← All conferences

ICLR 2026 Accepted Papers

The full list of 5,356 papers accepted at ICLR 2026 (International Conference on Learning Representations). 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: 5,118Oral: 223ICLR 2026 ConditionalPoster: 14ICLR 2026 ConditionalOral: 1
  1. Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective AnalysisPoster
  2. Rodrigues Network for Learning Robot ActionsOral
  3. Rolling Forcing: Autoregressive Long Video Diffusion in Real TimePoster
  4. Rote Learning Considered Useful: Generalizing over Memorized Data in LLMsPoster
  5. RouterArena: An Open Platform for Comprehensive Comparison of LLM RoutersPoster
  6. Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral DecompositionPoster
  7. Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMsPoster
  8. Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing GuidancePoster
  9. Routing, Cascades, and User Choice for LLMsPoster
  10. Rubrics as Rewards: Reinforcement Learning Beyond Verifiable DomainsPoster
  11. RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic SamplingPoster
  12. Rényi Sharpness: A Novel Sharpness that Strongly Correlates with GeneralizationPoster
  13. S$^2$-Guidance: Stochastic Self-Guidance for Training-Free Enhancement of Diffusion ModelsPoster
  14. S2GO: Streaming Sparse Gaussian OccupancyPoster
  15. S2R-HDR: A Large-Scale Rendered Dataset for HDR FusionPoster
  16. S3OD: Towards Generalizable Salient Object Detection with Synthetic DataPoster
  17. SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt LearningPoster
  18. SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential ModelingPoster
  19. SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without TrainingPoster
  20. SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM CompressionPoster
  21. SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural NetworkPoster
  22. SAFER: Risk-Constrained Sample-then-Filter in Large Language ModelsPoster
  23. SAFETY-GUIDED FLOW (SGF): A UNIFIED FRAMEWORK FOR NEGATIVE GUIDANCE IN SAFE GENERATIONOral
  24. SAGA: Structural Aggregation Guided Alignment with Dynamic View and Neighborhood Order Selection for Multiview Graph Domain AdaptationPoster
  25. SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place RecognitionPoster
  26. SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human FeedbackPoster
  27. SAIR: Enabling Deep Learning for Protein-Ligand Interactions with a Synthetic Structural DatasetPoster
  28. SAM 3: Segment Anything with ConceptsPoster
  29. SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning SegmentationPoster
  30. SANA-Video: Efficient Video Generation with Block Linear Diffusion TransformerOral
  31. SAQ: Stabilizer-Aware Quantum Error Correction DecoderPoster
  32. SARM: Stage-Aware Reward Modeling for Long Horizon Robot ManipulationPoster
  33. SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMsPoster
  34. SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block AttentionPoster
  35. SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented EvaluationPoster
  36. SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised LearningPoster
  37. SCI-Verifier: Scientific Verifier with ThinkingPoster
  38. SCOPED: Score–Curvature Out-of-distribution Proximity Evaluator for DiffusionPoster
  39. SCRAPL: Scattering Transform with Random Paths for Machine LearningPoster
  40. SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement LearningPoster
  41. SCUBA: Salesforce Computer Use BenchmarkPoster
  42. SCoT: Teaching 3D-LLMs to Think Spatially with Million-scale CoT AnnotationsPoster
  43. SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion ClassifierPoster
  44. SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG GenerationPoster
  45. SEED-SET: Scalable Evolving Experimental Design for System-level Ethical TestingPoster
  46. SEED: Towards More Accurate Semantic Evaluation for Visual Brain DecodingPoster
  47. SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNINGPoster
  48. SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak AttacksPoster
  49. SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE ModelsPoster
  50. SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM QuantizationPoster
  51. SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image GenerationPoster
  52. SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing FlowsPoster
  53. SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samplesPoster
  54. SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMsPoster
  55. SGD with Adaptive Preconditioning: Unified Analysis and Momentum AccelerationPoster
  56. SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and GuidelinesPoster
  57. SHAPO: Sharpness-Aware Policy Optimization for Safe ExplorationPoster
  58. SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRAPoster
  59. SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability DefensePoster
  60. SIGMA-GEN: STRUCTURE AND IDENTITY GUIDED MULTI-SUBJECT ASSEMBLY FOR IMAGE GENERATIONPoster
  61. SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video DiffusionPoster
  62. SIM-CoT: Supervised Implicit Chain-of-ThoughtPoster
  63. SIPDO: Closed-Loop Prompt Optimization via Synthetic Data FeedbackPoster
  64. SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to SkinPoster
  65. SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear AttentionPoster
  66. SLM-MUX: Orchestrating Small Language Models for ReasoningPoster
  67. SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy TasksPoster
  68. SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority OversamplingPoster
  69. SMixer: Rethinking Efficient-Training and Event-Driven SNNsPoster
  70. SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyMLPoster
  71. SNAPHARD CONTRAST LEARNINGPoster
  72. SNaX: sparse narrow accelerated mixture of expertsPoster
  73. SONA: Learning Conditional, Unconditional, and Matching-Aware DiscriminatorPoster
  74. SONATA: Synergistic Coreset Informed Adaptive Temporal Tensor FactorizationPoster
  75. SONIC: Spectral Oriented Neural Invariant ConvolutionsPoster
  76. SOSBENCH: Benchmarking Safety Alignment on Scientific KnowledgePoster
  77. SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model AccelerationPoster
  78. SPACeR: Self-Play Anchoring with Centralized Reference ModelsPoster
  79. SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and TablesPoster
  80. SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold StartPoster
  81. SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion ModelsPoster
  82. SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language ModelsPoster
  83. SPG: Sandwiched Policy Gradient for Masked Diffusion Language ModelsPoster
  84. SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model TrainingPoster
  85. SPIKE-RL: Video-LLMs meet Bayesian SurprisePoster
  86. SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement LearningPoster
  87. SPR$^2$Q: Static Priority-based Rectifier Routing Quantization for Image Super-ResolutionPoster
  88. SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive DiffusionPoster
  89. SPRIG: Improving Large Language Model Performance by System Prompt OptimizationPoster
  90. SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion TransformersPoster
  91. SPWOOD: Sparse Partial Weakly-Supervised Oriented Object DetectionPoster
  92. SR-Scientist: Scientific Equation Discovery With Agentic AIPoster
  93. SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for ReasoningPoster
  94. SRT: Super-Resolution for Time Series via Disentangled Rectified FlowPoster
  95. SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian SplattingPoster
  96. SSDi8: Accurate and Efficient 8-bit Quantization for State Space DualityPoster
  97. SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive GenerationPoster
  98. SSVPO: Effective Step-Level Credit Assignment for RL Training of Language ModelsPoster
  99. ST-HHOL: Spatio-Temporal Hierarchical Hypergraph Online Learning for Crime PredictionPoster
  100. ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMsPoster
  101. ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web AgentsPoster
  102. STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure TransFormer for Offline Mulit-task Multi-agent Reinforcement LearningPoster
  103. STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D IntelligencePoster
  104. STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling ModelsPoster
  105. STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language ModelPoster
  106. STARK: Strategic Team of Agents for Refining KernelsPoster
  107. STAT: Skill-Targeted Adaptive TrainingPoster
  108. STDDN: A Physics-Guided Deep Learning Framework for Crowd SimulationPoster
  109. STEDiff: Revealing the Spatial and Temporal Redundancy of Backdoor Attacks in Text-to-Image Diffusion ModelsPoster
  110. STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULESPoster
  111. STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language ModelsPoster
  112. STORK: Faster Diffusion and Flow Matching Sampling by Resolving both Stiffness and Structure-DependencePoster
  113. STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather ForecastingPoster
  114. STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement LearningPoster
  115. STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation QuantizationPoster
  116. STream3R: Scalable Sequential 3D Reconstruction with Causal TransformerPoster
  117. SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMsPoster
  118. SUSD: Structured Unsupervised Skill Discovery through State FactorizationPoster
  119. SVD Provably Denoises Nearest Neighbor DataPoster
  120. SWE-RM: Execution-free Feedback for Software Engineering AgentsPoster
  121. SWERank: Software Issue Localization with Code RankingPoster
  122. SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue SolvingOral
  123. SYNC: Measuring and Advancing Synthesizability in Structure-Based Drug DesignPoster
  124. Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle EscapePoster
  125. Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network ArchitecturesPoster
  126. Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph FormPoster
  127. Safe Exploration via Policy PriorsPoster
  128. SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced SafetyOral
  129. SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak AttacksPoster
  130. SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier FunctionsPoster
  131. SafeMPO: Constrained Reinforcement Learning with Probabilistic Incremental ImprovementPoster
  132. SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input RoutingPoster
  133. Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service EnvironmentPoster
  134. Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-DefensePoster
  135. Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine UnlearningPoster
  136. Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case StudyPoster
  137. Safety at One Shot: Patching Fine-Tuned LLMs with A Single InstancePoster
  138. Salient Object Ranking via Cyclical Perception-Viewing Interaction ModelingPoster
  139. Same Content, Different Representations: A Controlled Study for Table QAPoster
  140. Sample Complexity and Representation Ability of Test-time Scaling ParadigmsPoster
  141. Sample Efficient Offline RL via T-Symmetry Enforced Latent State-StitchingPoster
  142. Sample Lottery: Unsupervised Discovery of Critical Instances for LLM ReasoningPoster
  143. Sample More to Think Less: Group Filtered Policy Optimization for Concise ReasoningPoster
  144. Sample Reward Soups: Query-efficient Multi-Reward Guidance for Text-to-Image Diffusion ModelsPoster
  145. Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMsPoster
  146. Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online InteractionPoster
  147. Sample-efficient and Scalable Exploration in Continuous-Time RLPoster
  148. Sample-efficient evidence estimation of score based priors for model selectionPoster
  149. Samples Are Not Equal: A Sample Selection Approach for Deep ClusteringPoster
  150. Sampling Complexity of TD and PPO in RKHSPoster
  151. Sampling-aware Adversarial Attacks Against Large Language ModelsPoster
  152. Sapiens2Poster
  153. Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite ImagePoster
  154. SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite ImageryPoster
  155. Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM ReasoningPoster
  156. Scalable Chain of Thoughts via Elastic ReasoningPoster
  157. Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and GenerationPoster
  158. Scalable Exploration for High-Dimensional Continuous Control via Value-Guided FlowPoster
  159. Scalable In-Context Q-LearningPoster
  160. Scalable Multilingual Multimodal Machine Translation with Speech-Text FusionPoster
  161. Scalable Offline Model-Based RL with Action ChunksPoster
  162. Scalable Oversight via Partitioned Human SupervisionPoster
  163. Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence GuaranteesPoster
  164. Scalable Second-order Riemannian Optimization for $K$-means ClusteringPoster
  165. Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein DynamicsPoster
  166. Scalable Training for Vector-Quantized Networks with 100% Codebook UtilizationPoster
  167. Scalable and Adaptive Trust-Region Learning via Projection Convex HullPoster
  168. Scale-wise Distillation of Diffusion ModelsPoster
  169. ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform DataOral
  170. ScaleCap: Scalable Image Captioning via Dual-Modality DebiasingPoster
  171. ScaleLong: A Multi-Timescale Benchmark for Long Video UnderstandingPoster
  172. Scaling Agent Learning via Experience SynthesisPoster
  173. Scaling Agents via Continual Pre-trainingPoster
  174. Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time ComputeOral
  175. Scaling Attention via Feature SparsityPoster
  176. Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided DiffusionPoster
  177. Scaling Behavior of Discrete Diffusion Language ModelsPoster
  178. Scaling Direct Feedback Learning with Theoretical GuaranteesPoster
  179. Scaling Generalist Data-Analytic AgentsPoster
  180. Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric DistancesPoster
  181. Scaling Group Inference for Diverse and High-Quality GenerationPoster
  182. Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV DatabasePoster
  183. Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMsPoster
  184. Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model PretrainingPoster
  185. Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning RegimeOral
  186. Scaling Laws and Symmetry, Evidence from Neural Force FieldsPoster
  187. Scaling Laws for Diffusion TransformersPoster
  188. Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?Poster
  189. Scaling Linear Attention with Sparse State ExpansionPoster
  190. Scaling Multi-Task Bayesian Optimization with Large Language ModelsPoster
  191. Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language ModelsPoster
  192. Scaling Sequence-to-Sequence Generative Neural RenderingPoster
  193. Scaling Speech Tokenizers with Diffusion AutoencodersPoster
  194. Scaling Synthetic Task Generation for Agents via ExplorationPoster
  195. Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time ScalingPoster
  196. Scaling up Memory for Robotic Control via Experience RetrievalPoster
  197. Scaling with Collapse: Efficient and Predictable Training of LLM FamiliesPoster
  198. ScalingCache: Extreme Acceleration of DiTs through Difference Scaling and Dynamic Interval CachingPoster
  199. SceneCOT: Eliciting Chain-of-Thought Reasoning in 3D ScenesPoster
  200. SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene GenerationPoster
  201. Scenethesis: A Language and Vision Agentic Framework for 3D Scene GenerationPoster
  202. Scheduling Your LLM Reinforcement Learning with Reasoning TreesPoster
  203. Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief GenerationPoster
  204. SciNav: A Principled Agent Framework for Scientific Coding TasksPoster
  205. SciTS: Scientific Time Series Understanding and Generation with LLMsPoster
  206. ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific WorkflowsPoster
  207. Score Distillation Beyond Acceleration: Generative Modeling from Corrupted DataPoster
  208. Score-Based Density Estimation from Pairwise ComparisonsPoster
  209. Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal ModelsPoster
  210. Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual LearningPoster
  211. Sculptor: Empowering LLMs with Cognitive Agency via Active Context ManagementPoster
  212. SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box AttacksPoster
  213. SealQA: Raising the Bar for Reasoning in Search-Augmented Language ModelsPoster
  214. Search Arena: Analyzing Search-Augmented LLMsPoster
  215. Search Self-Play: Pushing the Frontier of Agent Capability without SupervisionPoster
  216. Searching for Privacy Risks in LLM Agents via SimulationPoster
  217. SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPCPoster
  218. Secret-Protected Evolution for Differentially Private Synthetic Text GenerationPoster
  219. Secure Inference for Diffusion Models via Unconditional ScoresPoster
  220. Secure Outlier-Aware Large Language Model InferencePoster
  221. SeeDNorm: Self-Rescaled Dynamic NormalizationPoster
  222. SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained FromPoster
  223. SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-TrainingPoster
  224. Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic ScenesPoster
  225. Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language ModelsPoster
  226. Seeing Through Words: Controlling Visual Retrieval Quality with LanguagePoster
  227. Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRIOral
  228. Seeing What’s Not There: Negation Understanding Needs More Than TrainingPoster
  229. Seeing What’s Wrong: A Trajectory-Guided Approach to Caption Error DetectionPoster
  230. Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMsPoster
  231. Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term MemoryPoster
  232. Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekPoster
  233. Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate SchedulingPoster
  234. Segment Any Events with LanguagePoster
  235. Segment-Level Attribution for Selective Learning of Long Reasoning TracesPoster
  236. Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal LensPoster
  237. Selective Data Removal for Distributional Machine UnlearningPoster
  238. Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMsPoster
  239. Selective Rotary Position EmbeddingPoster
  240. Self-Aligned Reward: Towards Effective and Efficient ReasonersPoster
  241. Self-Augmented Visual Contrastive DecodingPoster
  242. Self-Consistency Improves the Trustworthiness of Self-Interpretable GNNsPoster
  243. Self-Destructive Language ModelsPoster
  244. Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and RankingPoster
  245. Self-Forcing++: Towards Minute-Scale High-Quality Video GenerationPoster
  246. Self-Guided Low Light Object Detection FrameworkPoster
  247. Self-Improving Loops for Visual Robotic PlanningPoster
  248. Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement LearningPoster
  249. Self-Improving Vision-Language-Action Models with Data Generation via Residual RLPoster
  250. Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning TrainingPoster
  251. Self-Predictive Representations for Combinatorial Generalization in Behavioral CloningPoster
  252. Self-Refining Vision Language Model for Robotic Failure Detection and ReasoningPoster
  253. Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy OptimizationPoster
  254. Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive ModelsPoster
  255. Self-Speculative Masked DiffusionsPoster
  256. Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical SystemsPoster
  257. Self-Supervised Learning from Structural InvariancePoster
  258. SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?Poster
  259. SelvaBox: A high‑resolution dataset for tropical tree crown detectionPoster
  260. Sem-MoE: Semantic-aware Model-Data Collaborative Scheduling for Efficient MoE InferencePoster
  261. SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and GenerationPoster
  262. Semantic Regexes: Auto-Interpreting LLM Features with a Structured LanguagePoster
  263. Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based MethodPoster
  264. Semantic Visual Anomaly Detection and Reasoning in AI-Generated ImagesPoster
  265. Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended TasksPoster
  266. Semantic-Aware Diffusion LLM Inference With Adaptive Block SizePoster
  267. Semantic-Enhanced Time-Series Forecasting via Large Language ModelsPoster
  268. Semantic-aware Wasserstein Policy Regularization for Large Language Model AlignmentPoster
  269. Semi-Parametric Contextual Pricing with General SmoothnessPoster
  270. Semi-Supervised Preference Optimization with Limited FeedbackOral
  271. SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image DistillationPoster
  272. Separable Neural Networks: Approximation Theory, NTK Regime, and Preconditioned Gradient DescentPoster
  273. Seq vs Seq: An Open Suite of Paired Encoders and DecodersPoster
  274. Sequences of Logits Reveal the Low Rank Structure of Language ModelsOral
  275. Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor SegmentationPoster
  276. Sequential Parallel Duality in Prefix Scannable ModelsPoster
  277. SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural AlignmentPoster
  278. Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and OptimizationPoster
  279. Setting up for failure: automatic discovery of the neural mechanisms of cognitive errorsPoster
  280. ShapeGen4D: Towards High Quality 4D Shape Generation from VideosPoster
  281. Sharing State Between Prompts and ProgramsPoster
  282. Sharp Monocular View Synthesis in Less Than a SecondPoster
  283. Sharp asymptotic theory for Q-learning with \texttt{LD2Z} learning rate and its generalizationPoster
  284. Sharpness-Aware Machine UnlearningPoster
  285. Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference OptimizationPoster
  286. Sheaves Reloaded: A Direction AwakeningPoster
  287. ShieldedCode: Learning Robust Representations for Virtual Machine Protected CodePoster
  288. Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion EstimatesPoster
  289. Shift-and-Sum Quantization for Visual Autoregressive ModelsPoster
  290. ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program EvolutionPoster
  291. Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like PeopleOral
  292. Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement LearningPoster
  293. Short Window Attention Enables Long-Term MemorizationPoster
  294. Shortcut Diffusion Training with Cumulative Consistency Loss: An Optimal Control ViewPoster
  295. Should We Still Pretrain Encoders with Masked Language Modeling?Poster
  296. Shrinking Proteins with DiffusionPoster
  297. Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic ShufflePoster
  298. Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGDPoster
  299. Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph TransformersPoster
  300. SiMO: Single-Modality-Operable Multimodal Collaborative PerceptionPoster
  301. SiNGER: A Clearer Voice Distills Vision Transformers FurtherPoster
  302. SigLIP-HD by Fine-to-Coarse SupervisionPoster
  303. SigmaDock: Untwisting Molecular Docking with Fragment-Based SE(3) DiffusionPoster
  304. Sign-SGD via Parameter-Free OptimizationPoster
  305. Signal Structure-Aware Gaussian Splatting for Large-Scale Scene ReconstructionPoster
  306. Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model InfluencePoster
  307. Silent Leaks: Implicit Knowledge Extraction Attack on RAG SystemsPoster
  308. Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic ManipulationPoster
  309. SimBench: Benchmarking the Ability of Large Language Models to Simulate Human BehaviorsPoster
  310. SimULi: Real-Time LiDAR and Camera Simulation with Unscented TransformsPoster
  311. SimpleFold: Folding Proteins is Simpler than You ThinkPoster
  312. SimpleGVR: A Simple Baseline for Latent-Cascaded Generative Video Super-ResolutionPoster
  313. SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated ReasoningPoster
  314. SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMsPoster
  315. SimpleVLA-RL: Scaling VLA Training via Reinforcement LearningPoster
  316. Simplicial Embeddings Improve Sample Efficiency in Actor–Critic AgentsPoster
  317. SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM AgentsOral
  318. Simulation to Rules: A Dual-VLM Framework for Formal Visual PlanningPoster
  319. Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward FunctionsPoster
  320. Single-Loop Byzantine-Resilient Federated Bilevel OptimizationPoster
  321. Single-stream Policy OptimizationPoster
  322. Singleton-Optimized Conformal PredictionPoster
  323. SinkTrack: Attention Sink based Context Anchoring for Large Language ModelsPoster
  324. SketchEvo: Leveraging Drawing Dynamics for Enhanced Image SynthesisPoster
  325. SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal ModelsPoster
  326. SketchingReality: From Freehand Scene Sketches to Photorealistic ImagesPoster
  327. Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement LearningPoster
  328. SkillFactory: Self-Distillation for Learning Cognitive BehaviorsPoster
  329. Skirting Additive Error Lower Bounds for Private Turnstile StreamsPoster
  330. SkyEvents: A Large-Scale Event-enhanced UAV Dataset for Robust 3D Scene ReconstructionPoster
  331. Slicing Wasserstein over Wasserstein via Functional Optimal TransportPoster
  332. SliderQuant: Accurate Post-Training Quantization for LLMsPoster
  333. SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak AttacksPoster
  334. Slow-Fast Policy Optimization: Reposition-Before-Update for LLM ReasoningPoster
  335. Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via SpeculationPoster
  336. SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAGPoster
  337. Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward ShapingPoster
  338. SmellNet: A Large-scale Dataset for Real-world Smell RecognitionPoster
  339. Smooth Calibration Error: Uniform Convergence and Functional Gradient AnalysisPoster
  340. Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context UnderstandingPoster
  341. SoFlow: Solution Flow Models for One-Step Generative ModelingPoster
  342. SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference OptimizationPoster
  343. Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence AnalysisPoster
  344. Social Agents: Collective Intelligence Improves LLM PredictionsPoster
  345. SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful RequestsPoster
  346. SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social DilemmasPoster
  347. Soft Equivariance Regularization for Invariant Self-Supervised LearningPoster
  348. Soft Quality-Diversity OptimizationPoster
  349. Soft Tokens, Hard TruthsPoster
  350. Soft-Di[M]O: Improved one-step Image Discrete ModelPoster
  351. Soft-Masked Diffusion Language ModelsPoster
  352. SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive ModelPoster
  353. Softmax Transformers are Turing-CompleteOral
  354. Softmax is not Enough (for Adaptive Conformal Classification)Poster
  355. Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided InformationPoster
  356. Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online PlanningPoster
  357. Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement LearningPoster
  358. Solving the 2-norm k-hyperplane clustering problem via multi-norm formulationsPoster
  359. Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM AgentsPoster
  360. Some Neural Networks Inherently Preserve Subspace Clustering StructurePoster
  361. SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear ModulationPoster
  362. SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking RewardPoster
  363. Source-Guided Flow MatchingPoster
  364. SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial IntelligencePoster
  365. SpaCE-Eval: A Benchmark for Real-World Multi-Modal ReasoningPoster
  366. SpaceControl: Introducing Test-Time Spatial Control to 3D Generative ModelingPoster
  367. SpareTrain: Fault-Tolerant LLM Training via Low-Cost Dual Modular RedundancyPoster
  368. Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion CapturePoster
  369. Sparling: End-to-End Spatial Concept Learning via Extremely Sparse ActivationsPoster
  370. Sparse Attention Adaptation for Long ReasoningPoster
  371. Sparse Autoencoders Trained on the Same Data Learn Different FeaturesPoster
  372. Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive LearningPoster
  373. Sparse Imagination for Efficient Visual World Model PlanningPoster
  374. Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMsPoster
  375. SparseD: Sparse Attention for Diffusion Language ModelsPoster
  376. SparseEval: Efficient Evaluation of Large Language Models by Sparse OptimizationPoster
  377. Sparsity Forcing: Reinforcing Token Sparsity of MLLMsPoster
  378. Sparsity-promoting Fine-tuning for Equivariant Materials Foundation ModelPoster
  379. SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild?Poster
  380. Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine DifferentiationPoster
  381. Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action ModelPoster
  382. Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View ScenesPoster
  383. Spatial Structure and Selective Text Jointly Facilitate Image ClusteringPoster
  384. Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language ModelsICLR 2026 ConditionalPoster
  385. SpatialHand: Generative Object Manipulation from 3D PrespectivePoster
  386. SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language ModelsPoster
  387. SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMsPoster
  388. Spatially Guided Training for Vision-Language-Action ModelPoster
  389. Spatially Informed Autoencoders for Interpretable Visual Representation LearningPoster
  390. SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human GenerationICLR 2026 ConditionalPoster
  391. SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch ParallelismPoster
  392. Special Unitary Parameterized Estimators of RotationPoster
  393. Specialization after Generalization: Towards Understanding Test-Time Training in Foundation ModelsPoster
  394. SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-SpectraPoster
  395. Spectral Attention Steering for Prompt HighlightingPoster
  396. Spectral Bellman Method: Unifying Representation and Exploration in RLPoster
  397. Spectral-guided Physical Dynamics DistillationPoster
  398. SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category DiscoveryPoster
  399. Spectrum Tuning: Post-Training for Distributional Coverage and In-Context SteerabilityPoster
  400. Speculative Actions: A Lossless Framework for Faster AI AgentsOral
  401. Speculative Speculative DecodingPoster
  402. Speech World Model: Causal State–Action Planning with Explicit Reasoning for SpeechPoster
  403. Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and SentencesPoster
  404. SpeechJudge: Towards Human-Level Judgment for Speech NaturalnessPoster
  405. SpeechOp: Inference-Time Task Composition for Generative Speech ProcessingPoster
  406. Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion ModelsOral
  407. Spike-based Digital Brain: a novel fundamental model for brain activity analysisPoster
  408. SpikeGen: Decoupled “Rods and Cones” Visual Representation Processing with Latent Generative FrameworkPoster
  409. SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot SystemPoster
  410. SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike StreamsPoster
  411. Spiking Discrepancy Transformer for Point Cloud AnalysisPoster
  412. Spilled Energy in Large Language ModelsPoster
  413. Spilling the Beans: Teaching LLMs to Self-Report Their Hidden ObjectivesPoster
  414. SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMsPoster
  415. SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k CorpusICLR 2026 ConditionalPoster
  416. Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful DemonstrationsPoster
  417. Splat Feature SolverPoster
  418. Splat Regression ModelsPoster
  419. Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware DistillationPoster
  420. Splat the Net: Radiance Fields with Splattable Neural PrimitivesPoster
  421. SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space SplittingPoster
  422. SportR: A Benchmark for Multimodal Large Language Model Reasoning in SportsPoster
  423. SpotIt: Evaluating Text-to-SQL Evaluation with Formal VerificationPoster
  424. Spotlight on Token Perception for Multimodal Reinforcement LearningPoster
  425. Spurious Correlation-Aware Embedding Regularization for Worst-Group RobustnessPoster
  426. Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language ModelPoster
  427. StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental LearningPoster
  428. Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD MappingPoster
  429. Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive ClippingPoster
  430. Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM ReasoningPoster
  431. Stable Video Infinity: Infinite-Length Video Generation with Error RecyclingOral
  432. Stable and Scalable Deep Predictive Coding Networks with Meta Prediction ErrorsPoster
  433. Stable coresets: Unleashing the power of uniform samplingPoster
  434. Stable-LoRA: Stabilizing Feature Learning of Low-Rank AdaptionPoster
  435. StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMsPoster
  436. Stacked from One: Multi-Scale Self-Injection for Context Window ExtensionPoster
  437. Stackelberg Coupling of Online Representation Learning and Reinforcement LearningPoster
  438. Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential GamePoster
  439. Stage-wise Dynamics of Classifier-Free Guidance in Diffusion ModelsPoster
  440. Statistical Advantage of Softmax Attention: Insights from Single-Location RegressionPoster
  441. Statistical Guarantees for Offline Domain RandomizationPoster
  442. Statistical Guarantees in the Search for Less Discriminatory AlgorithmsPoster
  443. Steerable Adversarial Scenario Generation through Test-Time Preference AlignmentPoster
  444. Steering Autoregressive Music Generation with Recursive Feature MachinesPoster
  445. Steering Diffusion Models Towards Credible Content RecommendationPoster
  446. Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and ModelsPoster
  447. Steering Evaluation-Aware Language Models To Act Like They Are DeployedPoster
  448. Steering Language Models with Weight ArithmeticPoster
  449. Steering MoE LLMs via Expert (De)ActivationPoster
  450. Steering and Rectifying Latent representation manifolds in Frozen Multi-modal LLMs for Video Anomaly DetectionPoster
  451. Steering the Herd: A Framework for LLM-based Control of Social LearningOral
  452. SteinsGate: Adding Causality to Diffusions for Long Video Generation via Path IntegralPoster
  453. Step-Aware Residual-Guided Diffusion for EEG Spatial Super-ResolutionPoster
  454. StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language ModelsPoster
  455. StochasTok: Improving Fine-Grained Subword Understanding in LLMsPoster
  456. Stochastic Neural Networks for Causal Inference with Missing ConfoundersPoster
  457. Stochastic Optimal Control for Continuous-Time fMRI Representation LearningPoster
  458. Stochastic Self-Organization in Multi-Agent SystemsPoster
  459. Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep LearningPoster
  460. Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMsPoster
  461. Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated PenaltyPoster
  462. Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent SystemsPoster
  463. Stopping Computation for Converged Tokens in Masked Diffusion-LM DecodingPoster
  464. Story-Iter: A Training-free Iterative Paradigm for Long Story VisualizationPoster
  465. StoryAlign: Evaluating and Training Reward Models for Story GenerationPoster
  466. Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMsPoster
  467. Strategic Obfuscation of Deceptive Reasoning in Language ModelsPoster
  468. Strategic Planning and Rationalizing on Trees Make LLMs Better DebatersPoster
  469. Strategic Scaling of Test-Time Compute: A Bandit Learning ApproachPoster
  470. StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video StreamsPoster
  471. Streaming Autoregressive Video Generation via Diagonal DistillationPoster
  472. Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!Poster
  473. Streaming Visual Geometry TransformerPoster
  474. StreamingThinker: Large Language Models Can Think While ReadingPoster
  475. StreamingVLM: Real-Time Understanding for Infinite Video StreamsPoster
  476. Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual InvariancePoster
  477. Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement LearningPoster
  478. Strictly Constrained Generative Modeling via Split Augmented Langevin SamplingPoster
  479. String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse GenerationPoster
  480. Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion modelsPoster
  481. Strong Correlations Induce Cause Only Predictions in Transformer TrainingPoster
  482. Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMsPoster
  483. Strongly Convex Sets in Riemannian ManifoldsPoster
  484. Structural Inference: Interpreting Small Language Models with SusceptibilitiesPoster
  485. Structural Prognostic Event Modeling for Multimodal Cancer Survival AnalysisPoster
  486. Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNsPoster
  487. Structure Learning from Time-Series Data with Lag-Agnostic Structural PriorPoster
  488. Structure-Aware Graph Hypernetworks for Neural Program SynthesisPoster
  489. Structured Flow Autoencoders: Learning Structured Probabilistic Representations with Flow MatchingOral
  490. Structured Reasoning for LLMs: A Unified Framework for Efficiency and ExplainabilityPoster
  491. Study of Training Dynamics for Memory-Constrained Fine-TuningPoster
  492. StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled SteeringPoster
  493. Stylos: Multi-View 3D Stylization with Single-Forward Gaussian SplattingPoster
  494. SubDyve: Subgraph-Driven Dynamic Propagation for Virtual Screening Enhancement Controlling False PositivePoster
  495. Sublinear Spectral Clustering Oracle with Little MemoryPoster
  496. Sublinear Time Quantum Algorithm for Attention ApproximationPoster
  497. Submodular Function Minimization with Dueling OraclePoster
  498. Subquadratic Algorithms and Hardness for Attention with Any TemperaturePoster
  499. Subspace Kernel Learning on Tensor SequencesPoster
  500. SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal BasisPoster
  501. Summaries as Centroids for Interpretable and Scalable Text ClusteringPoster
  502. SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector RegularizationPoster
  503. SuperF: Neural Implicit Fields for Multi-Image Super-ResolutionPoster
  504. Superficial Safety Alignment HypothesisPoster
  505. Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM RerankingPoster
  506. Supervised Reinforcement Learning: From Expert Trajectories to Step-wise ReasoningPoster
  507. Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent SpacePoster
  508. Supporting Multimodal Intermediate Fusion with Informatic Constraint and Distribution CoherencePoster
  509. SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity PriorsPoster
  510. SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival AnalysisPoster
  511. Swap-guided Preference Learning for Personalized Reinforcement Learning from Human FeedbackPoster
  512. SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMsPoster
  513. SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-LearningPoster
  514. Symmetric Space Learning for Combinatorial GeneralizationPoster
  515. Symmetry-Aware Bayesian Optimization via Max KernelsPoster
  516. SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate ModelingPoster
  517. SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music GenerationPoster
  518. Synchronizing Probabilities in Model-Driven Lossless CompressionPoster
  519. Syncphony: Synchronized Audio-to-Video Generation with Diffusion TransformersPoster
  520. Synergizing Understanding and Generation with Interleaved Analyzing-Drafting ThinkingPoster
  521. SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language ModelsPoster
  522. Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational AutoencodersPoster
  523. Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMsPoster
  524. Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General ReasoningPoster
  525. Synthetic Bootstrapped PretrainingPoster
  526. Synthetic History: Evaluating Visual Representations of the Past in Diffusion ModelsPoster
  527. SysMoBench: Evaluating AI on Formally Specifying Complex Real-World SystemsPoster
  528. Sysformer: Safeguarding Frozen Large Language Models with Adaptive System PromptsPoster
  529. Systematic Biosafety Evaluation of DNA Language Models under Jailbreak AttacksPoster
  530. T-TAMER: Provably Taming Trade-offs in ML ServingPoster
  531. T1: One-to-One Channel-Head Binding for Multivariate Time-Series ImputationPoster
  532. T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language ModelsPoster
  533. TABLET: A Large-Scale Dataset for Robust Visual Table UnderstandingPoster
  534. TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal ModelsPoster
  535. TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language ModelsPoster
  536. TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long VideoPoster
  537. TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language ModelingPoster
  538. TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual CortexPoster
  539. TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption ViolationsPoster
  540. TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement LearningOral
  541. TD-MoE: Tensor Decomposition for MoE ModelsPoster
  542. TEDM: Time Series Forecasting with Elucidated Diffusion ModelsPoster
  543. TEMPFLOW-GRPO: WHEN TIMING MATTERS FOR GRPO IN FLOW MODELSPoster
  544. TEN-DM: Topology-Enhanced Diffusion Model for Spatio-Temporal Event PredictionPoster
  545. TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi TessellationPoster
  546. TEST-TIME SCALING IN DIFFUSION LLMS VIA HIDDEN SEMI-AUTOREGRESSIVE EXPERTSPoster
  547. TGM: A Modular and Efficient Library for Machine Learning on Temporal GraphsPoster
  548. THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELSPoster
  549. THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUSPoster
  550. THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCEPoster
  551. THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud ForensicsPoster
  552. THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical ReasoningPoster
  553. TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D AlignmentPoster
  554. TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATIONPoster
  555. TINKER: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene OptimizationPoster
  556. TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICESPoster
  557. TIPO: Text to Image with Text Pre-sampling for Prompt OptimizationPoster
  558. TIPS: Turn-level Information-Potential Reward Shaping for Search-Augmented LLMsPoster
  559. TNT: Improving Chunkwise Training for Test-Time MemorizationPoster
  560. TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object InteractionsPoster
  561. TP-Spikformer: Token Pruned Spiking TransformerPoster
  562. TPDiff: Temporal Pyramid Video Diffusion ModelPoster
  563. TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal ModelsPoster
  564. TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-TuningPoster
  565. TRACE: Your Diffusion Model is Secretly an Instance Edge DetectorOral
  566. TRACED: Transition-aware Regret Approximation with Co-learnability for Environment DesignPoster
  567. TRACEDET: HALLUCINATION DETECTION FROM THE DECODING TRACE OF DIFFUSION LARGE LANGUAGE MODELSPoster
  568. TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool UsePoster
  569. TRIBE: TRImodal Brain Encoder for whole-brain fMRI response predictionPoster
  570. TRIDENT: Cross-Domain Trajectory Spatio-Temporal Representation via Distance-Preserving Triplet LearningPoster
  571. TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning TasksPoster
  572. TROLL: Trust Regions Improve Reinforcement Learning for Large Language ModelsOral
  573. TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-TuningPoster
  574. TS-Attn: Temporal-wise Separable Attention for Multi-Event Video GenerationPoster
  575. TS-DDAE: A novel Temporal-Spectral Denoising Diffusion AutoEncoder for Wireless Signal Recognition Model Pre-trainingPoster
  576. TSLM: Tree-Structured Language Modeling for Divergent ThinkingPoster
  577. TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing PracticesPoster
  578. TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series AnalysisPoster
  579. TTOM: Test-Time Optimization and Memorization for Compositional Video GenerationPoster
  580. TTS Can Speak in Any Style with Any VoicePoster
  581. TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech SystemsOral
  582. TTT3R: 3D Reconstruction as Test-Time TrainingPoster
  583. TUMIX: Multi-Agent Test-Time Scaling with Tool-Use MixturePoster
  584. TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and AnonymizationPoster
  585. TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile DataPoster
  586. TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular ReasoningPoster
  587. Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMsPoster
  588. TabStruct: Measuring Structural Fidelity of Tabular DataOral
  589. TableDART: Dynamic Adaptive Multi-Modal Routing for Table UnderstandingPoster
  590. TableMaster: A Recipe to Advance Table Understanding with Language ModelsPoster
  591. Tackling Heavy-Tailed Q-Value Bias in Offline-to-Online Reinforcement Learning with Laplace-Robust ModelingPoster
  592. Tackling Time-Series Forecasting Generalization via Mitigating Concept DriftPoster
  593. Tackling the XAI Disagreement Problem with Adaptive Feature GroupingPoster
  594. Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMsPoster
  595. Take Note: Your Molecular Dataset Is Probably AlignedPoster
  596. Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error AnalysisPoster
  597. Talking Points: Describing and Localizing PixelsPoster
  598. Taming Curvature: Architecture Warm-up for Stable Transformer TrainingPoster
  599. Taming Hierarchical Image Coding Optimization: A Spectral Regularization PerspectivePoster
  600. Taming Imperfect Process Verifiers: A Sampling Perspective on BacktrackingPoster
  601. Taming Momentum: Rethinking Optimizer States Through Low-Rank ApproximationOral
  602. Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse AutoencodersPoster
  603. Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play FrameworkPoster
  604. Taming the Fragility of KV Cache Eviction in LLM InferencePoster
  605. TangleScore: Tangle-Guided Purge and Imprint for Unstructured Knowledge EditingPoster
  606. TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference OptimizationPoster
  607. Target-Aware Video Diffusion ModelsPoster
  608. Task Tokens: A Flexible Approach to Adapting Behavior Foundation ModelsPoster
  609. Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic InsightsPoster
  610. Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation ModelsPoster
  611. Task-Agnostic Amortized Multi-Objective OptimizationPoster
  612. Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM FinetuningPoster
  613. Task-Related Token Compression in Multimodal Large Language Models from an Explainability PerspectivePoster
  614. Task-free Adaptive Meta Black-box OptimizationOral
  615. TaskCraft: Automated Generation of Agentic TasksPoster
  616. Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMsPoster
  617. Teach2Eval: An Interaction-Driven LLMs Evaluation Method via Teaching EffectivenessPoster
  618. Teaching Metric Distance to Discrete Autoregressive Language ModelsPoster
  619. Teaching VLMs to Admit Uncertainty in OCR from Lossy Visual InputsPoster
  620. Tell me Habibi, is it Real or Fake?Poster
  621. Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement LearningPoster
  622. Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned InterventionsPoster
  623. Temporal Generalization: A Reality CheckPoster
  624. Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic ExplainabilityPoster
  625. Temporal Graph Thumbnail: Robust Representation Learning with Global Evolutionary SkeletonPoster
  626. Temporal Slowness in Central Vision Drives Semantic Object LearningPoster
  627. Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for InterpretabilityOral
  628. Temporal superposition and feature geometry of RNNs under memory demandsOral
  629. Temporally Detailed Hypergraph Neural ODE for Disease Progression ModelingPoster
  630. Tensor learning with orthogonal, Lorentz, and symplectic symmetriesPoster
  631. Tequila: Deadzone-free Ternary Quantization for Large Language ModelsPoster
  632. Terminal Velocity MatchingPoster
  633. Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line InterfacesPoster
  634. TerraFM: A Scalable Foundation Model for Unified Multisensor Earth ObservationPoster
  635. Test-Time Accuracy-Cost Control in Neural Simulators via Recurrent-DepthPoster
  636. Test-Time Adaptation for LLM Agents via Environment InteractionPoster
  637. Test-Time Adaptation without Source Data for Out-of-Domain Bioactivity PredictionPoster
  638. Test-Time Alignment for Large Language Models via Textual Model Predictive ControlPoster
  639. Test-Time Efficient Pretrained Model Portfolios for Time Series ForecastingPoster
  640. Test-Time Iterative Error Correction for Efficient Diffusion ModelsPoster
  641. Test-Time Matching: Unlocking Compositional Reasoning in Multimodal ModelsPoster
  642. Test-Time Mixture of World Models for Embodied Agents in Dynamic EnvironmentsPoster
  643. Test-Time Optimization of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and RefinementPoster
  644. Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIPPoster
  645. Test-Time Scaling with Reflective Generative ModelPoster
  646. Test-Time Training Done RightPoster
  647. Test-time Domain Generalization for Image Super-resolutionPoster
  648. Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimalityPoster
  649. Testing Most Influential SetsPoster
  650. TetraGT: Tetrahedral Geometry-Driven Explicit Token Interactions with Graph Transformer for Molecular Representation LearningPoster
  651. Text summarization via global structure awarenessPoster
  652. Text-Aware Image Restoration with Diffusion ModelsPoster
  653. Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video GeneratorOral
  654. Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language DescriptionsPoster
  655. Text2Grad: Reinforcement Learning from Natural Language FeedbackPoster
  656. Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction GenerationPoster
  657. Textual Bayes: Quantifying Uncertainty in LLM-Based SystemsPoster
  658. Textual Equilibrium Propagation for Deep Compound AI SystemsPoster
  659. Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-ResolutionPoster
  660. The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language AbilitiesPoster
  661. The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM ObjectivesPoster
  662. The Alignment Waltz: Jointly Training Agents to Collaborate for SafetyPoster
  663. The Art of Scaling Reinforcement Learning Compute for LLMsOral
  664. The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable RewardPoster
  665. The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will ThinkPoster
  666. The Counting Power of TransformersPoster
  667. The Coverage Principle: How Pre-Training Enables Post-TrainingOral
  668. The Curious Case of In-Training Compression of State Space ModelsPoster
  669. The Deleuzian Representation HypothesisPoster
  670. The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMsPoster
  671. The Diffusion Duality, Chapter II: $\Psi$-Samplers and Efficient CurriculumPoster
  672. The Effect of Attention Head Count on Transformer ApproximationPoster
  673. The Expressive Limits of Diagonal SSMs for State-TrackingPoster
  674. The False Promise of Zero-Shot Super-Resolution in Machine-Learned OperatorsPoster
  675. The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning ModelsPoster
  676. The Forecast After the Forecast: A Post-Processing Shift in Time SeriesPoster
  677. The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global StatisticsPoster
  678. The Geometry and Topology of Circuits: the Manifolds of Modular AdditionPoster
  679. The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane AlgorithmPoster
  680. The Geometry of Reasoning: Flowing Logics in Representation SpacePoster
  681. The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?Poster
  682. The Human Brain as a Dynamic Mixture of Expert Models in Video UnderstandingPoster
  683. The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research IdeasPoster
  684. The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMsPoster
  685. The Imitation Game: Turing Machine Imitator is Length Generalizable ReasonerPoster
  686. The Intricate Dance of Prompt Complexity, Quality, Diversity and Consistency in T2I ModelsPoster
  687. The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's AlgorithmPoster
  688. The Lattice Representation Hypothesis and Concept Algebra in LLMsPoster
  689. The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D KnowledgePoster
  690. The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?Poster
  691. The Limits of Inference Scaling Through ResamplingPoster
  692. The Logical Expressiveness of Topological Neural NetworksPoster
  693. The Markovian ThinkerPoster
  694. The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software EvolutionPoster
  695. The Mind's Transformer: Computational Neuroanatomy of LLM-Brain AlignmentPoster
  696. The Natural Geometry of Code: Hyperbolic Representation Learning for Program ReasoningPoster
  697. The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical ProofsPoster
  698. The Overthinking Predicament: When Reasoning Hurts RankingPoster
  699. The Pensieve Paradigm: Stateful Language Models with Learned Memory ManagementPoster
  700. The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon AlgorithmOral
  701. The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-NewtonPoster
  702. The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor RecoveryPoster
  703. The Price of Amortized inference in Sparse AutoencodersPoster
  704. The Price of Robustness: Stable Classifiers Need OverparameterizationPoster
  705. The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT DistillationPoster
  706. The Quest for Generalizable Motion Generation: Data, Model, and EvaluationPoster
  707. The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement LearningPoster
  708. The Sample Complexity of Online Reinforcement Learning: A Multi-model PerspectivePoster
  709. The Seismic Wavefield Common Task FrameworkPoster
  710. The Serial Scaling HypothesisPoster
  711. The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent HomologyOral
  712. The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely TokensPoster
  713. The Spacetime of Diffusion Models: An Information Geometry PerspectiveOral
  714. The State of Reinforcement Finetuning for Transformer-based Generative AgentsPoster
  715. The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task ExecutionPoster
  716. The Tutor-Pupil Augmentation: Enhancing Learning and Interpretability via Input CorrectionsPoster
  717. The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information LossPoster
  718. The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMMPoster
  719. The Value of Information in Human-AI Decision-makingPoster
  720. Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning SolutionPoster
  721. Theoretical Guarantees for Causal Discovery on Large Random GraphsPoster
  722. Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier GapPoster
  723. Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and TimePoster
  724. Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?Poster
  725. Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM ReasoningPoster
  726. There Was Never a Bottleneck in Concept Bottleneck ModelsPoster
  727. There and Back Again: On the relation between Noise and Image Inversions in Diffusion ModelsPoster
  728. Thicker and Quicker: The Jumbo Token for Fast Plain Vision TransformersPoster
  729. ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning ModelsOral
  730. Think Then Embed: Generative Context Improves Multimodal EmbeddingPoster
  731. Think in Parallel, Answer as One: Logit Averaging for Open-Ended ReasoningPoster
  732. Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form GenerationPoster
  733. ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought ReasoningPoster
  734. ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance DecodingPoster
  735. Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation DetectionPoster
  736. Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy OptimizationPoster
  737. Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and GenerationPoster
  738. Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient ReasonersPoster
  739. Thompson Sampling via Fine-Tuning of LLMsPoster
  740. Thought Branches: Interpreting LLM Reasoning Requires ResamplingPoster
  741. Threading Keyframe with Narratives: MLLMs as Strong Long Video ComprehendersPoster
  742. Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward PassesPoster
  743. Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMsOral
  744. Thyme: Think Beyond ImagesPoster
  745. TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRAPoster
  746. TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology StatePoster
  747. Tight Bounds for Schrodinger Potential Estimation in Unpaired Data TranslationPoster
  748. Tighter Performance Theory of FedExProxPoster
  749. TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement LearningPoster
  750. TileLang: Bridge Programmability and Performance in Modern Neural KernelsOral
  751. Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural NetworksPoster
  752. Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language ModelsPoster
  753. Time Optimal Execution of Action Chunk Policies Beyond Demonstration SpeedPoster
  754. Time-Gated Multi-Scale Flow Matching for Time-Series ImputationPoster
  755. Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial AttacksPoster
  756. Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock DenoisingPoster
  757. TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language ModelsPoster
  758. TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level EffectivenessPoster
  759. TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement LearningPoster
  760. TimeSeg: An Information-Theoretic Segment-Wise Explainer for Time-Series PredictionsPoster
  761. TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at ScalePoster
  762. Tina: Tiny Reasoning Models via LoRAPoster
  763. To Augment or Not to Augment? Diagnosing Distributional Symmetry BreakingPoster
  764. To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent ConcentrationPoster
  765. To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space ModelsOral
  766. To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language ModelsPoster
  767. To View Transform or Not to View Transform: NeRF-based Pre-training PerspectivePoster
  768. ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity OptimizationPoster
  769. TokMem: Tokenized Procedural Memory for Large Language ModelsPoster
  770. TokUR: Token-Level Uncertainty Estimation for Large Language Model ReasoningPoster
  771. Token Distillation: Attention-Aware Input Embeddings for New TokensPoster
  772. Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement LearningPoster
  773. Token-Based Audio Inpainting via Discrete DiffusionPoster
  774. Token-Efficient Long-Term Interest Sketching and Internalized Reasoning for LLM-based RecommendationPoster
  775. Token-Guard: Towards Token-Level Hallucination Control via Self-Checking DecodingPoster
  776. Token-Importance Guided Direct Preference OptimizationOral
  777. Token-level Data Selection for Safe LLM Fine-tuningPoster
  778. TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token DitchingPoster
  779. Tokenisation over Bounded Alphabets is HardPoster
  780. Tokenizing Single-Channel EEG with Time-Frequency Motif LearningPoster
  781. ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn InteractionPoster
  782. ToolTree: Efficient LLM Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional PruningPoster
  783. ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language ModelsPoster
  784. Tools are under-documented: Simple Document Expansion Boosts Tool RetrievalPoster
  785. ToonComposer: Streamlining Cartoon Production with Generative Post-KeyframingPoster
  786. TopoFormer: Topology Meets Attention for Graph LearningPoster
  787. Topological Anomaly Quantification for Semi-supervised Graph Anomaly DetectionPoster
  788. Topological Causal EffectsPoster
  789. Topological Flow MatchingPoster
  790. Topology Matters in RTL Circuit Representation LearningPoster
  791. Topology and geometry of the learning space of ReLU networks: connectivity and singularitiesPoster
  792. Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question AnsweringPoster
  793. Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving SilkPoster
  794. Toward Complex-Valued Neural Networks for Waveform GenerationPoster
  795. Toward Conservative Planning from Preferences in Offline Reinforcement LearningPoster
  796. Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference LearningPoster
  797. Toward Efficient Exploration by Large Language Model AgentsPoster
  798. Toward Enhancing Representation Learning in Federated Multi-Task SettingsPoster
  799. Toward Faithful Retrieval-Augmented Generation with Sparse AutoencodersPoster
  800. Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual ConnectionsPoster
  801. Toward Principled Flexible Scaling for Self-Gated Neural ActivationPoster
  802. Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming VulnerabilityPoster
  803. Toward Universal and Transferable Jailbreak Attacks on Vision-Language ModelsPoster
  804. Towards All-Atom Foundation Models for Biomolecular Binding Affinity PredictionPoster
  805. Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly DetectionPoster
  806. Towards Better Branching Policies: Leveraging the Sequential Nature of Branch-and-Bound TreePoster
  807. Towards Better Optimization For Listwise Preference in Diffusion ModelsPoster
  808. Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid ControlPoster
  809. Towards Cognitively-Faithful Decision-Making Models to Improve AI AlignmentPoster
  810. Towards Dynamic Interleaving OptimizersPoster
  811. Towards Efficient Constraint Handling in Neural Solvers for Routing ProblemsPoster
  812. Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank ExtensionPoster
  813. Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language ModelsPoster
  814. Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant LearningPoster
  815. Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language ModelsPoster
  816. Towards High Data Efficiency in Reinforcement Learning with Verifiable RewardPoster
  817. Towards Improved Sentence Representations using Token GraphsPoster
  818. Towards Improvisational TAMP: Learning Low-Level Shortcuts in Abstract Planning GraphsPoster
  819. Towards Interpretable Visual Decoding with Attention to Brain RepresentationsPoster
  820. Towards Knowledge‑and‑Data‑Driven Organic Reaction Prediction: RAG‑Enhanced and Reasoning‑Powered Hybrid System with LLMsPoster
  821. Towards Learned Optimization Free LunchPoster
  822. Towards Lossless Memory-efficient Training of Spiking Neural Networks via Gradient Checkpointing and Spike CompressionPoster
  823. Towards Multimodal Data-Driven Scientific Discovery Powered by LLM AgentsPoster
  824. Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed InteractionPoster
  825. Towards One-step Causal Video Generation via Adversarial Self-DistillationPoster
  826. Towards Persistent Noise-Tolerant Active Learning of Regular Languages with Class QueryPoster
  827. Towards Personalized Deep Research: Benchmarks and EvaluationsICLR 2026 ConditionalPoster
  828. Towards Physically Executable 3D Gaussian for Embodied NavigationPoster
  829. Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without DisclosurePoster
  830. Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a MeasurementPoster
  831. Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMsPoster
  832. Towards Real-World Routing with Neural Combinatorial OptimizationPoster
  833. Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function CallingPoster
  834. Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object DetectionPoster
  835. Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and MissingnessPoster
  836. Towards Safe Reasoning in Large Reasoning Models via Corrective InterventionPoster
  837. Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov FrameworkPoster
  838. Towards Sampling Data Structures for Tensor Products in Turnstile StreamsPoster
  839. Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time ExplorationPoster
  840. Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPOPoster
  841. Towards Sequence Modeling Alignment between Tokenizer and Autoregressive ModelPoster
  842. Towards Spatial Supersensing in VideoPoster
  843. Towards Strategic Persuasion with Language ModelsPoster
  844. Towards Sustainable Investment Policies Informed by Opponent ShapingPoster
  845. Towards Text-Mask Consistency in Medical Image SegmentationPoster
  846. Towards True Speech-to-Speech Models Without Text GuidancePoster
  847. Towards Understanding Subliminal Learning: When and How Hidden Biases TransferPoster
  848. Towards Understanding The Calibration Benefits of Sharpness-Aware MinimizationPoster
  849. Towards Understanding Valuable Preference Data for Large Language Model AlignmentPoster
  850. Towards Understanding the Nature of Attention with Low-Rank Sparse DecompositionPoster
  851. Towards Understanding the Shape of Representations in Protein Language ModelsPoster
  852. Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AIPoster
  853. Towards a Foundation Model for Crowdsourced Label AggregationPoster
  854. Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual BanditsPoster
  855. Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D GeneralisationPoster
  856. Towards a Universally Transferable Acceleration Method for Density Functional TheoryPoster
  857. TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM ReasoningPoster
  858. Trace Anything: Representing Any Video in 4D via Trajectory FieldsPoster
  859. Traceable Black-Box Watermarks For Federated LearningPoster
  860. Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and MethodPoster
  861. Tracing and Reversing Edits in LLMsPoster
  862. Tracing the Traces: Latent Temporal Signals for Efficient and Accurate ReasoningPoster
  863. Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural NetworksPoster
  864. Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial TradingPoster
  865. Train Once, Answer All: Many Pretraining Experiments for the Cost of OnePoster
  866. Train on Validation (ToV): Fast data selection with applications to fine-tuningPoster
  867. Train-before-Test Harmonizes Language Model RankingsOral
  868. TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable ConfidencePoster
  869. Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMsPoster
  870. Training Deep Normalization-Free Spiking Neural Networks with Lateral InhibitionPoster
  871. Training Dynamics Impact Post-Training Quantization RobustnessPoster
  872. Training Large Language Models To Reason In Parallel With Global Forking TokensPoster
  873. Training Large Reasoning Models Efficiently via Progressive Thought EncodingPoster
  874. Training-Free Determination of Network Width via Neural Tangent KernelPoster
  875. Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact MatchPoster
  876. Training-Free Reward-Guided Image Editing via Trajectory Optimal ControlPoster
  877. Training-Free Text-Guided Color Editing with Multi-Modal Diffusion TransformerPoster
  878. Training-free Counterfactual Explanation for Temporal Graph Model InferencePoster
  879. TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching ModelsPoster
  880. TrajTok: What makes for a good trajectory tokenizer in behavior generation?Poster
  881. Trajectory Generation with Conservative Value Guidance for Offline Reinforcement LearningPoster
  882. Trajectory-aware Shifted State Space Models for Online Video Super-ResolutionPoster
  883. Transducing Language ModelsPoster
  884. Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial ReasoningPoster
  885. Transfer Learning in Infinite Width Feature Learning NetworksPoster
  886. Transferable and Stealthy Adversarial Attacks on Large Vision-Language ModelsPoster
  887. Transformers Don’t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic InterpretabilityPoster
  888. Transformers Learn Latent Mixture Models In-Context via Mirror DescentPoster
  889. Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher ModelsPoster
  890. Transformers are Inherently SuccinctPoster
  891. Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax OptimalityPoster
  892. Transformers as Unsupervised Learning Algorithms: A study on Gaussian MixturesPoster
  893. Transformers with Endogenous In-Context Learning: Bias Characterization and MitigationPoster
  894. Transitive RL: Value Learning via Divide and ConquerPoster
  895. Translate Policy to Language: Flow Matching Generated Rewards for LLM ExplanationsPoster
  896. Translating Flow to Policy via Hindsight Online ImitationPoster
  897. Translation Heads: Unveiling Attention's Role in LLM Multilingual TranslationPoster
  898. Trapped by simplicity: When Transformers fail to learn from noisy featuresPoster
  899. Tree Search for LLM Agent Reinforcement LearningPoster
  900. Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming AttacksPoster
  901. Tree-sliced Sobolev IPMPoster
  902. TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion ModelsPoster
  903. TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision TreesPoster
  904. TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion GenerationPoster
  905. TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural NetworksPoster
  906. Triangle Multiplication is All You Need for Biomolecular Structure RepresentationsPoster
  907. Tricks or Traps? A Deep Dive into RL for LLM ReasoningPoster
  908. TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time ScalingPoster
  909. Trinity: An Evolved LLM CoordinatorPoster
  910. Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?Oral
  911. TripleSumm: Adaptive Triple-Modality Fusion for Video SummarizationPoster
  912. TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization ModelsPoster
  913. True Self-Supervised Novel View Synthesis is TransferableOral
  914. Trust The TypicalPoster
  915. Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation ModelingPoster
  916. Trust-Region Adaptive Policy OptimizationPoster
  917. TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation ModelsPoster
  918. TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate ThemPoster
  919. Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in ExplanationsPoster
  920. Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer PredictionPoster
  921. Tucker-FNO: Tensor Tucker-Fourier Neural Operator and its Universal Approximation TheoryPoster
  922. Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector MergingPoster
  923. TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor AnalysisPoster
  924. Tuning the burn-in phase in training recurrent neural networks improves their performancePoster
  925. Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image CompressionPoster
  926. TurboBoA: Faster and Exact Attention-aware Quantization without BackpropagationPoster
  927. TurboQuant: Online Vector Quantization with Near-optimal Distortion RatePoster
  928. Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMsPoster
  929. TusoAI: Agentic Optimization for Scientific MethodsPoster
  930. Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky SimilarityPoster
  931. TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial FlowsPoster
  932. TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action ModelsPoster
  933. Two (narrow) heads are better than (an arbitrarily wide) onePoster
  934. Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisationPoster
  935. Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen AnomaliesPoster
  936. Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental LearningPoster
  937. Type-Compliant Adaptation CascadesPoster
  938. TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared PrefixPoster
  939. U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMsPoster
  940. U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound UnderstandingPoster
  941. UALM: Unified Audio Language Model for Understanding, Generation and ReasoningOral
  942. UFO-4D: Unposed Feedforward 4D reconstruction from Two ImagesPoster
  943. UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as ReasoningPoster
  944. UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information SeekingPoster
  945. ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted InferencePoster
  946. ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional ViewsPoster
  947. UME-R1: Exploring Reasoning-Driven Generative Multimodal EmbeddingsPoster
  948. UNDERSTANDING TRANSFORMERS FOR TIME SEIRES FORECASTING: A CASE STUDY ON MOIRAIPoster
  949. UNITE: Universal kNowledge Integration from Task-specific ExpertsPoster
  950. UNIVERSAL AND EFFICIENT LOADING BALANCING FOR RL TRAINING OF LARGE MULTIMODAL MODELSPoster
  951. UP2You: Fast Reconstruction of Yourself from Unconstrained Photo CollectionsPoster
  952. USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning Capabilities of LLMs as Urban AgentsPoster
  953. Ultra-Fast Language Generation via Discrete Diffusion Divergence InstructPoster
  954. UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound VolumesPoster
  955. UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language ModelsPoster
  956. UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context LearningPoster
  957. UltraViCo: Breaking Extrapolation Limits in Video Diffusion TransformersPoster
  958. UnLoc: Leveraging Depth Uncertainties for Floorplan LocalizationPoster
  959. Unbalanced Soft-Matching Distance For Neural Representational Comparison With Partial Unit CorrespondencePoster
  960. Unbiased Gradient Estimation for Event Binning via Functional BackpropagationPoster
  961. Uncertainty Estimation via Hyperspherical Confidence MappingPoster
  962. Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D ReconstructionPoster
  963. Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-AnsweringPoster
  964. Uncertainty-Aware 3D Reconstruction for Dynamic Underwater ScenesPoster
  965. Uncertainty-Aware Diagnostics for Physics-Informed Machine LearningPoster
  966. Uncertainty-Aware Gaussian Map for Vision-Language NavigationPoster
  967. Uncertainty-driven Embedding ConvolutionPoster
  968. Uncover Underlying Correspondence for Robust Multi-view ClusteringOral
  969. Uncovering Conceptual Blindspots in Generative Image Models Using Sparse AutoencodersPoster
  970. Uncovering Robot Vulnerabilities through Semantic Potential FieldsPoster
  971. Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided DiffusionPoster
  972. Understanding Dataset Distillation via Spectral FilteringPoster
  973. Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel MethodsPoster
  974. Understanding Language Prior of LVLMs by Contrasting Chain-of-EmbeddingPoster
  975. Understanding Routing Mechanism in Mixture-of-Experts Language ModelsPoster
  976. Understanding Sensitivity of Differential Attention through the Lens of Adversarial RobustnessPoster
  977. Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and LimitationsPoster
  978. Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and CompressibilityPoster
  979. Understanding VLMs Spatial Mental Modeling Capability from Limited ViewsPoster
  980. Understanding and Improving Continuous LLM Adversarial Training via In-context Learning TheoryPoster
  981. Understanding and Improving Hyperbolic Deep Reinforcement LearningPoster
  982. Understanding and Improving Length Generalization in Hierarchical Sparse Attention ModelsPoster
  983. Understanding and Relaxing the Limitations of Transformers for Linear AlgebraPoster
  984. Understanding and improving Shampoo and SOAP via Kullback-Leibler MinimizationPoster
  985. Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent KernelPoster
  986. Understanding the Emergence of Seemingly Useless Features in Next-Token PredictorsPoster
  987. Understanding the Implicit Biases of Design Choices for Time Series Foundation ModelsPoster
  988. Understanding the Learning Phases in Self-Supervised Learning via Critical PeriodsPoster
  989. Understanding the Mechanisms of Fast Hyperparameter TransferPoster
  990. Understanding the Mixture-of-Experts with Nadaraya-Watson KernelPoster
  991. Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID DataPoster
  992. Understanding the Role of Training Data in Test-Time ScalingPoster
  993. Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal ModelsPoster
  994. Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual SimulationsPoster
  995. Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and VisionPoster
  996. Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMsPoster
  997. Uni-NTFM: A Unified Foundation Model for EEG Signal Representation LearningPoster
  998. Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal ModelsPoster
  999. UniCA: Unified Covariate Adaptation for Time Series Foundation ModelPoster
  1000. UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese CalligraphyPoster

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