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.

1. $AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-TuningPoster
2. $PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video ModelsOral
3. $\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ DivergencePoster
4. $\boldsymbol{\partial^\infty}$-Grid: A Neural Differential Equation Solver with Differentiable Feature GridsPoster
5. $\ell_1$ Latent Distance based Continuous-time Graph RepresentationPoster
6. $\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed GeneralizationPoster
7. $\mu$LO: Compute-Efficient Meta-Generalization of Learned OptimizersPoster
8. $\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual SpacePoster
9. $\pi^3$: Permutation-Equivariant Visual Geometry LearningPoster
10. $\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solvingPoster
11. $\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image GenerationPoster
12. $p\textrm{-less}$ Sampling: A Robust Hyperparameter-Free Approach for LLM DecodingOral
13. (Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Privacy Assessment for LLMsPoster
14. (U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEsPoster
15. **TandemFoilSet**: Datasets for Flow Field Prediction of Tandem-Airfoil Through the Reuse of Single AirfoilsPoster
16. 3D Aware Region Prompted Vision Language ModelPoster
17. 3D Scene Prompting for Scene-Consistent Camera-Controllable Video GenerationPoster
18. 3D-aware Disentangled Representation for Compositional Reinforcement LearningPoster
19. 3DCS: Datasets and Benchmark for Evaluating Conformational Sensitivity in Molecular RepresentationsPoster
20. 3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic CamerasPoster
21. 3DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud AnalysisPoster
22. <SO$G_k$>: One LLM Token for Explicit Graph Structural UnderstandingPoster
23. A Balanced Neuro-Symbolic Approach for Commonsense Abductive LogicPoster
24. A Bayesian Nonparametric Framework For Learning Disentangled RepresentationsPoster
25. A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data SynthesisPoster
26. A Benchmark for Deep Information SynthesisPoster
27. A Biologically Plausible Dense Associative Memory with Exponential CapacityPoster
28. A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality ConstraintsPoster
29. A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning across Broad Atlases and DisordersPoster
30. A Brain-Inspired Gating Mechanism Unlocks Robust Computation in Spiking Neural NetworksPoster
31. A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual DecodingPoster
32. A Comprehensive Information-Decomposition Analysis of Large Vision-Language ModelsPoster
33. A Convergence Analysis of Adaptive Optimizers under Floating-point QuantizationPoster
34. A Dense Subset Index for Collective Query CoveragePoster
35. A Derandomization Framework for Structure Discovery: Applications in Neural Networks and BeyondPoster
36. A Fair Bayesian Inference through Matched Gibbs PosteriorPoster
37. A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QAPoster
38. A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of ComponentsPoster
39. A Fictional Q&A Dataset for Studying Memorization and Knowledge AcquisitionPoster
40. A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice ExperimentsPoster
41. A Function-Centric Graph Neural Network Approach for Predicting Electron DensitiesPoster
42. A General Framework for Black-Box Attacks Under Cost AsymmetryPoster
43. A General Spatio-Temporal Backbone with Scalable Contextual Pattern Bank for Urban Continual ForecastingPoster
44. A Generalized Geometric Theoretical Framework of Centroid Discriminant Analysis for Linear Classification of Multi-dimensional DataPoster
45. A Genetic Algorithm for Navigating Synthesizable Molecular SpacesPoster
46. A Graph Meta-Network for Learning on Kolmogorov–Arnold NetworksPoster
47. A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-SpacePoster
48. A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion TransformersPoster
49. A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic OptimizationPoster
50. A High Quality Dataset and Reliable Evaluation for Interleaved Image-Text GenerationPoster
51. A Joint Diffusion Model with Pre-Trained Priors for RNA Sequence–Structure Co-DesignPoster
52. A Law of Data Reconstruction for Random Features (And Beyond)Poster
53. A Memory-Efficient Hierarchical Algorithm for Large-scale Optimal Transport ProblemsPoster
54. A Near-Optimal Best-of-Both-Worlds Algorithm for Federated BanditsPoster
55. A New Approach to Controlling Linear Dynamical SystemsPoster
56. A New Initialization to Control Gradients in Sinusoidal Neural NetworksPoster
57. A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation InputPoster
58. A Noise is Worth Diffusion GuidancePoster
59. A One-shot Framework for Directed Evolution of AntibodiesPoster
60. A Physics-Inspired Optimizer: Velocity Regularized AdamPoster
61. A Primer on SO(3) Action Representations in Deep Reinforcement LearningPoster
62. A Probabilistic Hard Concept Bottleneck for Steerable Generative ModelsPoster
63. A Problem-Oriented Perspective and Anchor Verification for Code OptimizationPoster
64. A Recovery Guarantee for Sparse Neural NetworksPoster
65. A Relative Error-Based Evaluation Framework of Heterogeneous Treatment Effect EstimatorsPoster
66. A Representer Theorem for Hawkes Processes via Penalized Least Squares MinimizationOral
67. A Resolution-Agnostic Geometric Transformer for Chromosome Modeling Using Inertial FramePoster
68. A Reward-Free Viewpoint on Multi-Objective Reinforcement LearningPoster
69. A Rich Knowledge Space for Scalable Deepfake DetectionPoster
70. A Scalable Constant-Factor Approximation Algorithm for $W_p$ Optimal TransportPoster
71. A Scalable Distributed Framework for Multimodal GigaVoxel Image RegistrationOral
72. A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign PredictionPoster
73. A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image FeaturesPoster
74. A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal ControlPoster
75. A Sharp KL-Convergence Analysis for Diffusion Models under Minimal AssumptionsPoster
76. A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning ModelsPoster
77. A Single Architecture for Representing Invariance Under Any Space GroupPoster
78. A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systemsPoster
79. A State-Transition Framework for Efficient LLM ReasoningPoster
80. A Statistical Benchmark for Diffusion Posterior Sampling AlgorithmsPoster
81. A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport SolversPoster
82. A Statistical Theory of Overfitting for Imbalanced ClassificationPoster
83. A Step to Decouple Optimization in 3DGSPoster
84. A Stitch in Time Saves Nine: Proactive Self-Refinement for Language ModelsPoster
85. A Structured, Tagged, and Localized Visual Question Answering Dataset with Full Sentence Answers and Scene Graphs for Chest X-ray ImagesPoster
86. A Study of Posterior Stability in Time-Series Latent DiffusionPoster
87. A Study on PAVE Specification for LearnwarePoster
88. A Tale of Two Smoothness Notions: Adaptive Optimizers and Non-Euclidean DescentPoster
89. A Theoretical Analysis of Mamba’s Training Dynamics: Filtering Relevant Features for Generalization in State Space ModelsPoster
90. A Training-Free Framework for Long Video Understanding via Video-Query-Options SimilarityPoster
91. A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow ModelingPoster
92. A Unification of Discrete, Gaussian, and Simplicial DiffusionPoster
93. A Unified Federated Framework for Trajectory Data Preparation via LLMsPoster
94. A Unified Total Variation Framework for Membrane Potential Perturbation DynamicPoster
95. A Unifying View of Coverage in Linear Off-policy EvaluationPoster
96. A foundation model with multi-variate parallel attention to generate neuronal activityPoster
97. A tale of two tails: Preferred and anti-preferred natural stimuli in visual cortexPoster
98. A universal compression theory: Lottery ticket hypothesis and superpolynomial scaling lawsPoster
99. A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid ReasoningPoster
100. A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement LearningPoster
101. A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language ModelsPoster
102. A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question AnsweringPoster
103. A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent SystemsPoster
104. A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language ModelsPoster
105. ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation ModelsPoster
106. AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic TransferPoster
107. AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings AlgorithmPoster
108. ACADREASON: Exploring the Limits of Reasoning Models with Academic Research ProblemsPoster
109. ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion PersonalizationPoster
110. ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual RecallPoster
111. ACPBench Hard: Unrestrained Reasoning about Action, Change, and PlanningPoster
112. ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled TuningPoster
113. ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and EvaluationPoster
114. AEGIS: Adversarial Target–Guided Retention-Data-Free Robust Concept Erasure from Diffusion ModelsPoster
115. AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and DesignPoster
116. AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation EditingPoster
117. AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent FrameworkPoster
118. AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space ModelsPoster
119. ALM-MTA: Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem OptimizationPoster
120. AMLRIS: Alignment-aware Masked Learning for Referring Image SegmentationPoster
121. AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill DiversificationPoster
122. AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon ConversationsPoster
123. AMiD: Knowledge Distillation for LLMs with $\alpha$-mixture Assistant DistributionPoster
124. AP-OOD: Attention Pooling for Out-of- Distribution DetectionPoster
125. APC-RL: Exceeding data-driven behavior priors with adaptive policy compositionPoster
126. APPLE: Toward General Active Perception via Reinforcement LearningPoster
127. APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt TuningPoster
128. AQER: A Scalable and Efficient Data Loader for Digital Quantum ComputersPoster
129. AQuA: Toward Strategic Response Generation for Ambiguous Visual QuestionsPoster
130. ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy ShapingPoster
131. ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame ForecastingPoster
132. ARINBEV: Bird's-Eye View Layout Estimation with Conditional Autoregressive ModelPoster
133. ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement LearningPoster
134. ARMOR: Aligning Secure and Safe Large Language Models via Meticulous ReasoningPoster
135. ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix FactorizationPoster
136. ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play AttacksPoster
137. ARROW: An Adaptive Rollout and Routing Method for Global Weather ForecastingPoster
138. ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward GuidancePoster
139. ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII ArtPoster
140. ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking AttackPoster
141. ASIDE: Architectural Separation of Instructions and Data in Language ModelsPoster
142. ASMIL: Attention-Stabilized Multiple Instance Learning for Whole-Slide ImagingPoster
143. ASSESS: A Semantic and Structural Evaluation Framework for Statement SimilarityPoster
144. ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series ForecastingPoster
145. ASTRAEA: A Token-wise Acceleration Framework for Video Diffusion TransformersPoster
146. ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural NetworksPoster
147. ATGen: Adversarial Reinforcement Learning for Test Case GenerationPoster
148. ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of MultilingualityPoster
149. ATLAS: Alibaba Dataset and Benchmark for Learning-Augmented SchedulingPoster
150. ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel PlanningPoster
151. ATOM: A Pretrained Neural Operator for Multitask Molecular DynamicsPoster
152. ATPO: ADAPTIVE TREE POLICY OPTIMIZATION FOR MULTI-TURN MEDICAL DIALOGUEPoster
153. ATTS: Asynchronous Test-Time Scaling via Conformal PredictionPoster
154. AUHead: Realistic Emotional Talking Head Generation via Action Units ControlPoster
155. AVERE: Improving Audiovisual Emotion Reasoning with Preference OptimizationPoster
156. AVEX: What Matters for Animal Vocalization EncodingPoster
157. AVoCaDO: An Audiovisual Video Captioner Driven by Temporal OrchestrationPoster
158. AWM: Accurate Weight-Matrix Fingerprint for Large Language ModelsPoster
159. A^2TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene RepresentationPoster
160. AbdCTBench: Learning Clinical Biomarker Representations from Abdominal Surface GeometryPoster
161. AbsTopK: Rethinking Sparse Autoencoders For Bidirectional FeaturesPoster
162. AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract ThinkingPoster
163. Abstracting Robot Manipulation Skills via Mixture-of-Experts Diffusion PoliciesPoster
164. Accelerated Learning with Linear Temporal Logic using Differentiable SimulationPoster
165. Accelerated Parallel Tempering via Neural TransportsPoster
166. Accelerated co-design of robots through morphological pretrainingPoster
167. Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set SelectionPoster
168. Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden PrinciplesPoster
169. Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory DistillationPoster
170. Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace FilterPoster
171. Accelerating Inference for Multilayer Neural Networks with Quantum ComputersPoster
172. Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning AlgorithmsPoster
173. AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL SynergyPoster
174. Achieving Approximate Symmetry Is Exponentially Easier than Exact SymmetryPoster
175. Achieving Expert-Level Agent from Foundation Model via Complexity Curriculum Reinforcement Learning with Synthetic DataPoster
176. Achieving low-bit Muon through subspace preservation and grid quantizationPoster
177. Action Chunking and Data Augmentation Yield Exponential Improvements in Behavior Cloning for Continuous SpacesPoster
178. Action-Free Offline-To-Online RL via Discretised State PoliciesPoster
179. Action-Guided Attention for Video Action AnticipationPoster
180. Action-aware Dynamic Pruning for Efficient Vision-Language-Action ManipulationPoster
181. Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph InferenceOral
182. Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic ForgettingPoster
183. Activation Function Design Sustains Plasticity in Continual LearningPoster
184. Activation Steering for LLM Alignment via a Unified ODE-Based FrameworkPoster
185. Activation Steering with a Feedback ControllerPoster
186. ActivationReasoning: Logical Reasoning in Latent Activation SpacesPoster
187. Active Learning for Decision Trees with Provable GuaranteesPoster
188. Active Learning of 3D Gaussian Splatting with Consistent Region Partition and Robust Pose EstimationPoster
189. ActiveCQ: Active Estimation of Causal QuantitiesPoster
190. ActiveDPO: Active Direct Preference Optimization for Sample-Efficient AlignmentPoster
191. AdAEM: An Adaptively and Automated Extensible Evaluation Method of LLMs' Value DifferenceOral
192. AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference OptimizationPoster
193. AdS-GNN - a Conformally Equivariant Graph Neural NetworkPoster
194. Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-MakingPoster
195. AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM ServingPoster
196. AdaRank: Adaptive Rank Pruning for Enhanced Model MergingPoster
197. AdaReasoner: Dynamic Tool Orchestration for Iterative Visual ReasoningPoster
198. AdaSpec: Adaptive Spectrum for Enhanced Node DistinguishabilityPoster
199. AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D ScenesPoster
200. Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation ModelsPoster
201. Adapting Self-Supervised Representations as a Latent Space for Efficient GenerationPoster
202. Adaptive Acquisition Selection for Bayesian Optimization with Large Language ModelsPoster
203. Adaptive Attacks on Trusted Monitors Subvert AI Control ProtocolsPoster
204. Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic SegmentationPoster
205. Adaptive Canonicalization with Application to Invariant Anisotropic Geometric NetworksPoster
206. Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual LearningPoster
207. Adaptive Concept Discovery for Interpretable Few-Shot Text ClassificationPoster
208. Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring.Poster
209. Adaptive Conformal Guidance for Learning under UncertaintyPoster
210. Adaptive Conformal Prediction via Mixture-of-Experts Gating SimilarityPoster
211. Adaptive Data-Knowledge Alignment in Genetic Perturbation PredictionPoster
212. Adaptive Debiasing Tsallis Entropy for Test-Time AdaptationPoster
213. Adaptive Domain Shift in Diffusion Models for Cross-Modality Image TranslationPoster
214. Adaptive Gaussian Expansion for On-the-fly Category DiscoveryPoster
215. Adaptive Hopfield Network: Rethinking Similarities in Associative MemoryPoster
216. Adaptive Logit Adjustment for Debiasing Multimodal Language ModelsPoster
217. Adaptive Mamba Neural OperatorsPoster
218. Adaptive Methods Are Preferable in High Privacy Settings: An SDE PerspectivePoster
219. Adaptive Mixture of Disentangled Experts for Dynamic Graphs under Distribution ShiftsPoster
220. Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion SamplingPoster
221. Adaptive Nonlinear Compression for Large Foundation ModelsPoster
222. Adaptive Regularization for Large-Scale Sparse Feature Embedding ModelsPoster
223. Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable RewardsPoster
224. Adaptive Scaling of Policy Constraints for Offline Reinforcement LearningPoster
225. Adaptive Social Learning via Mode Policy Optimization for Language AgentsPoster
226. Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center CohortsPoster
227. Adaptive Thinking: Large Language Models Know When to Think in Latent SpacePoster
228. Adaptive Width Neural NetworksPoster
229. Adaptive gradient descent on Riemannian manifolds and its applications to Gaussian variational inferencePoster
230. Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language GenerationPoster
231. Addressing divergent representations from causal interventions on neural networksOral
232. Adjusting Prediction Model Through Wasserstein Geodesic for Causal InferencePoster
233. Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior ModelsPoster
234. AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning ModelsPoster
235. Advancing Complex Video Object Segmentation via Progressive Concept ConstructionPoster
236. Advancing End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-TrainingPoster
237. Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-TuningPoster
238. Advancing Spatiotemporal Representations in Spiking Neural Networks via Parametric Invertible TransformationPoster
239. Advancing Universal Deep Learning for Electronic-Structure Hamiltonian Prediction of MaterialsPoster
240. Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language ModelsPoster
241. Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen AttacksPoster
242. Adversarially Pretrained Transformers may be Universally Robust In-Context LearnersPoster
243. Aegis: Automated Error Generation and Identification for Multi-Agent SystemsPoster
244. AesCoder: Code Aesthetics with Agentic Reward FeedbackPoster
245. AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming CompetitionsPoster
246. AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?Poster
247. Agent Data ProtocolOral
248. Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic TasksPoster
249. AgentFold: Long-Horizon Web Agents with Proactive Context FoldingPoster
250. AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RLOral
251. AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented AgentPoster
252. AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement LearningPoster
253. AgentSynth: Scalable Task Generation for Generalist Computer-Use AgentsPoster
254. Agentic Collaboration as an Information Bottleneck ProblemPoster
255. Agentic Context Engineering: Learning Comprehensive Contexts for Self-Improving Language ModelsPoster
256. Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language ModelsPoster
257. Agentic Reinforced Policy OptimizationPoster
258. Agentic Reinforcement Learning with Implicit Step RewardsPoster
259. Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning EnvironmentPoster
260. Algorithm Generation via Creative IdeationPoster
261. Algorithmic Guarantees for Distilling Supervised and Offline RL DatasetsPoster
262. Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety AlignmentPoster
263. Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular DynamicsPoster
264. Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM JudgesPoster
265. Align-SAM: Seeking Flatter Minima for Better Cross-Subset AlignmentPoster
266. Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent GuidancePoster
267. AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal TransportPoster
268. AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow MatchingPoster
269. Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention InstillationPoster
270. Aligner, Diagnose Thyself: A Meta-Learning Paradigm for Fusing Intrinsic Feedback in Preference AlignmentPoster
271. Aligning Collaborative View Recovery and Tensorial Subspace Learning via Latent Representation for Incomplete Multi-View ClusteringPoster
272. Aligning Deep Implicit Preferences by Learning to Reason DefensivelyPoster
273. Aligning Visual Foundation Encoders to Tokenizers for Diffusion ModelsPoster
274. Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference OptimizationPoster
275. Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLMPoster
276. Alignment-Weighted DPO: A principled reasoning approach to improve alignmentPoster
277. All Code, No Thought: Language Models Struggle to Reason in Ciphered LanguagePoster
278. All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch LearningPoster
279. All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-TuningPoster
280. All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian SplattingPoster
281. All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker AdaptationPoster
282. Almost Bayesian: Dynamics of SGD Through Singular Learning TheoryPoster
283. AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement LearningPoster
284. AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement LearningPoster
285. AlphaBench: Benchmarking Large Language Models in Formulaic Alpha Factor MiningPoster
286. AlphaFlow: Understanding and Improving MeanFlow ModelsPoster
287. AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust ExplorationPoster
288. AlphaSteer: Learning Refusal Steering with Principled Null-Space ConstraintPoster
289. Alternating Diffusion for Proximal Sampling with Zeroth Order QueriesPoster
290. Amortising Inference and Meta-Learning Priors in Neural NetworksPoster
291. An Agentic Framework with LLMs for Solving Complex Vehicle Routing ProblemsPoster
292. An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based RepresentationPoster
293. An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language ModelsPoster
294. An Ensemble Framework for Unbiased Language Model WatermarkingPoster
295. An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPsPoster
296. An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention ScorePoster
297. An Information-Theoretical Framework For Optimizing Experimental Design To Distinguish Probabilistic Neural CodesPoster
298. An Open-Ended Benchmark and Formal Framework for Adjuvant Research with MLLMPoster
299. An Optimal Diffusion Approach to Quadratic Rate-Distortion Problems: New Solution and Approximation MethodsPoster
300. An Orthogonal Learner for Individualized Outcomes in Markov Decision ProcessesPoster
301. An efficient, provably optimal, practical algorithm for the 0-1 loss linear classification problemPoster
302. An evolutionary perspective on modes of learning in TransformersPoster
303. Analysis of approximate linear programming solution to Markov decision problem with log barrier functionPoster
304. Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven AnalysisPoster
305. Analyzing and Evaluating Unbiased Language Model WatermarkPoster
306. Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer NormalizationPoster
307. Anatomy-aware Representation Learning for Medical UltrasoundPoster
308. Anchor Frame Bridging for Coherent First-Last Frame Video GenerationPoster
309. Anchored Supervised Fine-TuningPoster
310. AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMsPoster
311. Angle K-MeansPoster
312. Animal behavioral analysis and neural encoding with transformer-based self-supervised pretrainingPoster
313. Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion ModelsPoster
314. Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment ModelingPoster
315. Annotation-Efficient Honesty Alignment via Confidence Elicitation and CalibrationPoster
316. Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient InfluencePoster
317. AntigenLM: Structure-Aware DNA Language Modeling for InfluenzaPoster
318. Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language ModelsPoster
319. Antithetic Noise in Diffusion ModelsPoster
320. Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-DepthPoster
321. Any-Order Any-Subset AutoRegressive ModelPoster
322. Any-Order Flexible Length Masked DiffusionPoster
323. Any-Subgroup Equivariant Networks via Symmetry BreakingPoster
324. Any-step Generation via N-th Order Recursive Consistent Velocity Field EstimationPoster
325. Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion ModelPoster
326. AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMsPoster
327. AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile PerceptionPoster
328. AnyUp: Universal Feature UpsamplingOral
329. Arbitrary Generative Video InterpolationPoster
330. Arbitrary-Order Block SignSGD for Memory-Efficient LLM Fine-TuningPoster
331. Arbitrary-Shaped Image Generation via Spherical Neural Field DiffusionPoster
332. Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding AlignmentPoster
333. Are Deep Speech Denoising Models Robust to Adversarial Noise?Poster
334. Are EEG Foundation Models Worth It? Comparative Evaluation with Traditional Decoders in Diverse BCI TasksPoster
335. Are Global Dependencies Necessary? Scalable Time Series Forecasting via Local Cross-Variate ModelingPoster
336. Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' MemoryPoster
337. Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?Poster
338. Are we measuring oversmoothing in graph neural networks correctly?Poster
339. Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency GraphPoster
340. ArtUV: Artist-style UV UnwrappingPoster
341. ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot LearningPoster
342. Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static DisentanglementPoster
343. Assembling the Mind's Mosaic: Towards EEG Semantic Intent DecodingPoster
344. AssetFormer: Modular 3D Assets Generation with Autoregressive TransformerPoster
345. AssoMem: Scalable Memory QA with Multi-Signal Associative RetrievalPoster
346. AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research SuiteOral
347. Astra: General Interactive World Model with Autoregressive DenoisingPoster
348. Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoningPoster
349. Asymmetric Synthetic Data Update for Domain Incremental Dataset DistillationPoster
350. Asymptotic analysis of shallow and deep forgetting in replay with neural collapsePoster
351. AsyncBEV: Cross-modal flow alignment in Asynchronous 3D Object DetectionPoster
352. Asynchronous Denoising Diffusion Models for Aligning Text-to-Image GenerationPoster
353. Asynchronous Matching with Dynamic Sampling for Multimodal Dataset DistillationPoster
354. Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement LearningPoster
355. AtC: Aggregate-then-Calibrate for Human-centered AssessmentPoster
356. AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAMPoster
357. Atomic HINs: Entity-Attribute Duality for Heterogeneous Graph ModelingPoster
358. AttTok: Marrying Attribute Tokens with Generative Pre-trained Vision-Language Models towards Medical Image UnderstandingPoster
359. Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic DeflectionPoster
360. Attend to the Active: Structure-Aware Dynamic Attention in LLMs for Compositional Instruction FollowingPoster
361. Attention Is All You Need for KV Cache in Diffusion LLMsPoster
362. Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same CoinPoster
363. Attention Smoothing Is All You Need For UnlearningPoster
364. Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning ModelsPoster
365. Attention, Please! Revisiting Attentive Probing Through the Lens of EfficiencyPoster
366. AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion ModelsPoster
367. Attributing Response to Context: A Jensen–Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented GenerationPoster
368. Attribution-Guided DecodingPoster
369. AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language ModelsPoster
370. AudioX: A Unified Framework for Anything-to-Audio GenerationPoster
371. Auditing Black-Box LLM APIs with a Rank-Based Uniformity TestPoster
372. Augmented Radiance Field: A General Framework for Enhanced Gaussian SplattingPoster
373. Aurelius: Relation Aware Text-to-Audio Generation At ScalePoster
374. Aurora: Towards Universal Generative Multimodal Time Series ForecastingPoster
375. Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language ModelsPoster
376. AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology LaboratoryPoster
377. AutoCode: LLMs as Problem Setters for Competitive ProgrammingPoster
378. AutoCodeBench: Large Language Models are Automatic Code Benchmark GeneratorsPoster
379. AutoDA-Timeseries: Automated Data Augmentation for Time SeriesPoster
380. AutoDV: An End-to-End Deep Learning Model for High-Dimensional Data VisualizationPoster
381. AutoDrive-R²: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous DrivingPoster
382. AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic AlgorithmsOral
383. AutoFigure: Generating and Refining Publication-Ready Scientific IllustrationsPoster
384. AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the WildPoster
385. AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive ReasoningPoster
386. AutoLibra: Agent Metric Induction from Open-Ended Human FeedbackPoster
387. AutoMetrics: Approximate Human Judgments with Automatically Generated EvaluatorsPoster
388. AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity OptimizationPoster
389. AutoQVLA: Not All Channels Are Equal in Vision-Language-Action Model's QuantizationPoster
390. AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence ParallelismPoster
391. AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy ConstraintsPoster
392. Autoencoding-Free Context Compression for LLMs via Contextual Semantic AnchorsPoster
393. Automata Learning and Identification of the Support of Language ModelsPoster
394. Automated Formalization via Conceptual Retrieval-Augmented LLMsPoster
395. Automated Interpretability Metrics Do Not Distinguish Trained and Random TransformersPoster
396. Automated Stateful Specialization for Adaptive Agent SystemsPoster
397. Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak StrategiesPoster
398. Automatic Image-Level Morphological Trait Annotation for Organismal ImagesPoster
399. Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?Poster
400. Automatic and Structure-Aware Sparsification of Hybrid Neural ODEs with Application to Glucose PredictionPoster
401. Automating the Refinement of Reinforcement Learning SpecificationsPoster
402. Autonomous Play with Correspondence-Driven Trajectory WarpingPoster
403. Autoregressive Image Generation with Randomized Parallel DecodingPoster
404. Autoregressive Visual Decoding from EEG SignalsPoster
405. Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image CompressionPoster
406. Avey-BPoster
407. Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion ModelsPoster
408. BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language ModelsPoster
409. BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural ChangePoster
410. BANZ-FS: BANZSL Fingerspelling DatasetPoster
411. BAR: Refactor the Basis of Autoregressive Visual GenerationPoster
412. BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMsPoster
413. BBQ: Boosting Quantization Entropy with Bell Box QuantizationPoster
414. BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger LearningPoster
415. BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental DesignPoster
416. BEP: A Binary Error Propagation Algorithm for Binary Neural Networks TrainingPoster
417. BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement LearningPoster
418. BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic InteractionsOral
419. BIRD: Behavior Induction via Representation-structure DistillationPoster
420. BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video GenerationPoster
421. BOLT: Decision‑Aligned Distillation and Budget-Aware Routing for Constrained Multimodal QA on RobotsPoster
422. BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement FinetuningPoster
423. BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation GamesPoster
424. BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, and RerankersPoster
425. BWCache: Accelerating Video Diffusion Transformers through Block-Wise CachingPoster
426. Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGDPoster
427. Balancing the Experts: Unlocking LoRA-MoE for GRPO via Mechanism-Aware RewardsPoster
428. Bandit Learning in Matching Markets Robust to Adversarial CorruptionsPoster
429. Bandits with Single-Peaked Preferences and Limited ResourcesPoster
430. Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of PlasticityPoster
431. BaseReward: A Strong Baseline for Multimodal Reward ModelPoster
432. Batch Pruning by Activation StabilityPoster
433. Batch and Sequential Unlearning for Neural NetworksPoster
434. Battery Fault: A Comprehensive Dataset and Benchmark for Battery Fault DiagnosisPoster
435. Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement LearningPoster
436. Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length ExtrapolationPoster
437. Bayesian Ensemble for Sequential Decision-MakingPoster
438. Bayesian Evidence-Driven Prototype Evolution for Federated Domain AdaptationPoster
439. Bayesian Influence Functions for Hessian-Free Data AttributionPoster
440. Bayesian Neural Networks for Functional ANOVA ModelPoster
441. Bayesian Parameter Shift Rules in Variational Quantum EigensolversPoster
442. Bayesian Post Training Enhancement of Regression Models with Calibrated RankingsPoster
443. Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown AdversariesPoster
444. Bayesian Test-Time Adaptation via Dirichlet feature projection and GMM-Driven Inference for Motor Imagery EEG DecodingPoster
445. Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!Poster
446. Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMsPoster
447. Behavior Learning (BL)Poster
448. Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization PredictionPoster
449. Belief-Based Offline Reinforcement Learning for Delay-Robust Policy OptimizationPoster
450. Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMsPoster
451. Benchmarking ECG Foundational Models: A Reality Check Across Clinical TasksPoster
452. Benchmarking Empirical Privacy Protection for Adaptations of Large Language ModelsOral
453. Benchmarking LLM Tool-Use in the WildPoster
454. Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive EvaluationPoster
455. Benchmarking Multi-Agent Reinforcement Learning in Power Grid OperationsPoster
456. Benchmarking Open-ended SegmentationPoster
457. Benchmarking Overton Pluralism in LLMsPoster
458. Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural NetworksPoster
459. Benefits and Limitations of Communication in Multi-Agent ReasoningPoster
460. Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical PerspectivePoster
461. Best-of-Infinity: Asymptotic Performance of Test-Time ComputePoster
462. Best-of-Majority: Minimax-Optimal Strategy for Pass@k Inference ScalingPoster
463. Best-of-N through the Smoothing Lens: KL Divergence and Regret AnalysisPoster
464. Best-of-three-worlds Analysis for Dueling Bandits with Borda WinnerPoster
465. Better Bounds for the Distributed Experts ProblemPoster
466. Better Learning-Augmented Spanning Tree Algorithms via Metric Forest CompletionPoster
467. Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal ModelsPoster
468. Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement LearningPoster
469. Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?Poster
470. Beyond Aggregation: Guiding Clients in Heterogeneous Federated LearningPoster
471. Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal FeedbackPoster
472. Beyond Binary Rewards: Training LMs to Reason About Their UncertaintyPoster
473. Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning BenchmarksPoster
474. Beyond DAGs: A Latent Partial Causal Model for Multimodal LearningPoster
475. Beyond Distributions: Geometric Action Control for Continuous Reinforcement LearningPoster
476. Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMsPoster
477. Beyond Ensembles: Simulating All-Atom Protein Dynamics in a Learned Latent SpacePoster
478. Beyond Entity Correlations: Disentangling Event Causal Puzzles in Temporal Knowledge GraphsPoster
479. Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language ModelsPoster
480. Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image SynthesisPoster
481. Beyond Grid-Locked Voxels: Neural Response Functions for Continuous Brain EncodingPoster
482. Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed TokenizationPoster
483. Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination DetectionPoster
484. Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text RetrievalPoster
485. Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining DataPoster
486. Beyond Linear Probes: Dynamic Safety Monitoring for Language ModelsPoster
487. Beyond Linear Processing: Dendritic Bilinear Integration in Spiking Neural NetworksPoster
488. Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TAREPoster
489. Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized SummarizationPoster
490. Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM ReasoningPoster
491. Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion ProcessesPoster
492. Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided MatchingPoster
493. Beyond Membership: Limitations of Add/Remove Adjacency in Differential PrivacyPoster
494. Beyond Multi-Token Prediction: Pretraining LLMs with Future SummariesPoster
495. Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress MonitoringPoster
496. Beyond Outliers: A Study of Optimizers Under QuantizationPoster
497. Beyond Pairwise: Empowering LLM Alignment With (Ranked) Choice ModelingPoster
498. Beyond Pass@ 1: Self-Play with Variational Problem Synthesis Sustains RLVRPoster
499. Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement LearningPoster
500. Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign PromptsOral
501. Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge GroundingPoster
502. Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic FrameworkPoster
503. Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text DetectionPoster
504. Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMsPoster
505. Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable PrefixesPoster
506. Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive RetrievalPoster
507. Beyond Short Steps in Frank-Wolfe AlgorithmsPoster
508. Beyond Simple Graphs: Neural Multi-Objective Routing on MultigraphsPoster
509. Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training StrategyPoster
510. Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with $\boldsymbol{f}$-SoftArgmax Parameterization $\&$ Coupled RegularizationPoster
511. Beyond Spectra: Eigenvector Overlaps in Loss GeometryPoster
512. Beyond Speedup - Utilizing KV Cache for Sampling and ReasoningPoster
513. Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language ModelsPoster
514. Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray DiffractionPoster
515. Beyond Student: An Asymmetric Network for Neural Network InheritancePoster
516. Beyond Text-Only: Towards Multimodal Table Retrieval in Open-WorldPoster
517. Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion ModelPoster
518. Beyond URLs: Metadata Diversity and Position for Efficient LLM PretrainingPoster
519. Beyond Uniformity: Regularizing Implicit Neural Representations through a Lipschitz LensPoster
520. Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion ModelsPoster
521. Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous DrivingPoster
522. Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMsPoster
523. Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP SolversPoster
524. Beyond the Known: An Unknown-Aware Large Language Model for Open-Set Text ClassificationPoster
525. BeyondBench: Benchmark-Free Evaluation of Reasoning in Language ModelsPoster
526. Bi-Criteria Metric DistortionPoster
527. Bi-Lipschitz Autoencoder With Injectivity GuaranteePoster
528. Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale ModelsPoster
529. Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying PromptsPoster
530. Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMsPoster
531. BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language ModelsPoster
532. BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model ResponsesPoster
533. BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge EvaluationPoster
534. BideDPO: Conditional Image Generation with Simultaneous Text and Condition AlignmentPoster
535. Bidirectional Predictive CodingPoster
536. BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose RepresentationsPoster
537. Bilateral Information-aware Test-time Adaptation for Vision-Language ModelsPoster
538. Bilevel Optimization with Lower-Level Uniform Convexity: Theory and AlgorithmPoster
539. Bilinear relational structure fixes reversal curse and enables consistent model editingPoster
540. BindWeave: Subject-Consistent Video Generation via Cross-Modal IntegrationPoster
541. Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient EstimationPoster
542. BioBO: Biology-informed Bayesian Optimization for Perturbation DesignPoster
543. BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation ModelsPoster
544. BioMD: All-atom Generative Model for Biomolecular Dynamics SimulationPoster
545. BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical ImagesPoster
546. BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across BiosignalsOral
547. Biologically Plausible Learning via Bidirectional Spike-Based DistillationPoster
548. Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD MethodsPoster
549. Bird's-eye-view Informed Reasoning DriverPoster
550. Black-Box Privacy Attacks on Shared Representations in Multitask LearningPoster
551. Block Recurrent Dynamics in Vision TransformersPoster
552. Block-Sample MAC-Bayes Generalization BoundsPoster
553. Block-wise Adaptive Caching for Accelerating Diffusion PolicyPoster
554. BoGrape: Bayesian optimization over graphs with shortest-path encodedPoster
555. BoRA: Towards More Expressive Low-Rank Adaptation with Block DiversityPoster
556. Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard ProblemsPoster
557. Boolean Satisfiability via Imitation LearningPoster
558. Boomerang Distillation Enables Zero-Shot Model Size InterpolationPoster
559. Boosted Trees on a Diet: Compact Models for Resource-Constrained DevicesPoster
560. Boosting Medical Visual Understanding From Multi-Granular Language LearningPoster
561. Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy OptimizationPoster
562. Boosting Open Set Recognition Performance through Modulated Representation LearningPoster
563. Boosting for Predictive SufficiencyPoster
564. Bootstrapping MLLM for Weakly‑Supervised Class‑Agnostic Object CountingPoster
565. BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest ManagementPoster
566. Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised ReasoningPoster
567. Bound by semanticity: universal laws governing the generalization-identification tradeoffPoster
568. Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and BeyondPoster
569. Bradley-Terry and Multi-Objective Reward Modeling Are ComplementaryPoster
570. Brain-IT: Image Reconstruction from fMRI via Brain-Interaction TransformerPoster
571. Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation ModelPoster
572. Branch and Bound Search for Exact MAP Inference in Credal NetworksPoster
573. BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion ModelsPoster
574. Branched Schrödinger Bridge MatchingPoster
575. Break the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language ModelsPoster
576. Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI AgentsPoster
577. Breaking Barriers: Do Reinforcement Fine-tuning Gains Transfer To Unseen Domains?Poster
578. Breaking Gradient Temporal Collinearity for Robust Spiking Neural NetworksPoster
579. Breaking Safety Paradox with Feasible Dual Policy IterationPoster
580. Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution TrainingPoster
581. Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent SystemsPoster
582. Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based RegressorsPoster
583. Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code GenerationPoster
584. Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action SetPoster
585. BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous DrivingPoster
586. Bridging Degradation Discrimination and Generation for Universal Image RestorationPoster
587. Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative DecodingPoster
588. Bridging Explainability and Embeddings: BEE Aware of SpuriousnessPoster
589. Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?Poster
590. Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative ModelsPoster
591. Bridging Input Feature Spaces Towards Graph Foundation ModelsPoster
592. Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for TransformersPoster
593. Bridging ML and algorithms: comparison of hyperbolic embeddingsPoster
594. Bridging Past and Future: Distribution-Aware Alignment for Time Series ForecastingPoster
595. Bridging Piano Transcription and Rendering via Disentangled Score Content and StylePoster
596. Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-AdaptationPoster
597. Bridging Successor Measure and Online Policy Learning with Flow Matching-Based RepresentationsPoster
598. Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-ResolutionPoster
599. Bridging the Gap Between Promise and Performance for FP4 QuantizationPoster
600. Bridging the performance-gap between target-free and target-based reinforcement learningPoster
601. Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion ModelsPoster
602. BrowseNet: Knowledge Graph-Based Associative Memory for Contextual Information RetrievalPoster
603. Buckingham $\pi$-Invariant Test‑Time Projection for Robust PDE Surrogate ModelingPoster
604. Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model ReasoningPoster
605. Building a Foundational Guardrail for General Agentic Systems via Synthetic DataPoster
606. Building spatial world models from sparse transitional episodic memoriesPoster
607. Bures Generalized Category DiscoveryPoster
608. Bures-Wasserstein Flow Matching for Graph GenerationPoster
609. ByteFlow: Language Modeling through Adaptive Byte Compression without a TokenizerPoster
610. Byzantine-Robust Federated Learning with Learnable Aggregation WeightsPoster
611. BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step GenerationPoster
612. C-Evolve: Consensus-based Evolution for Prompt GroupsPoster
613. C-Voting: Confidence-Based Test-Time Voting without Explicit Energy FunctionsPoster
614. CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark GenerationPoster
615. CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic DesignPoster
616. CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular LocalizationPoster
617. CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMsPoster
618. CARD: Towards Conditional Design of Multi-agent Topological StructuresPoster
619. CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent AttentionPoster
620. CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic FrameworkPoster
621. CARL: Camera-Agnostic Representation Learning for Spectral Image AnalysisPoster
622. CARL: Preserving Causal Structure in Representation LearningPoster
623. CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language ModelPoster
624. CASteer: Cross-Attention Steering for Controllable Concept ErasurePoster
625. CDBridge: A Cross-omics Post-training Bridge Strategy for Context-aware Biological ModelingPoster
626. CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language ModelsPoster
627. CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local NavigationPoster
628. CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITYPoster
629. CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural OperatorsPoster
630. CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo FilterPoster
631. CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object DetectionsPoster
632. CHAMMI-75: pre-training multi-channel models with heterogeneous microscopy imagesPoster
633. CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid PredictionPoster
634. CIAR: Interval-based Collaborative Decoding for Image Generation AccelerationPoster
635. CIMemories: A Compositional Benchmark For Contextual Integrity In LLMsPoster
636. CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior SamplingPoster
637. CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype LearningPoster
638. CLARC: C/C++ Benchmark for Robust Code SearchPoster
639. CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple PerspectivesPoster
640. CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context EngineeringPoster
641. CLEAR: Calibrated Learning for Epistemic and Aleatoric RiskPoster
642. CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modallyPoster
643. CLIP-FMoE: Scalable CLIP via Fused Mixture-of-Experts with Enforced SpecializationPoster
644. CLUE: Conflict-guided Localization for LLM Unlearning FrameworkPoster
645. CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wildPoster
646. CLoD-GS: Continuous Level-of-Detail via 3D Gaussian SplattingPoster
647. CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter PhysicsPoster
648. CMT-Benchmark: A Benchmark for Condensed Matter Theory Built by Expert ResearchersPoster
649. CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map ModelsPoster
650. CO3: CONTRASTING CONCEPTS COMPOSE BETTERPoster
651. COLD-Steer: Steering Large Language Models via In-Context One-step Learning DynamicsPoster
652. COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General PreferencesPoster
653. COMI: Coarse-to-fine Context Compression via Marginal Information GainPoster
654. COMPACT: COMPositional Atomic-to-Complex Visual Capability TuningPoster
655. COMPASS: Robust Feature Conformal Prediction for Medical Segmentation MetricsPoster
656. CONCUR: A Framework for Continual Constrained and Unconstrained RoutingPoster
657. CONSIGN: Conformal Segmentation Informed by Spatial Groupings via DecompositionPoster
658. CORDS - Continuous Representations of Discrete StructuresPoster
659. CORE: Concept-Oriented Reinforcement for Bridging the Definition–Application Gap in Mathematical ReasoningPoster
660. COSA: Context-aware Output-Space Adapter for Test-Time Adaptation in Time Series ForecastingPoster
661. COSMO-INR: Complex Sinusoidal Modulation for Implicit Neural RepresentationsPoster
662. COSMOS: A Hybrid Adaptive Optimizer for Efficient Training of Large Language ModelsPoster
663. CP-Agent: Context‑Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical PerturbationsPoster
664. CPQS-Tuning: A Model Self-Perception-Based Data Filtering Algorithm for Efficient Instruction Fine-TuningPoster
665. CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series ForecastingPoster
666. CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank StructurePoster
667. CREPE: Controlling diffusion with REPlica ExchangePoster
668. CRONOS: Continuous time reconstruction for 4D medical longitudinal seriesPoster
669. CSRv2: Unlocking Ultra-Sparse EmbeddingsPoster
670. CTBench: Cryptocurrency Time Series Generation BenchmarkPoster
671. CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech RecognitionPoster
672. CTRL&SHIFT: High-quality Geometry-Aware Object Manipulation in Visual GenerationPoster
673. CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement LearningPoster
674. CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single ModelPoster
675. CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement LearningPoster
676. CaReBench: A Fine-grained Benchmark for Video Captioning and RetrievalPoster
677. CaTS: Calibrated Test-Time Scaling for Efficient LLM ReasoningPoster
678. CaTs and DAGs: Integrating Directed Acyclic Graphs with Transformers for Causally Constrained PredictionsPoster
679. Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMsPoster
680. Cache-to-Cache: Direct Semantic Communication Between Large Language ModelsPoster
681. Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative SamplingPoster
682. Calibrated Information Bottleneck for Trusted Multi-modal ClusteringPoster
683. Calibrating Verbalized Confidence with Self-Generated DistractorsPoster
684. Can LLMs Move Beyond Short Exchanges to Realistic Therapy Conversations?Poster
685. Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal JudgmentPoster
686. Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual TasksPoster
687. Can Language Models Discover Scaling Laws?Poster
688. Can Large Language Models Match the Conclusions of Systematic Reviews?Poster
689. Can SAEs reveal and mitigate racial biases of LLMs in healthcare?Poster
690. Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model PracticePoster
691. Can Speech LLMs Think while Listening?Poster
692. Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across TasksPoster
693. Can Vision-Language Models Answer Face to Face Questions in the Real-World?Poster
694. Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective.Poster
695. Can You Hear Me Now? A Benchmark for Long-Range Graph PropagationPoster
696. Can we generate portable representations for clinical time series data using LLMs?Poster
697. Cancer-Myth: Evaluating Large Language Models on Patient Questions with False PresuppositionsPoster
698. Cannistraci-Hebb Training on Ultra-Sparse Spiking Neural NetworksPoster
699. CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement LearningPoster
700. Capability-Based Scaling Trends for LLM-Based Red-TeamingPoster
701. Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of ExpertsPoster
702. Captain Cinema: Towards Short Movie GenerationPoster
703. Capturing Visual Environment Structure Correlates with Control PerformancePoster
704. CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion ModelsPoster
705. Carré du champ flow matching: better quality-generalisation tradeoff in generative modelsPoster
706. Cartridges: Lightweight and general-purpose long context representations via self-studyPoster
707. Cascadia: An Efficient Cascade Serving System for Large Language ModelsPoster
708. Cat-PO: Cross-modal Adaptive Token-rewards for Preference Optimization in Truthful Multimodal LLMsPoster
709. Catalog-Native LLM: Speaking Item-ID dialect with Less Entanglement for RecommendationPoster
710. CatalystBench: A Comprehensive Multi-Task Benchmark for Advancing Language Models in Catalysis SciencePoster
711. Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM PerceptionPoster
712. CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic DataOral
713. Causal Discovery in the Wild: A Voting-Theoretic Ensemble ApproachPoster
714. Causal Discovery via Quantile Partial EffectPoster
715. Causal Imitation Learning under Expert-Observable and Expert-Unobservable ConfoundingPoster
716. Causal Interpretation of Neural Network Computations with Contribution Decomposition (CODEC)Poster
717. Causal Score Conditioning for Multi-Resolution Latent SystemsPoster
718. Causal Structure Learning in Hawkes Processes with Complex Latent Confounder NetworksOral
719. Causal-Steer: Disentangled Continuous Style Control without Parallel CorporaPoster
720. Causality ≠ Invariance: Function and Concept Vectors in LLMsPoster
721. Causally Robust Preference Learning with ReasonsPoster
722. Cautious Optimizers: Improving Training with One Line of CodePoster
723. Cautious Weight DecayPoster
724. CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell AnalysisPoster
725. CerebraGloss: Instruction-Tuning a Large Vision-Language Model for Fine-Grained Clinical EEG InterpretationPoster
726. Certified Evaluation of Model-Level Explanations for Graph Neural NetworksPoster
727. Certifying the Full YOLO Pipeline: A Probabilistic Verification ApproachPoster
728. Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPsPoster
729. ChainGPT: Dual-Reasoning Model with Recurrent Depth and Multi-Rank State UpdatesPoster
730. ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation HallucinationsPoster
731. Change Point Localization and Inference in Dynamic Multilayer NetworksPoster
732. Channel-Aware Mixed-Precision Quantization for Efficient Long-Context InferencePoster
733. Characteristic Root Analysis and Regularization for Linear Time Series ForecastingPoster
734. Characterization and Learning of Causal Graphs with Latent Confounders and Post-treatment Selection from Interventional DataPoster
735. Characterizing Deep Research: A Benchmark and Formal DefinitionPoster
736. Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding SpacePoster
737. Characterizing Pattern Matching and Its Limits on Compositional Task StructuresPoster
738. Characterizing and Mitigating Reasoning Drift in Large Language ModelsPoster
739. Characterizing and Optimizing the Spatial Kernel of Multi Resolution Hash EncodingsPoster
740. Characterizing the Discrete Geometry of ReLU NetworksOral
741. Chart Deep Research in LVLMs via Parallel Relative Policy OptimizationPoster
742. ChartGalaxy: A Dataset for Infographic Chart Understanding and GenerationICLR 2026 ConditionalPoster
743. Charts Are Not Images: On the Challenges of Scientific Chart EditingPoster
744. Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-TrainingPoster
745. ChatInject: Abusing Chat Templates for Prompt Injection in LLM AgentsPoster
746. CheckMate! Watermarking Graph Diffusion Models in Polynomial TimePoster
747. ChemEval: A Multi-level and Fine-grained Chemical Capability Evaluation for Large Language ModelsPoster
748. Chessformer: A Unified Architecture for Chess ModelingPoster
749. Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMsPoster
750. ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language AgentsPoster
751. Choices Speak Louder than QuestionsPoster
752. ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World SimulationPoster
753. ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG BenchmarksPoster
754. Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step ReturnsPoster
755. CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion ModelsPoster
756. Circuit Insights: Towards Interpretability Beyond ActivationsPoster
757. CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit DesignPoster
758. CircuitSense: A Hierarchical Circuit System Benchmark Bridging Visual Comprehension and Symbolic Reasoning in Engineering Design ProcessPoster
759. Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language ModelsPoster
760. CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic SensingPoster
761. CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs?Poster
762. ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation PipelinePoster
763. Clipped Gradient Methods for Nonsmooth Convex Optimization under Heavy-Tailed Noise: A Refined AnalysisPoster
764. CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown ConditionsPoster
765. Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ biasPoster
766. Closing the Gap Between Text and Speech Understanding in LLMsPoster
767. Closing the Modality Gap Aligns Group-Wise SemanticsPoster
768. Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive ModelsPoster
769. Clustering by Denoising: Latent plug-and-play diffusion for single-cell embeddingsPoster
770. Co-occurring Associated REtained concepts in Diffusion UnlearningPoster
771. Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language ModelsPoster
772. CoAct-1: Computer-using Multi-agent System with Coding ActionsPoster
773. CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style TransferPoster
774. CoDA: Agentic Systems for Collaborative Data VisualizationPoster
775. CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset DistillationPoster
776. CoDi: Subject-Consistent and Pose-Diverse Text-to-Image GenerationPoster
777. CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content GenerationPoster
778. CoFact: Conformal Factuality Guarantees for Language Models under Distribution ShiftPoster
779. CoLA: Co-Calibrated Logit Adjustment for Long-Tailed Semi-Supervised LearningPoster
780. CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal ControlPoster
781. CoMAS: Co-Evolving Multi-Agent Systems via Interaction RewardsPoster
782. CoMem: Compositional Concept-Graph Memory for Vision–Language AdaptationPoster
783. CoMind: Towards Community-Driven Agents for Machine Learning EngineeringPoster
784. CoNavBench: Collaborative Long-Horizon Vision-Language Navigation BenchmarkPoster
785. CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning SegmentationPoster
786. CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware AdapterPoster
787. CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMsPoster
788. CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific ReasoningPoster
789. CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for VideosPoster
790. Coarse-to-Fine Learning of Dynamic Causal StructuresPoster
791. Code Driven Planning with Domain-Adaptive SelectorPoster
792. Code World Models for General Game PlayingPoster
793. Code2Bench: Scaling Source and Rigor for Dynamic Benchmark ConstructionPoster
794. CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation ModelPoster
795. CodeGenGuard: A Robust Watermark for Code Generation ModelsPoster
796. CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-ExpertsPoster
797. CodeSense: a Real-World Benchmark and Dataset for Code Semantic ReasoningPoster
798. Codified Finite-state Machines for Role-playingPoster
799. CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem SolvingPoster
800. CogMoE: Signal-Quality–Guided Multimodal MoE for Cognitive Load PredictionPoster
801. CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor DensityPoster
802. CogniMap3D: Cognitive 3D Mapping and Rapid RetrievalPoster
803. Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent CollaborationPoster
804. CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential RecommendationPoster
805. Color3D: Controllable and Consistent 3D Colorization with Personalized ColorizerPoster
806. ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral ProbesPoster
807. ComPhy: Composing Physical Models with end-to-end AlignmentPoster
808. Combination-of-Experts with Knowledge Sharing for Cross-Task Vehicle Routing ProblemsPoster
809. Combinatorial Bandit Bayesian Optimization for Tensor OutputsPoster
810. Combinatorial Rising BanditsPoster
811. Command-V: Training-Free Representation Finetuning TransferPoster
812. Common Corpus: The Largest Collection of Ethical Data for LLM Pre-TrainingOral
813. Communication-Efficient Decentralized Optimization via Double-Communication Symmetric ADMMPoster
814. CompMarkGS: Robust Watermarking for Compressed 3D Gaussian SplattingPoster
815. Compactness and Consistency: A Conjoint Framework for Deep Graph ClusteringOral
816. Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration TestingICLR 2026 ConditionalPoster
817. Comparing the learning dynamics of in-context learning and fine-tuning in language modelsPoster
818. CompassNav: Steering From Path Imitation to Decision Understanding In NavigationPoster
819. Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty QuantificationPoster
820. Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and DurationPoster
821. Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR BenchmarksPoster
822. Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyondPoster
823. Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation ModelsPoster
824. CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMsPoster
825. Composable Sparse Subnetworks via Maximum-Entropy PrinciplePoster
826. Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level CompositionPoster
827. Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal ReasoningPoster
828. Composer: A Search Framework for Hybrid Neural Architecture DesignPoster
829. Composite Optimization with Error Feedback: the Dual Averaging ApproachPoster
830. Composition of Memory Experts for Diffusion World ModelsPoster
831. Composition-Grounded Instruction Synthesis for Visual ReasoningPoster
832. Compositional Diffusion with Guided search for Long-Horizon PlanningOral
833. Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for ReasoningPoster
834. Compositional Generalization through Gradient Search in Nonparametric Latent SpacePoster
835. Compositional Neuro-Symbolic Concepts in Neural ActivitiesPoster
836. Compositional Visual Planning via Inference-Time Diffusion ScalingPoster
837. Compositional amortized inference for large-scale hierarchical Bayesian modelsPoster
838. Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial ReasoningPoster
839. Computational Bottlenecks for Denoising DiffusionsPoster
840. Compute-Optimal Quantization-Aware TrainingPoster
841. Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use AgentsPoster
842. ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use AgentsPoster
843. Computing Equilibrium beyond Unilateral DeviationPoster
844. ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across TypesPoster
845. Concept-Aware Privacy Mechanisms for Defending Embedding Inversion AttacksPoster
846. Concept-TRAK: Understanding how diffusion models learn concepts through concept attributionPoster
847. Concept-based Adversarial Attack: a Probabilistic PerspectivePoster
848. Concepts' Information Bottleneck ModelsPoster
849. Condition Errors Refinement in Autoregressive Image Generation with Diffusion LossPoster
850. Condition Matters in Full-head 3D GANsPoster
851. Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning ModelsPoster
852. Conditional Independent Component Analysis For Estimating Causal Structure with Latent VariablesPoster
853. Conditionally Whitened Generative Models for Probabilistic Time Series ForecastingPoster
854. Conditioned Initialization for AttentionPoster
855. ConfHit: Conformal Generative Design via Nested TestingPoster
856. Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view ClusteringPoster
857. Confident and Adaptive Generative Speech Recognition via Conformal Risk ControlPoster
858. Conformal Prediction for Long-Tailed ClassificationPoster
859. Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weightingPoster
860. Conformal Robustness Control: A New Strategy for Robust DecisionOral
861. Conformalized Decision Risk AssessmentPoster
862. Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive HashingPoster
863. Conformalized Survival Counterfactuals Prediction for General Right-Censored DataPoster
864. Conjuring Semantic SimilarityPoster
865. Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision CustomizationPoster
866. ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance MaskPoster
867. Consistency Geodesic Bridge: Image Restoration with Pretrained Diffusion ModelsPoster
868. Consistency-Driven Calibration and Matching for Few-Shot Class Incremental LearningPoster
869. Consistent Low-Rank ApproximationPoster
870. Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion ModelsPoster
871. Consistent Text-to-Image Generation via Scene De-ContextualizationPoster
872. Consolidating Reinforcement Learning for Multimodal Discrete Diffusion ModelsPoster
873. Constant Degree Matrix-Driven Incomplete Multi-View Clustering via Connectivity-Structure and Embedding Tensor LearningPoster
874. Constantly Improving Image Models Need Constantly Improving BenchmarksPoster
875. Constitutional Classifiers++: Production-Grade Defenses against Universal JailbreaksPoster
876. Constrained Decoding of Diffusion LLMs with Context-Free GrammarsPoster
877. Constrained Diffusion for Protein Design with Hard Structural ConstraintsPoster
878. Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programmingPoster
879. Constraint-guided Hardware-aware NAS through Gradient ModificationPoster
880. Constructive Distortion: Improving MLLMs with Attention-Guided Image WarpingPoster
881. Contact Wasserstein Geodesics for Non-Conservative Schrödinger BridgesPoster
882. Contact-guided Real2Sim from Monocular Video with Planar Scene PrimitivesPoster
883. Contamination Detection for VLMs Using Multi‑Modal Semantic PerturbationsPoster
884. Content-Aware Mamba for Learned Image CompressionPoster
885. Context Learning for Multi-Agent DiscussionPoster
886. Context Tokens are Anchors: Understanding the Repetition Curse in Diffusion MLLMs from an Information Flow PerspectivePoster
887. Context and Diversity Matter: The Emergence of In-Context Learning in World ModelsPoster
888. Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learningPoster
889. ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour ElicitationPoster
890. ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance GenerationPoster
891. ContextIF: Enhancing Instruction-Following through Context RewardPoster
892. ContextNav: Towards Agentic Multimodal In-Context LearningPoster
893. ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time ScalingPoster
894. Contextual Causal Bayesian OptimisationPoster
895. Contextual Similarity Distillation: Ensemble Uncertainties with a Single ModelPoster
896. Contextual and Seasonal LSTMs for Time Series Anomaly DetectionPoster
897. Continual Low-Rank Adapters for LLM-based Generative Recommender SystemsPoster
898. Continual Unlearning for Text-to-Image Diffusion Models: A Regularization PerspectivePoster
899. Continuous Audio Language ModelsPoster
900. Continuous Chain of Thought Enables Parallel Exploration and ReasoningPoster
901. Continuous Space-Time Video Super-Resolution with 3D Fourier FieldsPoster
902. Continuous multinomial logistic regression for neural decodingPoster
903. Continuous-Time Value Iteration for Multi-Agent Reinforcement LearningPoster
904. Continuously Augmented Discrete Diffusion model for Categorical Generative ModelingPoster
905. Continuum Transformers Perform In-Context Learning by Operator Gradient DescentPoster
906. Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential EquationsPoster
907. Contrastive Diffusion Guidance for Spatial Inverse ProblemsPoster
908. Contrastive Predictive Coding Done Right for Mutual Information EstimationPoster
909. Control Tax: The Price of Keeping AI in CheckPoster
910. Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal ReasoningPoster
911. Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-TuningPoster
912. Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge GraphsPoster
913. Controllable Sequence Editing for Biological and Clinical TrajectoriesPoster
914. Controllable Video Generation with Provable DisentanglementPoster
915. Controllable diffusion-based generation for multi-channel biological dataPoster
916. Controlling Repetition in Protein Language ModelsPoster
917. ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement LearningPoster
918. ConvT3: Structured State Kernels for Convolutional State Space ModelsPoster
919. Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order OptimizationPoster
920. Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: from $2$ Bits to $k$ BitsPoster
921. Convergence Dynamics of Over-Parameterized Score Matching for a Single GaussianPoster
922. Convergence of Muon with Newton-SchulzPoster
923. Convergence of Regret Matching in Potential Games and Constrained OptimizationPoster
924. Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spacesPoster
925. Convergent Differential Privacy Analysis for General Federated LearningPoster
926. Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning RatePoster
927. Convex Efficient CodingPoster
928. CooperTrim: Adaptive Data Selection for Uncertainty-Aware Cooperative PerceptionPoster
929. Cooperative Sheaf Neural NetworksPoster
930. Copy-Paste to Mitigate Large Language Model HallucinationsPoster
931. Corner Gradient DescentPoster
932. Correlated Policy Optimization in Multi-Agent SubteamsPoster
933. Correlations in the Data Lead to Semantically Rich Feature Geometry Under SuperpositionPoster
934. CortiLife: A Unified Framework for Cortical Representation Learning across the LifespanPoster
935. Cortical Policy: A Dual-Stream View Transformer for Robotic ManipulationPoster
936. Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and PlanningPoster
937. Cost-Aware Dynamic Tree Construction for Efficient Large Language Model InferencePoster
938. Cost-of-Pass: An Economic Framework for Evaluating Language ModelsPoster
939. CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question AnsweringOral
940. Count Bridges enable Modeling and Deconvolving Transcriptomic DataPoster
941. Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic RewardsPoster
942. Counterfactual Explanations on Robust Perceptual GeodesicsPoster
943. Counterfactual LLM-based Framework for Measuring Rhetorical StylePoster
944. Counterfactual Reasoning for Retrieval-Augmented GenerationPoster
945. Counterfactual Structural Causal BanditsPoster
946. Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent DynamicsPoster
947. Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary LossOral
948. Covariate-Guided Clusterwise Linear Regression for Generalization to Unseen DataPoster
949. CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic DesignPoster
950. Credit-Budgeted ICPC-Style Coding: When LLM Agents Must Pay for Every DecisionPoster
951. Critical Confabulation: Can LLMs Hallucinate for Social Good?Poster
952. Critical attention scaling in long-context transformersPoster
953. Critic–Adviser–Reviser Cyclic Refinement: Towards High-Quality EMR Corpus Generation with LLMsPoster
954. Critique-Coder: Enhancing Coder Models by Critique Reinforcement LearningPoster
955. Critique-RL: Training Critiquing Language Models Through Two-Stage RL for Improved Discrimination and Constructive FeedbackPoster
956. CroCoDiLight: Repurposing Cross-View Completion Encoders for RelightingPoster
957. Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image GenerationPoster
958. Cross-Domain Lossy Compression via Rate- and Classification-Constrained Optimal TransportOral
959. Cross-Domain Policy Optimization via Bellman Consistency and Hybrid CriticsPoster
960. Cross-Embodied Co-Design for Dexterous HandsPoster
961. Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot DatasetsPoster
962. Cross-Modal Redundancy and the Geometry of Vision–Language EmbeddingsPoster
963. Cross-Timestep: 3D Diffusion Model with Trans-temporal Memory LSTM and Adaptive Priori Decoding Strategy for Medical SegmentationPoster
964. Cross-Tokenizer Likelihood Scoring Algorithms for Language Model DistillationPoster
965. CrossPL: Systematic Evaluation of Large Language Models for Cross Programming Language Interoperating Code GenerationPoster
966. CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision ModelsPoster
967. CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map RestraintsPoster
968. CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous ReconstructionPoster
969. Ctrl-World: A Controllable Generative World Model for Robot ManipulationPoster
970. CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial ObservationsPoster
971. Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment DatasetPoster
972. Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally AwarenessPoster
973. Culture in Action: Evaluating Text-to-Image Models through Social ActivitiesPoster
974. CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMsPoster
975. Curation Leaks: Membership Inference Attacks against Data Curation for Machine LearningPoster
976. Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM ReasoningPoster
977. Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical DependencePoster
978. Curvature-Guided Task Synergy for Skeleton based Temporal Action SegmentationPoster
979. Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable ApproachPoster
980. Cut Less, Fold More: Model Compression through the Lens of Projection GeometryPoster
981. Cutting the Skip: Training Residual-Free TransformersPoster
982. Cyber-Zero: Training Cybersecurity Agents without RuntimePoster
983. CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at ScaleOral
984. CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token SchedulingPoster
985. CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View SynthesisPoster
986. D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View ReconstructionPoster
987. D&R: Recovery-based AI-Generated Text Detection via a Single Black-box LLM CallPoster
988. D-AR: Diffusion via Autoregressive ModelsPoster
989. D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous GraspingPoster
990. D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AIPoster
991. DA$^{2}$: Depth Anything in Any DirectionPoster
992. DAComp: Benchmarking Data Agents across the Full Data Intelligence LifecyclePoster
993. DADA: Dual Averaging with Distance AdaptationPoster
994. DAG-Math: Graph-Guided Mathematical Reasoning in LLMsPoster
995. DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTSPoster
996. DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data SciencePoster
997. DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM TrainingPoster
998. DAVE: A VLM Vision Encoder for Document Understanding and Web AgentsPoster
999. DCFold: Efficient Protein Structure Generation with Single Forward PassOral
1000. DEAS: DEtached value learning with Action Sequence for Scalable Offline RLPoster

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