards Professional-Grade Financial Agents: Benchmarking, Tooling, and Structured ReasoningPoster
  28. Towards Realistic Lifelong Re-identification: Identity Recurrence with Changing ClothesPoster
  29. Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level WatermarkingPoster
  30. Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation PipelinesPoster
  31. Towards Robust Human-AI Complementarity under UncertaintyPoster
  32. Towards Rule-Based Knowledge Sharing in Federated LearningPoster
  33. Towards Scalable and Consistent 3D EditingPoster
  34. Towards Seed-Robust Safety Alignment in Text-to-Image ModelsPoster
  35. Towards Solving the Gilbert-Pollak Conjecture via Large Language ModelsPoster
  36. Towards Spectroscopy: Susceptibility Clusters in Language ModelsPoster
  37. Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only InterventionsPoster
  38. Towards Sub-second Biological Foundation Model Infrastructure: A Quantized Consistency Diffusion Framework for Molecular DockingOral
  39. Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear RegressionPoster
  40. Towards Trustworthy Video Anomaly Understanding: A Class-Guided Chain-of-Evaluation Metric and An Anomaly-focused Meta-BenchmarkPoster
  41. Towards Trustworthy and Identifiable Virtual Face GenerationPoster
  42. Towards Understanding Adam Convergence on Highly Degenerate PolynomialsSpotlight
  43. Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to AlgorithmPoster
  44. Towards Understanding Generalization of Federated Adversarial Learning: Perspective of Algorithmic StabilityPoster
  45. Towards Understanding Massive Activations in Attention Sink MechanismPoster
  46. Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information DecompositionPoster
  47. Towards Understanding Steering StrengthPoster
  48. Towards Understanding the Dynamics of Low-Rank AdaptationPoster
  49. Towards Unified Multimodal PretrainingSpotlight
  50. Towards Uniformity and Alignment for Multimodal Representation LearningPoster
  51. Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation ModelsPoster
  52. Towards Whole-corpus Reconstruction of Heterogeneous RAG Knowledge BasesPoster
  53. Towards a Holistic Understanding of Selection Bias for Causal Effect IdentificationPoster
  54. Towards a Science of AI Agent ReliabilityPoster
  55. Towards a Unified Generative Model for Scarce Time Series with Domain ExpertsPoster
  56. Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological AttributionSpotlight
  57. Towards the Training of Deeper Predictive Coding Neural NetworksPoster
  58. TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level LabelsPoster
  59. TraceRouter: Robust Safety for Large Foundation Models via Path-Level InterventionPoster
  60. Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak DetectionPoster
  61. Tracing the Emergence of Symbol Grounding in Multimodal Language ModelsPoster
  62. Tracing the Persona Circuit: How Large Language Models Encode and Express Character TraitsPoster
  63. Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement LearningPoster
  64. Tractable Expected Information Gains for Exponential Family PosteriorsPoster
  65. Trading Complexity for Expressivity Through Structured Generalized Linear Token MixingPoster
  66. Train Once, Reuse Everywhere: Generalizable Implicit ICL by Routing AttentionPoster
  67. Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates HallucinationsSpotlight
  68. Trainable Nonexpansive Denoisers for Contractive Image ReconstructionPoster
  69. Training AI Co-Scientists Using Rubric RewardsPoster
  70. Training Data Efficiency in Multimodal Process Reward ModelsPoster
  71. Training Deep Spiking Neural Networks without NormalizationPoster
  72. Training Diffusion Language Models for Black-Box OptimizationSpotlight
  73. Training LLM Agents to Empower HumansPoster
  74. Training Language Model Agents to Find Vulnerabilities with CTF-DojoPoster
  75. Training Prompt Matters: State-Adaptive Optimization for Robust Fine-TuningPoster
  76. Training with Honeypots: Reshaping How LLMs FailPoster
  77. Training-Free Adaptation of Diffusion Models via Doob's $h$-TransformPoster
  78. Training-Free Adversarial Robustness in Deep Learning MRI ReconstructionPoster
  79. Training-Free Bayesian Filtering with Generative EmulatorsOral
  80. Training-Free Coverless Multi-Image Steganography with Access ControlPoster
  81. Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy GuidancePoster
  82. Training-Free Guided Diffusion for Planning: A Unified Framework via Doob’s h-Transform with Safety GuaranteesPoster
  83. Training-Free Hashing-Based Attention via Binary Principal ComponentsPoster
  84. Training-Free Hierarchical Working Memory for Small Language Model AgentsPoster
  85. Training-Free Multimodal Large Language Model OrchestrationPoster
  86. Training-Free Rate-Distortion-Perception Traversal With DiffusionPoster
  87. Training-Free Sparse Attention for Fast Video Generation via Offline Layer-Wise Sparsity Profiling and Online Bidirectional Co-ClusteringPoster
  88. Training-Trajectory-Aware Token SelectionPoster
  89. Training-free Composition of Pre-trained GFlowNets for Multi-Objective GenerationPoster
  90. Training–Inference Consistent Segmented Execution for Long-Context LLMsPoster
  91. Trajectory Consistency for One-Step Generation on Euler Mean FlowsPoster
  92. Trajectory Seriation via Spectral Tangent Alignment and Global EmbeddingPoster
  93. Trajectory Stitching for Solving Inverse Problems with Flow-Based ModelsPoster
  94. Trajectory-Aware Certified Decentralized Unlearning via SGD StabilityPoster
  95. Trajectory-Aware Heuristic Learning for Combinatorial SearchPoster
  96. Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-FeedbackPoster
  97. Trajectory-Level Data Augmentation for Offline Reinforcement LearningPoster
  98. Trajectory-Level Speculative Decoding for Diffusion Language ModelsPoster
  99. Trajectory-Stabilized Inference for Diffusion-Based Video InpaintingPoster
  100. TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image DetectionPoster
  101. TransLight: Image-Guided Customized Lighting Control with Generative DecouplingPoster
  102. TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal EstimationPoster
  103. Transfer Learning in High-dimensional Ising ModelsPoster
  104. Transfer Learning in Nonparametric Regression with Deep ReLU NetworksPoster
  105. Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real DeploymentPoster
  106. Transform Trained Transformer for Accelerating Native 4K Video GenerationPoster
  107. Transformed Latent Variable Multi-Output Gaussian ProcessesPoster
  108. Transformer Circuits Can Realize Clustering AlgorithmsSpotlight
  109. Transformers Can Learn Posterior Predictive Distributions In-ContextPoster
  110. Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient DescentPoster
  111. Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMsPoster
  112. Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right DataPoster
  113. Transformers learn factored representationsPoster
  114. Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But DifferentlyPoster
  115. Transforming Weather Data from Pixel to Latent SpaceOral
  116. Transitive Representation Learning Enhances Histopathology AnnotationPoster
  117. Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model AlignmentPoster
  118. Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale GeometriesPoster
  119. Transport Clustering: Solving Low-Rank Optimal Transport via ClusteringPoster
  120. Transport and Merge: Cross-Architecture Merging for Large Language ModelsPoster
  121. Transport or Discard: Robust Unbalanced Optimal Transport for Cross-Domain Policy AdaptationPoster
  122. Transporting Task Vectors across Different Architectures without TrainingPoster
  123. Treatment Responder Classification with AbstentionSpotlight
  124. Tree-Structured Orthonormal Decomposition of the Aitchison SimplexPoster
  125. TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable EvolutionPoster
  126. TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree ModelingPoster
  127. Trees to Flows and Back: Unifying Decision Trees and Diffusion ModelsPoster
  128. Tri-Scale Neural ODEs for Continuous Multi-Omics Disease ModelingPoster
  129. TriAttention: Efficient Long Reasoning with Trigonometric KV CompressionPoster
  130. TriForces: Augmenting Atomistic GNNs for Transferable RepresentationsPoster
  131. Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity SchedulesPoster
  132. Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal FusionPoster
  133. TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code GenerationPoster
  134. Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial FinetuningSpotlight
  135. Trust Functions: Near Lossless Weak-to-Strong Generalization by Learning to Trust the Weak TeacherPoster
  136. Trust Region Inverse Reinforcement LearningPoster
  137. Trust Region Masking for Long-Horizon LLM Reinforcement LearningPoster
  138. Trust-Region Diffusion Policies for Massively Parallel On-Policy RLPoster
  139. Trust3R: Unifying Feed-Forward Pointmap Prediction and Evidential Learning for Trust-Aware 3D ReconstructionPoster
  140. Trustworthy Federated Label Distribution Learning under Annotation Quality DisparityPoster
  141. TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern ClassificationPoster
  142. TruthRL: Incentivizing Truthful LLMs via Reinforcement LearningPoster
  143. Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy VerifierPoster
  144. TsLLM: Augmenting LLMs for General Time Series Understanding and PredictionPoster
  145. Tucker Attention: A generalization of approximate attention mechanismsPoster
  146. TuneAhead: Predicting Fine-tuning Performance Before Training BeginsPoster
  147. Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-ParityPoster
  148. Tuning-Free One-Class Discriminant Learning for Tabular Anomaly DetectionPoster
  149. Turbo Connection: Reasoning as Information Flow from Higher to Lower LayersPoster
  150. Turbo4DGen: Ultra-Fast Acceleration for 4D GenerationPoster
  151. TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and OptimizationPoster
  152. Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language NavigationPoster
  153. Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual LearningPoster
  154. Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM JudgesPoster
  155. Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream EnvironmentsPoster
  156. Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order OptimizationPoster
  157. Tvcache: A Tool-Value Cache for Post-Training LLM AgentsPoster
  158. Twice Sequential Monte Carlo for Tree SearchPoster
  159. TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM QuantizationPoster
  160. TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital TwinsPoster
  161. Twins: Learn to Predict Unified Representations with Focal LossPoster
  162. Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion ModelsPoster
  163. Two Modalities Are Better Than One: Efficient Adversarial Purification via Multimodal Diffusion ModelsPoster
  164. Two-Layer Linear Auto-Regressive Models Estimate Latent StatesPoster
  165. Two-Parameter Flows for Learning Population Dynamics of Physical SystemsPoster
  166. Two-Stage Unit Tying for Simplifying Differentiable Logic Gate NetworksPoster
  167. Two-dimensional quantization for geometry-aware audio codingPoster
  168. U$^3$CF: Unbiased, Unconfounding, and Unified Causal Framework for Multi-Target Domain AdaptationPoster
  169. U-Cast: A Surprisingly Simple Frontier Probabilistic AI Weather ForecasterPoster
  170. UAV$^2$: A Unified and Adaptive Scheduling Framework for UAV Autopilot System with Reinforcement LearningPoster
  171. UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation ModelsPoster
  172. UCB Exploration for Fixed-Budget Bayesian Best Arm IdentificationPoster
  173. UCPO: Uncertainty-Aware Policy OptimizationPoster
  174. UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion ModelsSpotlight
  175. UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image GenerationPoster
  176. UGround: Towards Unified Visual Grounding with Unrolled TransformersPoster
  177. UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote SensingPoster
  178. UI2Code^N: UI-to-Code Generation as Interactive Visual OptimizationPoster
  179. UMEM: Unified Memory Extraction and Management Framework for Generalizable MemoryPoster
  180. UNIVERSAL REPRESENTATION OF GENERALIZED CONVEX FUNCTIONS AND THEIR GRADIENTSPoster
  181. UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse ProblemsPoster
  182. URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot GeneralizationPoster
  183. USE : A Unified Self-Ensembling Framework for Test-Time Prompt TuningPoster
  184. Ubiquity of Homeostatic Hebbian Dynamics in Regularized LearningPoster
  185. UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon ScenariosPoster
  186. UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus AlgebraPoster
  187. Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov–Arnold NetworksPoster
  188. UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA UnlearningPoster
  189. UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action BranchingPoster
  190. Unbiased Alignment for Large Language Models with Noisy PreferencesPoster
  191. Unbiased Dynamic Pruning for Efficient Group-Based Policy OptimizationPoster
  192. Unbiased Principles, Robust RewardsPoster
  193. Unbiased Reward Modeling from Implicit PreferencePoster
  194. Unbiased and Second-Order-Free Training for High-Dimensional PDEsPoster
  195. Uncertainty-Aware Clarification in LLM Agents with Information GainPoster
  196. Uncertainty-Constrained Trustworthiness for Graph LearningPoster
  197. Uncertainty-Guided Exploration and Stable Planning for Sparse-Reward Manipulation from Limited DemonstrationsPoster
  198. Uncovering Bias Mechanisms in Observational StudiesPoster
  199. Uncovering Competency Gaps in Large Language Models and Their BenchmarksPoster
  200. Uncovering Grounding IDs: How External Cues Shape Multi-Modal BindingPoster
  201. Uncovering Hidden Triggers: Backdoor Attribution in Language ModelsPoster
  202. Uncovering Latent Communication Patterns in Brain Networks via Adaptive Flow RoutingPoster
  203. Uncovering the Gradient Geometry of Long CoT: A Spectral-guided Approach to Reasoning DistillationPoster
  204. Uncovering the Latent Potential of Deep Intermediate RepresentationsSpotlight
  205. Understand and Accelerate Memory Processing Pipeline for Large Language Model InferencePoster
  206. Understanding Behavior Cloning with Action QuantizationPoster
  207. Understanding Data Temporality Impact on Large Language Models Pre-trainingPoster
  208. Understanding Deep Representation Learning via Layerwise Feature Compression and DiscriminationPoster
  209. Understanding Dynamic Compute Allocation in Recurrent TransformersPoster
  210. Understanding Dynamics of Adam in Zero-Sum Games: An ODE ApproachPoster
  211. Understanding Generalization and Forgetting in In-Context Continual LearningPoster
  212. Understanding Generalization from Embedding Dimension and Distributional ConvergencePoster
  213. Understanding LoRA as Knowledge Memory: An Empirical AnalysisPoster
  214. Understanding MARS: When Scaling Momentum Provably HelpsPoster
  215. Understanding Multimodal Learning: A Loss Landscape Smoothness PerspectivePoster
  216. Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation TransitionsPoster
  217. Understanding Private Learning From Feature PerspectivePoster
  218. Understanding Reasoning Collapse in LLM Agent Reinforcement LearningOral
  219. Understanding SAM through Minimax PerspectivePoster
  220. Understanding Self-Supervised Learning via Latent Distribution MatchingSpotlight
  221. Understanding Transfer Learning of RNA Foundation Models on Downstream TasksPoster
  222. Understanding Truncated Positional Encodings for Graph Neural NetworksPoster
  223. Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMsPoster
  224. Understanding the Ability of LLMs to Handle Character-Level PerturbationPoster
  225. Understanding the Gaps in Satisficing BanditsPoster
  226. Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPOPoster
  227. Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network RepresentationPoster
  228. Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving LinearizationPoster
  229. Uni-DocRobust: Universal Plug-and-Play Robustness Enhancement for Multi-modal LLMs via Feature RestorationPoster
  230. UniCoD: Enhancing Robot Policy via Unified Continuous and Discrete Representation LearningPoster
  231. UniCode: Augmenting Evaluation for Code ReasoningPoster
  232. UniDrag: Unified Multi-Field Prediction and Robust Shape Optimization for Vehicle AerodynamicsPoster
  233. UniFLoW: Universal Multi-Modal Federated LoRA Fine-Tuning Framework with Analytical AggregationPoster
  234. UniFast-HGR: Scalable and Efficient Maximal Correlation for Multimodal ModelsPoster
  235. UniMapping: Unified SLAM Framework for Map-Centric Embodied PerceptionSpotlight
  236. UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-AnalysisPoster
  237. UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and TextureSpotlight
  238. UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation ParadigmsPoster
  239. UniRTL: Unifying Code and Graph for Robust RTL Representation LearningPoster
  240. UniSVQ: 2-bit Unified Scalar-Vector QuantizationPoster
  241. UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time ScalingPoster
  242. UniSparse: Combining Weight Pruning and Spike Sparsification in Spiking Neural NetworksPoster
  243. Unified Episodic and Semantic Memory via Modulating Transformer FeedForward LayersPoster
  244. Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to UnificationPoster
  245. Unified Multimodal Visual Tracking with Dual Mixture-of-ExpertsPoster
  246. Unified Safe In-context Image Generation in Multimodal Diffusion TransformersPoster
  247. Unified Time Series Explanations via Semi-Amortized Optimization and Instance-level Multi-Expert Knowledge DistillationPoster
  248. Unifying Adversarial Robustness and Training Across Text Scoring ModelsPoster
  249. Unifying Deep Stochastic Processes for Image EnhancementPoster
  250. Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image RestorationPoster
  251. Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted PretrainingPoster
  252. Unifying Low Dimensional Spectra in Deep LearningPoster
  253. Unifying Masked Diffusion Models with Various Generation Orders and BeyondSpotlight
  254. Unifying Stacking and Cascading for Efficient Ensemble InferencePoster
  255. Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous DatasetsPoster
  256. Unifying and Optimizing Data Values for Selection via Sequential Decision-MakingSpotlight
  257. Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and GenerationPoster
  258. Unitary Convolutions for Message-passing and Positional Encodings on Directed GraphsPoster
  259. Universal Algorithm-Implicit LearningPoster
  260. Universal Approximation with Softmax AttentionPoster
  261. Universal Learning of Nonlinear DynamicsPoster
  262. Universal Multiclass Transductive Online LearningPoster
  263. Universal One-third Time Scaling in Learning Peaked DistributionsPoster
  264. Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMsPoster
  265. Universal Redundancies in Time Series Foundation ModelsSpotlight
  266. Universal Skeleton Understanding via Differentiable Rendering and MLLMsPoster
  267. Universality, Function Composition, and Algorithm Emulation All In-ContextPoster
  268. Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMsPoster
  269. Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning EvaluationsPoster
  270. Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood ConstraintsPoster
  271. Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public DataPoster
  272. Unlearning’s Blind Spots: Over‑Unlearning and Prototypical Relearning AttackPoster
  273. Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level OptimizationPoster
  274. Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object DetectionPoster
  275. Unlocking Cross-Modal Biosignal Synthesis: A Temporally-Aware VAE-Diffusion ModelPoster
  276. Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian NoisePoster
  277. Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction TuningPoster
  278. Unlocking Zero-Shot Geospatial Reasoning via Indirect RewardsPoster
  279. Unlocking the Potential of Continual Model Merging: An ODE PerspectivePoster
  280. Unpaired Visual Editing with Self-Consistent Flow MatchingPoster
  281. Unraveling Syntax: Language Modeling and the Substructure of GrammarsSpotlight
  282. Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using AgentsPoster
  283. Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal HypergraphsPoster
  284. Unsupervised Camouflaged Object Detection with Dual-Eigenvector Spectral Pseudo-Labeling and Contrastive RefinementPoster
  285. Unsupervised Diffusion for Combinatorial Optimization via Adjoint MatchingPoster
  286. Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces IdentifiabilityPoster
  287. Unsupervised Hierarchical Skill DiscoveryPoster
  288. Unsupervised Mode Discovery for Fine-tuning Multimodal Generative PoliciesPoster
  289. Unsupervised Neural Langevin Sampler for Mixed Integer Linear ProgrammingPoster
  290. Unsupervised Partner Design Enables Robust Ad-hoc TeamworkOral
  291. Unsupervised Process-Aware Coreset Selection for In-Context LearningPoster
  292. Untied Ulysses: Memory-Efficient Context Parallelism via Headwise ChunkingPoster
  293. Unveiling And Addressing Dimensional Collapse In Vector Quantization Models Via Codebook RegularizationPoster
  294. Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific OptimizationPoster
  295. Unveiling Prior-data Fitted Networks on Causal Effect Estimation: Pre-training or Finetuning?Poster
  296. Unveiling the Entropy Dynamics of Chain-of-Thought ReasoningPoster
  297. Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error ReductionPoster
  298. Unveiling the Role of Data Uncertainty in Tabular Deep LearningPoster
  299. Unveiling the Structure of Do-Calculus Reasoning via Derivation GraphsPoster
  300. Unveiling the Visual Counting Bottleneck in Vision-Language ModelsPoster
  301. Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex SetsPoster
  302. UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial RepresentationsPoster
  303. UrbanMLLM: Joint Learning of Cross-view Imagery for Urban UnderstandingPoster
  304. Use What You Know: Causal Foundation Models with Partial GraphsPoster
  305. User-Aware Active Knowledge Acquisition for Emotional Support DialoguePoster
  306. Utility Boundary of Dataset Distillation: Scaling and Coverage LawsPoster
  307. Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuningPoster
  308. Utonia: Toward One Encoder for All Point CloudsPoster
  309. V-ABS: Action-Observer Driven Beam Search for Dynamic Visual ReasoningPoster
  310. V1: Unifying Generation and Self-Verification for Parallel ReasonersPoster
  311. VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language ModelsOral
  312. VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector AnimationPoster
  313. VBA: Vector Bundle Attention for Intrinsically Geometric Representation LearningPoster
  314. VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and EditingPoster
  315. VDW-GNNs: Vector diffusion wavelets for geometric graph neural networksPoster
  316. VELR: Efficient Video Reward Feedback via Ensemble Latent Reward ModelsPoster
  317. VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender SystemsPoster
  318. VEQ: Modality-Adaptive Quantization for MoE Vision-Language ModelsPoster
  319. VERA-V: Variational Inference Framework for Jailbreaking Vision-Language ModelsPoster
  320. VFMF: Dense Forecasting by Generating Foundation Model FeaturesPoster
  321. VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range ConsistencySpotlight
  322. VIA-SD: Verification via Intra-Model Routing for Speculative DecodingPoster
  323. VIBE: Disentangling Social Dynamics via Kinematics-Informed Variational Inference for Behavioral EmotionPoster
  324. VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language InferencePoster
  325. VIPO: Value Function Inconsistency Penalized Offline Reinforcement LearningPoster
  326. VIRUS: Injecting Persistent Cognitive Pathogens into Stateful Zero-Shot Object Navigation AgentsPoster
  327. VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World ModelsPoster
  328. VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic ModelPoster
  329. VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action ModelsPoster
  330. VLANeXt: Recipes for Building Strong VLA ModelsPoster
  331. VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World ModelPoster
  332. VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language ModelsPoster
  333. VPD-100K: Towards Generalizable and Fine-grained Visual Privacy ProtectionPoster
  334. VR-Thinker: Boosting Multimodal Reward Models through Think with Image ReasoningPoster
  335. VSCD: Video-based Scene Change Detection in Unaligned ScenesPoster
  336. VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal LearningPoster
  337. Value Aggregation with Uncertainty in Online Decentralized MARLPoster
  338. Value-as-Return: A Two-Stage Framework to Align on the Optimal Score FunctionPoster
  339. Var-JEPA: Variational Joint-Embedding Predictive Architecture – Bridging Predictive and Generative Self-Supervised LearningPoster
  340. Variable Clustering via Distributionally Robust Nodewise RegressionPoster
  341. Variable-Length Tokenization via Learnable Global Merging for Diffusion TransformersPoster
  342. Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic EnvironmentsPoster
  343. Variance-Reduced $(\varepsilon, \delta)-$Unlearning using Forget Set GradientsPoster
  344. Variance-Reduced Zeroth-Order Langevin Dynamics for Non-Log-Concave Black-Box Sampling and Inverse ProblemsPoster
  345. Variational Adapter for Cross-modal Similarity RepresentationPoster
  346. Variational Bayesian Flow Network for Graph GenerationPoster
  347. Variational Entropic Optimal TransportPoster
  348. Variational Flow Maps: Make Some Noise for One-Step Conditional GenerationPoster
  349. Variational Inference for Uncertain Optimal Transport via Sinkhorn ParametrizationPoster
  350. Variational Learning for Insertion-based GenerationSpotlight
  351. Variational Learning of Disentangled RepresentationsPoster
  352. Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts TransformersPoster
  353. Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence AcceptancePoster
  354. Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometryPoster
  355. VeRO: An Evaluation Harness for Agents to Optimize AgentsPoster
  356. VecDesigner: Exploring Visual Guidance and Structural Consistency for Semantic TypographyPoster
  357. VecMol: Vector-Field Representations for 3D Molecule GenerationPoster
  358. Vector Linking via Cross-Model Local Isometric ConsistencyPoster
  359. Vector Quantization using Gaussian Variational AutoencoderPoster
  360. VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector GraphsSpotlight
  361. Veda: Scalable Video Diffusion via Distilled Sparse AttentionPoster
  362. Vegas: Self-Speculative Decoding with Verification-Guided Sparse AttentionPoster
  363. VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability DiagnosticsOral
  364. Verbalized Bayesian PersuasionPoster
  365. Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM DiversityPoster
  366. VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based VerificationPoster
  367. Verifiable Multimodal Reasoning: Fact-level Attribution with Multimodal SourcesPoster
  368. Verifying Meta-Awareness via Predictive Rewards in Reasoning ModelsPoster
  369. Very Efficient Listwise Multimodal Reranking for Long DocumentsPoster
  370. ViEEG: Hierarchical Visual Neural Representation for EEG Brain DecodingPoster
  371. ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language ModelsPoster
  372. ViTok-v2: Scaling Native-Resolution Autoencoders to 5BPoster
  373. Vibe Checker: Aligning Code Evaluation with Human PreferencePoster
  374. VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video UnderstandingPoster
  375. Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video UnderstandingPoster
  376. Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement LearningOral
  377. Video-MTR: Reinforced Multi-Turn Reasoning for Long Video UnderstandingPoster
  378. Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy DistillationPoster
  379. Video-SVD: Efficient Video Diffusion via Orthogonal Basis CompositionPoster
  380. Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved ReasoningPoster
  381. Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent PretrainingPoster
  382. VideoBrain: Learning Adaptive Frame Sampling for Long Video UnderstandingPoster
  383. VideoFlexTok: Flexible-Length Coarse-to-Fine Video TokenizationSpotlight
  384. VideoKR: Towards Knowledge- and Reasoning-Intensive Video UnderstandingSpotlight
  385. VideoLoom: A Video Large Language Model for Joint Spatial-Temporal UnderstandingPoster
  386. VideoSEAL: Separating Planning from Answer Authority for Agentic Long Video UnderstandingPoster
  387. VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object SegmentationPoster
  388. VideoSeeker: Native Interleaved Clue Seeking for Long Video Multi-Hop ReasoningPoster
  389. VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-VideosPoster
  390. VideoTrace-R1: Long Video-based Retrieval-Augmented Generation via Temporal Path Graph UnderstandingPoster
  391. VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement LearningPoster
  392. View Space: Learning Representation across Arbitrary GraphsPoster
  393. ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Diffusion ModelsPoster
  394. VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory GraphPoster
  395. Vision Language Models Cannot Reason About Physical TransformationPoster
  396. Vision Transformer Finetuning Benefits from Non-Smooth ComponentsPoster
  397. Vision in One Vector: Implicit Visual Compression with Diffusion Foundation ModelsPoster
  398. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language ModelsPoster
  399. Vision-Language-Action Pretraining from Large-Scale Human VideosPoster
  400. Vision-aligned Latent Reasoning for Multi-Modal Large Language ModelPoster
  401. VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal ReasoningPoster
  402. VisionWebDev: A Hierarchical Benchmark for Visual Website Development with Agent VerificationSpotlight
  403. Visual Implicit Autoregressive ModelingPoster
  404. Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual ComprehensionPoster
  405. Visual Persuasion: What Influences Decisions of Vision-Language Models?Poster
  406. VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain KnowledgePoster
  407. VisualScore: Learning Holistic Visual Quality Scores via Multi-Task ReasoningPoster
  408. VividCam: Learning Unconventional Camera Motions from Virtual Synthetic VideosPoster
  409. VlogReward: Learning Multi-Dimensional Evaluation for Vlog EditingPoster
  410. VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source AudioPoster
  411. Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time TransductionPoster
  412. Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement LearningPoster
  413. WAVE: Window-Aware Vocabulary-Efficient Early-Exit for Training-Free LLM AccelerationPoster
  414. WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field ConvolutionSpotlight
  415. WET: Mitigating World-Conditioned Knowledge Conflicts via World Entropy TetheringPoster
  416. WEVSR: Adapting Video Diffusion Generators to Real-World Video Super‑Resolution with Wavelet-Enhanced VAE EncoderPoster
  417. WF-Bench: A Benchmark for Neural-Network WaveFunction Expressivity and Scaling LawsPoster
  418. WFR-MFM: One-Step Inference for Dynamic Unbalanced OTPoster
  419. WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric ModelingPoster
  420. WISE: World Knowledge-Informed Semantic Evaluation for Text-to-Image GenerationPoster
  421. WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language ModelsPoster
  422. WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient ReasoningPoster
  423. WUSH: Near-Optimal Adaptive Transforms for LLM QuantizationPoster
  424. Wait, Wait, Wait... Why Do Reasoning Models Loop?Spotlight
  425. Walrus: A Cross-domain Foundation Model for Continuum DynamicsSpotlight
  426. WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM ServingPoster
  427. Wasserstein Geometry-Aware Adaptive Control via Meta-LearningPoster
  428. Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep EmbeddingPoster
  429. WatchLog: Efficient and Interpretable Event Reasoning for Endpoint Detection and Response Logs with Multimodal LLMsPoster
  430. WaterSIC: information-theoretically (near) optimal linear layer quantizationSpotlight
  431. Watermarking Graph Neural Networks via Explanations for Ownership ProtectionPoster
  432. Watermarking LLM Agent TrajectoriesPoster
  433. WaveSSM: Multiscale State-Space Models for Non-stationary Signal AttentionPoster
  434. WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast InferenceOral
  435. Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem PerformanceSpotlight
  436. Weak-to-Strong Generalization via Bregman Bias–Variance DecompositionPoster
  437. Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow EstimationPoster
  438. Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data SelectionPoster
  439. WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report GenerationPoster
  440. Weaving Graph over Tokens: Contextualizing Structured Sequences for LLMsPoster
  441. Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated LearningPoster
  442. WebWorld: A Large-Scale World Model for Web Agent TrainingPoster
  443. Weight Decay Improves Language Model PlasticityPoster
  444. Weight Updates as Activation Shifts: A Principled Framework for SteeringPoster
  445. Weight-Space Learning for Certifiable Few-shot Transfer LearningPoster
  446. Weight-sparse transformers have interpretable circuitsPoster
  447. Weights to Code: Extracting Interpretable Algorithms from the Discrete TransformerPoster
  448. Welfare-Optimal Classification with Accuracy AuctionsSpotlight
  449. Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL DivergencesPoster
  450. WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic SystemsSpotlight
  451. What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoTPoster
  452. What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?Spotlight
  453. What Does Flow-Matching Bring to TD-Learning?Poster
  454. What Does Preference Learning Recover from Pairwise Comparison Data?Poster
  455. What Does Thompson Sampling Optimize?Poster
  456. What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-ZoomPoster
  457. What If We Allocate Test-Time Compute Adaptively?Poster
  458. What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable DependenciesPoster
  459. What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information DecompositionPoster
  460. What Language is This? Ask Your Tokenizer.Poster
  461. What Linear Probes Miss: Multi-View Probing for Weight-Space LearningPoster
  462. What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic AnalysisPoster
  463. What Makes Synthetic Data Effective in Image SegmentationPoster
  464. What Makes Value Learning Efficient in Residual Reinforcement Learning?Spotlight
  465. What Makes a Desired Graph for Relational Deep Learning?Poster
  466. What Makes a Good Representation for Single-Cell Perturbation Prediction?Poster
  467. What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear RegressionPoster
  468. What Preferences Can—and Cannot—Predict in Multi-Agent Online LearningOral
  469. What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure CodePoster
  470. What Reward Structure Enables Efficient Sparse-Reward RL? A Proof-of-Concept with Policy-Aware Matrix CompletionPoster
  471. What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic CuriositySpotlight
  472. What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual ConditionsPoster
  473. What is Missing? Explaining Neurons Activated by Absent ConceptsPoster
  474. When AI Agents Compete for Jobs: Strategic Capabilities and Economic Dynamics of AI Labour MarketsPoster
  475. When AI Benchmarks Plateau: A Systematic Study of Benchmark SaturationPoster
  476. When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use AgentsPoster
  477. When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent SystemsPoster
  478. When Attributes Disagree: Gradient Conflict in Image Aesthetic AssessmentSpotlight
  479. When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use AgentsPoster
  480. When Can We Trust Survival Model Evaluation ?Poster
  481. When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPsPoster
  482. When Data Is Scarce: Scaling Sparse Language Models with Repeated TrainingPoster
  483. When Diffusion Language Models Hesitate: Detecting and Correcting Visual Hallucinations via Confidence FluctuationPoster
  484. When Distance Distracts: Representation Distance Bias in BT-Loss for Reward ModelsPoster
  485. When Do Diffusion Models learn to Generate Multiple Objects?Poster
  486. When Do Graph Foundation Models Transfer? A Data-Centric TheoryPoster
  487. When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path CompressionPoster
  488. When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum ControlPoster
  489. When Does Sparsity Mitigate the Curse of Depth in LLMsPoster
  490. When Drafts Evolve: Speculative Decoding Meets Online LearningPoster
  491. When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent SystemsPoster
  492. When Generalized Zero-Shot Learning Meets PU Learning: A Plug-and-Play Framework for Seen-Class Bias MitigationPoster
  493. When Is Rank-1 Enough? Geometry-Guided Initialization for Parameter-Efficient Fine-TuningPoster
  494. When Is Symbolic Regression Tractable?Poster
  495. When Iteration Helps and Hurts in Self-Training: Denoising vs. Signal ForgettingPoster
  496. When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent ReasoningPoster
  497. When LLMs Encounter Open-world Graph Learning: A Fresh View on Unlabeled Data UncertaintyPoster
  498. When Labelers Stay Silent: The Power of Ties in Cost-Effective Preference LearningPoster
  499. When Model Merging Breaks Routing: Training-Free Calibration for MoEPoster
  500. When More Data Doesn't Help: Limits of Adaptation in Multitask LearningPoster
  501. When More Experts Hurt: Underfitting in Multi-Expert Learning to DeferPoster
  502. When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent SystemsPoster
  503. When Preference Labels Fall Short: Aligning Diffusion Models from Real DataPoster
  504. When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMsPoster
  505. When RL Meets Adaptive Speculative Training: A Unified Training-Serving SystemPoster
  506. When Random Saliency Looks Trained: Architectural Center Bias in CNN InterpretabilityPoster
  507. When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied AgentsPoster
  508. When Sample Selection Bias Precipitates Model CollapsePoster
  509. When Search Goes Wrong: Red-Teaming Web-Augmented Large Language ModelsPoster
  510. When Shared Knowledge Hurts: Spectral Over-Accumulation in Model MergingPoster
  511. When Simple Problems Wear Complex Costumes: Improving Efficiency in LRM’s Adaptive ReasoningPoster
  512. When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMsPoster
  513. When Softmax Fails at the Top: Extreme‑Value Corrections for InfoNCEPoster
  514. When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment ApproachPoster
  515. When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming LoopPoster
  516. When does predictive inverse dynamics outperform behavior cloning?Poster
  517. When less gives more: bias from small dataset can speed up trainingPoster
  518. When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing ModelsOral
  519. When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context ReasoningPoster
  520. When to Think, When to Speak: Learning Disclosure Policies for Large Language Model ReasoningPoster
  521. When to Trust the Cheap Check: Weak and Strong Verification for ReasoningSpotlight
  522. Where Concept Erasure Should Occur: Concept–Layer Alignment in Text-to-Video Diffusion ModelsPoster
  523. Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image DetectionPoster
  524. Where Rectified Flows Leak: Characterizing Membership Signals Along the Interpolation PathPoster
  525. Where Signals Are Sparse, We Synthesize: Reinforcing Self-Corrective Reasoning in Vision–Language Models via Rollout AugmentationPoster
  526. Which Algorithms Can Graph Neural Networks Learn?Oral
  527. Which Heads Matter for Reasoning? RL-Guided KV Cache CompressionPoster
  528. Which LLM Multi-Agent Protocol to Choose?Poster
  529. Which Reasoning Traces Are Worth Generating Further? Data Curation for Training Reasoning ModelsPoster
  530. WhisperSplat: Lossless Steganography in 3D Gaussian SplattingPoster
  531. Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party EvaluationsPoster
  532. Who Gets Credit or Blame? Attributing Accountability in Modern AI SystemsPoster
  533. Who Said Neural Networks Aren't Linear?Poster
  534. Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety NeuronsPoster
  535. Who can we trust? LLM-as-a-jury for Comparative AssessmentPoster
  536. Who’s in Charge? Disempowerment Patterns in Real-World LLM UsagePoster
  537. Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning ModelsPoster
  538. Why Are Linear RNNs More Parallelizable?Poster
  539. Why DDIM Hallucinates More than DDPM: A Theoretical Analysis of Reverse DynamicsPoster
  540. Why Dedicated Critics: Eliminating Target Drift in Multi-Constraint RLPoster
  541. Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector AlignmentSpotlight
  542. Why Do We Need Warm-up? A Theoretical PerspectivePoster
  543. Why Linear Recurrent Memory Works in Partially Observable Reinforcement LearningSpotlight
  544. Why ReLU? A Bit-Model Dichotomy for Deep Network TrainingPoster
  545. Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial IntelligencePoster
  546. Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPOPoster
  547. Width Independent Bounds for the Local Lipschitz Constant of Deep Neural Networks at Random Initialization and after Lazy TrainingPoster
  548. Wikipedia in the Era of LLMs: Evolution and RisksPoster
  549. WildActor: Unconstrained Identity-Preserving Video GenerationPoster
  550. WildCat: Near-Linear Attention in Theory and PracticePoster
  551. WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop EnvironmentsPoster
  552. WinQ: Accelerating Quantization-Aware Training of Large Language Models around Saddle PointsPoster
  553. Winformer: Transcending Pairwise Similarity for Time-series GenerationPoster
  554. With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind SpotsPoster
  555. Words & Weights: Streamlining Multi-Turn Interactions via Co-AdaptationPoster
  556. Words Towards Explainability: Caption Label-Free Learning via Dual Loop Agentic Time Series CaptioningPoster
  557. World Guidance: World Modeling in Condition Space for Action GenerationPoster
  558. World-Model Inspired Emotion-aware Token Refinement for Training-Free Multimodal Emotion RecognitionSpotlight
  559. World-R1: Reinforcing 3D Constraints for Text-to-Video GenerationPoster
  560. World-Shaper: A Unified Framework for 360° Panoramic EditingPoster
  561. WorldCache: Accelerating World Models for Free via Heterogeneous Token CachingPoster
  562. WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local ViewsPoster
  563. WorldCompass: Reinforcement Learning for Long-Horizon World ModelsPoster
  564. WorldMirror: Universal 3D World Reconstruction with Any-Prior PromptingPoster
  565. WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World ModelingPoster
  566. WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled ConstraintsPoster
  567. X-EviProbe: Post-hoc Parameter-free Evidential Uncertainty Quantification for Frozen Graph Neural NetworksPoster
  568. X-MoGe: A Cross-Modal Adaptation Framework with Mixture-of-Experts and Geometry Guidance for Heterogeneous Collaborative PerceptionPoster
  569. XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge CompositionPoster
  570. XPERT: Expert Knowledge Transfer for Effective Training of Language ModelsPoster
  571. XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion RepresentationsOral
  572. XRPO: Pushing the Limits of GRPO with Targeted Exploration and ExploitationPoster
  573. XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative DecodingPoster
  574. XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the EdgePoster
  575. XYZFlow: Scaling Multidimensional Shortcut Flows for Efficient Generative ModelingPoster
  576. You Can Learn Tokenization End-to-End with Reinforcement LearningPoster
  577. You Don't Protect if You Don't Expect: Breaking the Key Assumption behind CLIP's Test-Time DefensesPoster
  578. You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion ModelsPoster
  579. You Need Better Attention PriorsPoster
  580. Your Latent Reasoning is Secretly Policy Improvement OperatorPoster
  581. Z-Erase: Enabling Concept Erasure in Single Stream Diffusion TransformersPoster
  582. Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM CompressionPoster
  583. Zero-Flow EncodersPoster
  584. Zero-Shot 3D Question Answering via Hierarchical View-to-Token TransportationPoster
  585. Zero-Shot Off-Policy LearningPoster
  586. Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via LanguagePoster
  587. Zero-Shot Text-to-Motion Evaluation using Video Language ModelsPoster
  588. Zero-shot Active Mapping via Fused 360-BEV Representations and Vision–Language ModelsPoster
  589. Zero-source LLM Hallucination Detection with Human-like Criteria ProbingPoster
  590. ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal ModelsPoster
  591. ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior DiffusionPoster
  592. ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language ModelsPoster
  593. Zeroth-Order Forward-Only SNN Training Inspiring Neuromorphic On-Chip LearningPoster
  594. Zeroth-Order Optimization at the Edge of StabilityPoster
  595. Zeus: Towards Tuning-Free Foundation Model for Time Series AnalysisPoster
  596. ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity SchedulingPoster
  597. Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification TasksPoster
  598. Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal PerceptionPoster
  599. [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive AggregationPoster
  600. ``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based RetrievalPoster
  601. cMoLLM at Scale: Horizontal Scaling Laws for Convolutionally-Gated Mixture-of-LLMsPoster
  602. cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal TransportPoster
  603. d2: Improved Techniques for Training Reasoning Diffusion Language ModelsPoster
  604. d2p: Fast and Scalable Structured Attention with Differentiable Dynamic ProgrammingPoster
  605. d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory DistillationPoster
  606. dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive CachingPoster
  607. dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language ModelsPoster
  608. daVinci-Dev: Agent-native Mid-training for Software EngineeringOral
  609. dgMARK: Decoding-Guided Watermarking for Diffusion Language ModelsPoster
  610. dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence LearningOral
  611. ePC: Fast and Deep Predictive Coding for Digital HardwarePoster
  612. effGen: Enabling Small Language Models as Capable Autonomous AgentsPoster
  613. gp2Scale: A Class of Compactly Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data PointsPoster
  614. h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement LearningSpotlight
  615. iGRPO: Fast Online RL for Flow Matching Model with Dense RewardPoster
  616. iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome DiagnosisPoster
  617. iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic GuidancePoster
  618. iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement LearningPoster
  619. iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation FrameworkPoster
  620. mHC: Manifold-Constrained Hyper-ConnectionsSpotlight
  621. mSOP-765k: A Benchmark For Multi-Modal Structured Output PredictionsPoster
  622. mmBERT: A Modern Multilingual Encoder with Annealed Language LearningPoster
  623. nD-RoPE: A Generalized RoPE for n-Dimensional Position EmbeddingPoster
  624. pTNAS: Progressive Neural Architecture Search for Tabular DataPoster
  625. rePIRL: Learn PRM with Inverse RL for LLM ReasoningPoster
  626. scCBGM: Single-Cell Editing via Concept BottlenecksPoster
  627. scChord: A Probabilistic Manifold Rectification Framework for RNA-to-Protein TranslationPoster
  628. scDEBART: Predicting in silico Single-Cell Perturbation Responses via Large-Scale Differential Expression LearningPoster
  629. scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell OmicsPoster
  630. video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLMPoster
  631. xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector ExtractionPoster
  632. xLSTM Distillation: Achieving Teacher-Student Parity Through Efficient Hybrid ArchitecturesPoster
  633. “Do Diffusion Models Dream of Electric Planes?” Discrete and Continuous Simulation-Based Inference for Aircraft DesignPoster
  634. “very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty QuantificationPoster

ICML accepted papers in other years

ICML 2025 (3,333)ICML 2024 (2,610)ICML 2023 (1,828)ICML 2022 (1,228)ICML 2021 (1,181)ICML 2020 (1,082)ICML 2019 (773)ICML 2018 (620)ICML 2017 (433)ICML 2016 (322)ICML 2015 (270)

Looking for submission deadlines instead? See the conference deadline calendar.