ICML 2026 Accepted Papers

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

1. $A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program TreesPoster
2. $E^2$PO: Embedding-perturbed Exploration Preference Optimization for Flow ModelsPoster
3. $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QAPoster
4. $L^3$: Large Lookup LayersPoster
5. $R^3$DAO: Reactive Recovery and Reconstruction for Long-horizon Data Agent OrchestrationPoster
6. $V_0$: A Generalist Value Model for Any Policy at State ZeroPoster
7. $\alpha$-PFN: Fast Entropy Search via In-Context LearningPoster
8. $\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ RetrievalPoster
9. $\mathcal{O}(\log N)$ Latent Dimension Suffices for Universal Approximation of Permutation-invariant FunctionPoster
10. $\mu$pscaling small models: Principled warm starts and hyperparameter transferPoster
11. $\phi$-Balancing for Mixture-of-Experts TrainingPoster
12. $\sigma$: Sigmoid Modulation for Ultra High Resolution DiffusionPoster
13. $\tau$-Knowledge: Evaluating Conversational Agents over Unstructured KnowledgePoster
14. $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World DomainsPoster
15. $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control EnvironmentOral
16. $\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference OptimizationPoster
17. $\texttt{FlashSchNet}$: Fast and Accurate Coarse-Grained Neural Network Molecular DynamicsPoster
18. $\texttt{IDEAS}$: Interpretability Driven Evolutionary Approach for the Design of Biological SequencesPoster
19. $\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained OptimizersPoster
20. $\texttt{Multi}^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive EnvironmentsPoster
21. $\texttt{PRISM}$:A 3D Probabilistic Neural Representation for Interpretable Shape ModelingPoster
22. $\texttt{ShaplEIG}$: Bayesian Experimental Design for Shapley Value EstimationPoster
23. $\text{DT}^\text{2}$: Decision-Targeted Digital TwinsPoster
24. $f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified AnalysesPoster
25. $f$-Divergence Self-Play for Tabular Anomaly Detection via Large Language ModelsPoster
26. $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy DataPoster
27. (1D) Ordered Tokens Enable Efficient Test-Time SearchPoster
28. (Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biologically Plausible Perturbations and ML TransformationsPoster
29. (De)-regularized Maximum Mean Discrepancy Gradient FlowPoster
30. (Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential GamesSpotlight
31. (Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting ModelsPoster
32. *MemPot*: Defend Against Memory Extraction Attack with Optimized HoneypotsPoster
33. *Rank-Learner*: Orthogonal Ranking of Treatment EffectsPoster
34. 1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means QuantizationPoster
35. 3D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity TransportPoster
36. 3D Scene Assertion VerificationPoster
37. 3D-DLP: Self-supervised 3D Object-centric Scene Representation LearningPoster
38. 3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene UnderstandingPoster
39. 3DGS$^2$-TR: A Scalable Second-Order Trust-Region Method for 3D Gaussian SplattingPoster
40. 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise ClassificationPoster
41. 3DMedAgent: Unified Perception-to-Understanding for 3D Medical AnalysisPoster
42. 3DPoV: Improving 3D understanding via Patch Ordering on VideosPoster
43. 3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language ModelsOral
44. 4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware BootstrappingPoster
45. 4RC: 4D Reconstruction via Conditional Querying Anytime and AnywherePoster
46. A Bayesian Approach to Quantify the Uncertainty of Human Ratings in a Single-Instance Multimodal FrameworkPoster
47. A Behavioural and Representational Evaluation of Goal-Directedness in Language Model AgentsPoster
48. A Benchmark and Framework for Evaluating Next Action Predictions in SpreadsheetsPoster
49. A Bi-metric Framework for Efficient Nearest Neighbor SearchPoster
50. A Call to Lagrangian Action: Learning Population Mechanics from Temporal SnapshotsSpotlight
51. A Capacity-Based Rationale for Multi-Head AttentionPoster
52. A Cartesian-3j and nj Framework for Machine Learning Interatomic PotentialsPoster
53. A Close Look at Negative Label Guided Out-of-distribution Detection in Pre-trained Vision-Language ModelsPoster
54. A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial RobustnessPoster
55. A Computational Framework for Evaluating Human-likeness in LLMs' Open-ended Human BehaviorsPoster
56. A Conflict-aware Evidential Framework for Reliable Sleep Stage ClassificationPoster
57. A Consensus Anchor-guided Hypergraph Framework For Incomplete Multi-view ClusteringPoster
58. A Constrained Optimization Perspective of Unrolled TransformersSpotlight
59. A Control-Theoretic View of Mamba on Stability and RobustnessPoster
60. A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn’t)Poster
61. A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to AdaptPoster
62. A Deep Learning Model of Mental Rotation Informed by Interactive VR ExperimentsPoster
63. A Diagnostic Study of Multi-Agent LLMs for Real-World DebatesPoster
64. A Diffusive Classification Loss for Learning Energy-based Generative ModelsPoster
65. A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutionsSpotlight
66. A Direct Approach for Handling Contextual Bandits with Latent State DynamicsPoster
67. A Direct Second-Order Method for Solving Two-Player Zero-Sum GamesPoster
68. A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint PrincipleSpotlight
69. A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and ConnectivitySpotlight
70. A Fast and Soft Pattern Matcher for Trillion-Scale CorpusPoster
71. A Fine-Grained Understanding of Uniform Convergence for HalfspacesPoster
72. A Flat Vocabulary or a Rich Hierarchy? Re-introducing Intrinsic Structure Transforms the Autoregressive Image GenerationPoster
73. A Formal Comparison Between Chain of Thought and Latent ThoughtPoster
74. A Foundation-style Model for Zero-Shot Statistical Dependency MeasurementPoster
75. A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insightsPoster
76. A Framework for Understanding Learnability in TransformersPoster
77. A Fully First-Order Layer for Differentiable OptimizationSpotlight
78. A Game-Theoretic Framework for Measuring and Explaining Metric Compatibility in Fair Machine LearningPoster
79. A General Framework for Dynamic Consistent Submodular MaximizationPoster
80. A General Framework for Fair and Robust RegressionPoster
81. A General Neural Backbone for Mixed-Integer Linear Optimization via Dual AttentionPoster
82. A Generalist Pair-wise Progress Critic Model for Vision-Language-Action RobotsPoster
83. A Geometric Analysis of Small-sized Language Model HallucinationsPoster
84. A Geometric Lens on Physics-Aligned Data CompressionPoster
85. A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk MinimizationPoster
86. A Geometry-Based View of Mahalanobis OOD DetectionPoster
87. A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal GraphsPoster
88. A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal ApproximationPoster
89. A Hitchhiker's Guide to Poisson Gradient EstimationPoster
90. A Hypertoroidal Covering for Perfect Color EquivariancePoster
91. A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground TruthPoster
92. A KL-regularization framework for learning to plan with adaptive priorsPoster
93. A Kinetic-Energy Perspective of Flow MatchingSpotlight
94. A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter SearchPoster
95. A Linear Expectation Constraint for Selective Prediction and Routing with False-Discovery ControlPoster
96. A Linearly Convergent Proximal Subgradient Algorithm for Sparse Portfolio Optimization with Transaction CostPoster
97. A Machine-Learned Comorbidity IndexPoster
98. A Mechanistic Understanding of Sim-and-Real Co-Training in Generative PoliciesPoster
99. A Minimal Agent for Automated Theorem ProvingPoster
100. A Minimax Approach for Optimal Intervention Policy Learning with Two-Stage OutcomesPoster
101. A Narrowing Geometry in Contaminated ReasoningPoster
102. A New Framework for Cybersecurity Refusals in AI AgentsPoster
103. A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index ModelsSpotlight
104. A Penalty Approach For Differentiation Through Black-box Quadratic Programming SolversPoster
105. A Perturbation Approach to Unconstrained Linear BanditsPoster
106. A Positive Case for Faithfulness: Explanations Help Predict Model BehaviorPoster
107. A Probabilistic Framework for LLM-Based Model DiscoveryPoster
108. A Progressive Evidence Localization Framework Based on Wasserstein Gradient Flows for Document Visual Question AnsweringPoster
109. A Provable Expressiveness Hierarchy in Hybrid Linear-Full AttentionPoster
110. A Pure Hierarchical Spectral Parcellation Network for Brain Network AnalysisPoster
111. A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory ConstraintsPoster
112. A Random Matrix Perspective on the Consistency of Diffusion ModelsOral
113. A Random Matrix Theory of Masked Self-Supervised LearningPoster
114. A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent VariablesOral
115. A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation LearningPoster
116. A Regime-Aware Trajectory Prediction Framework for 1000+ Systems Biology ModelsPoster
117. A Regret Minimization Framework on Preference Learning in Large Language ModelsSpotlight
118. A Risk Decomposition Framework for Pre-hoc Fine-tuning PredictionPoster
119. A Robust Optimization Guided Pruning Framework for Vision and Large Language ModelsPoster
120. A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound SeparationPoster
121. A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG AlgorithmsPoster
122. A Single Layer to Explain Them All: Understanding Massive Values in Large Language ModelsPoster
123. A Sketch-and-Project Analysis of Subsampled Natural Gradient AlgorithmsPoster
124. A Solvable High-Dimensional Model Where Nonlinear Autoencoders Learn Structure Invisible to PCA While Test Loss Misaligns With GeneralizationPoster
125. A Solver-Free Training Method for Predict-then-OptimizePoster
126. A Spiking Heterogeneous Harmonic Resonate-and-Fire State Space Model for Time SeriesPoster
127. A Statistical Framework for Analyzing Specification Resistance to Learnware-Inversion RisksPoster
128. A Strictly Proper Scoring Rule and a Calibration Metric for Interval-Censored Data AnalysisPoster
129. A Stronger Benchmark for Online Bilateral Trade: From Fixed Prices to DistributionsPoster
130. A Studentized Spherical Harmonics–Based Nonparametric Two-Sample Test for Compositional and Directional DataPoster
131. A Systematic Study of Behavioral Cloning for Scientific Data AnnotationOral
132. A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep ResearchPoster
133. A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective OptimizationPoster
134. A Task-centric Theory for Iterative Self-Improvement with Easy-to-Hard CurriculaPoster
135. A Theoretical Framework for Modular Learning of Robust Generative ModelsPoster
136. A Theoretical Framework for Statistical Evaluability of Generative ModelsPoster
137. A Theoretical Game of Attacks via Compositional SkillsPoster
138. A Theory of Contrastive Learning with Natural ImagesPoster
139. A Theory of Data Acquisition and Pricing at ScalePoster
140. A Theory of How Pretraining Shapes Inductive Bias in Fine-TuningPoster
141. A Tight Theory of Error Feedback Algorithms in Distributed OptimizationPoster
142. A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow MatchingPoster
143. A Two-Layer Framework for Joint Online Configuration Selection and Admission ControlPoster
144. A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM SystemsPoster
145. A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via InteractionsPoster
146. A Unified Density Operator View of Flow Control and MergingPoster
147. A Unified Framework for Deep Hypergraph Clustering Beyond HomophilyPoster
148. A Unified Framework for Diffusion Model Unlearning with f-DivergencePoster
149. A Unified Sparse Attention via Multi-Granularity CompressionPoster
150. A Unifying Relational Perspective on Expressive Lottery TicketsSpotlight
151. A Unifying View of Variational Generative Wasserstein FlowsSpotlight
152. A Very Big Video Reasoning SuitePoster
153. A World in Pieces: Structural Certification of General AgentsPoster
154. A geometric relation of the error introduced by sampling a language model's output distribution to its internal statePoster
155. A model of errors in transformersPoster
156. A novel statistical approach to analyze image classificationPoster
157. A proximal ADMM for multiblock problems with block anti-upper triangular constraintsPoster
158. A recipe for scalable attention-based ML potentials: unlocking long-range accuracy with all-to-all node attentionPoster
159. A robust PPG foundation model using multimodal physiological supervisionPoster
160. A theory of learning data statistics in diffusion models, from easy to hardPoster
161. A unified theory of feature learning in RNNs and DNNsPoster
162. A$^2$SG: Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural NetworkPoster
163. A3: an Analytical Low-Rank Approximation Framework for AttentionPoster
164. AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video GenerationPoster
165. ABC-Bench: An Agentic Bio-Capabilities Benchmark for BiosecurityPoster
166. ABCD: All Biases Come DisguisedPoster
167. ABSINT-AI: Agentic Heap Abstractions for Abstract InterpretationPoster
168. AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM PretrainingPoster
169. ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized DomainsPoster
170. ACON: Optimizing Context Compression for Long-horizon LLM AgentsPoster
171. ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted ControlPoster
172. ACTIVE-o3 : Empowering MLLMs with Active Perception via Pure Reinforcement LearningPoster
173. AD-BTS: Adaptive Dual-Branch Token Sparsification via Spatial Information DensityPoster
174. AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured ReasoningPoster
175. ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools — From Consensus Learning to Ambiguity-Driven Emotion ReasoningSpotlight
176. ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph NetworkPoster
177. AES: Curing Optimizer Blindness in Long-Tailed Recognition via State-Aware CorrectionPoster
178. AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow MatchingPoster
179. AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-TuningPoster
180. AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMsPoster
181. AI Engram: In Search of Memory Traces in Artificial IntelligenceOral
182. AICrypto: Evaluating Cryptography Capabilities of Large Language ModelsPoster
183. AIR-VLA: Vision-Language-Action Systems for Aerial ManipulationPoster
184. AIR: Improving Agent Safety through Incident ResponsePoster
185. AIR: Post-training Data Selection for Reasoning via Attention Head InfluencePoster
186. ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian OptimizationPoster
187. ALSO: Adversarial Online Strategy Optimization for Social AgentsPoster
188. AMA-Bench: Evaluating Long-Horizon Memory for Agentic ApplicationsPoster
189. AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models TrainingPoster
190. ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language ModelsPoster
191. ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World HarmPoster
192. ANTiC: Adaptive Neural Temporal In Situ CompressorPoster
193. AOEB: Benchmarking Agent-Oriented Multimodal EmbeddingsPoster
194. AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality Missing Prompt TuningPoster
195. AOrchestra: Automating Sub-Agent Creation for Agentic OrchestrationPoster
196. APE-Bench: Evaluating Automated Proof Engineering for Formal Math LibrariesPoster
197. APEX: Approximate-but-exhaustive search for ultra-large combinatorial synthesis librariesPoster
198. API: Adaptive Prototype Imputation for Incomplete Multimodal Sentiment AnalysisPoster
199. APIC: Orthogonalized Neuro-Symbolic Modeling for Nonlinear Dissipative DynamicsPoster
200. ARC-Decode: Accelerated Decoding with Risk-Bounded AcceptancePoster
201. AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental LearningPoster
202. ARLArena: Demystifying Policy Gradient Stability in Agentic Reinforcement LearningPoster
203. AReaL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language ModelsPoster
204. ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial OptimizationPoster
205. ASIR: Steganography for Diffusion Models via Antipodal Sampling and Iterative RecoveryPoster
206. ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language ModelsPoster
207. ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer InferencePoster
208. ASyMOB: Algebraic Symbolic Mathematical Operations BenchmarkPoster
209. ATLAS: Learning to Optimally Memorize the Context at Test TimePoster
210. AURA: Visually Interpretable Affective Understanding via Robust ArchetypesPoster
211. AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video GenerationPoster
212. AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMsPoster
213. AVTrack: Audio-Visual Speaker Tracking in Complex ScenesPoster
214. Abductive Reasoning with Probabilistic CommonsensePoster
215. Absorbing Quantization Error by Deformable Noise Scheduler for Diffusion ModelsPoster
216. Abstraction Induces the Brain Alignment of Language and Speech ModelsPoster
217. Accelerated Dual Method for Distributed Optimization: An Inexact-Gradient View of Local UpdatesPoster
218. Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional OptimizationPoster
219. Accelerated and Stable Convergence with Anchored Generalized Optimistic MethodPoster
220. Accelerating Langevin Monte Carlo via Efficient Stochastic Runge-Kutta Methods beyond Log-ConcavityPoster
221. Accelerating Q-learning through Efficient Value-sharing across ActionsSpotlight
222. Accelerating Regression Tasks with Quantum AlgorithmsPoster
223. Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM ReasoningPoster
224. Accuracy and Normalized Accuracy under Length Bias: Analysis, Guidelines, and a Bayesian AlternativePoster
225. Accuracy-First Rényi Differential Privacy and Post-Processing ImmunityPoster
226. Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival AnalysisPoster
227. Accurate Large-scale Uncertainty Quantification using Stochastic Gradient Markov Chain Monte CarloPoster
228. Accurate, private, secure, federated U-statistics with higher degreePoster
229. Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov GamesPoster
230. Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-MaskPoster
231. Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language ModelsPoster
232. Action Manifold Smoothing: A Lipschitz Pathway Perspective on High-Dimensional Reinforcement LearningPoster
233. Action-Sufficient Goal RepresentationsPoster
234. Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation ExplainersOral
235. Activation with Intrinsic-Extrinsic ConsensusPoster
236. Activation-Free Backbones for Image Recognition: Polynomial Alternatives for Spatial and Channel MixingPoster
237. Active Attacks: Red-teaming LLMs via Adaptive EnvironmentsPoster
238. Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided PruningPoster
239. Active Continual Learning with Metaplastic Binary Bayesian Neural NetworksPoster
240. Active Curriculum Refinement for Reinforcement LearningPoster
241. Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language ModelsPoster
242. Active Learning with Foundation Model Priors: Efficient Learning under Class ImbalancePoster
243. Active Learning with Low-Rank Structure for Data SelectionPoster
244. Active Policy Optimization for Individualized Dosing via Gradient Variance MinimizationPoster
245. Active Reasoning Vision-Language Model via Sequential Experimental DesignPoster
246. Active Regression for Single-Index Models with Unknown Link FunctionsPoster
247. Active Tabular Augmentation via Policy-Guided Diffusion InpaintingPoster
248. Active Timepoint Selection for Learning Measure-Valued TrajectoriesPoster
249. ActiveScope: Actively Seeking and Correcting Perception for MLLMsPoster
250. ActiveUltraFeedback: Efficient Preference Data Generation using Active LearningPoster
251. AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven EditingSpotlight
252. AdaEraser: Training-Free Object Removal via Adaptive Attention SuppressionPoster
253. AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient ClippingPoster
254. AdaHC: Accelerating Multi-Token Prediction with Adaptive Head Chunking with Pipeline ParallelismPoster
255. AdaMEM: Test-Time Adaptive Memory for Language AgentsPoster
256. AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the MomentsPoster
257. AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language NavigationPoster
258. AdaRoPE: Not All Attention Heads Should Rotate and Scale EquallyPoster
259. AdaS: Adaptive Gradient Descent for Spiking TransformersPoster
260. AdaSCALE: Adaptive Scaling for OOD DetectionPoster
261. AdaSplash-2: Faster Differentiable Sparse AttentionPoster
262. AdamO: A Collapse-Suppressed Optimizer for Offline RLPoster
263. Adapting Noise to Data: Generative Flows from Learned 1D ProcessesPoster
264. Adapting to Evolving Graphs: A Scalable Framework for Dynamic CoarseningPoster
265. Adaptive Bandit Algorithms for Contextual Matching MarketsPoster
266. Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral DescentPoster
267. Adaptive Code Watermarking Through Reinforcement LearningPoster
268. Adaptive Contracts for Cost-Effective AI DelegationPoster
269. Adaptive DNA Sequence Modeling via Synergistic Plasticity UnitsPoster
270. Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman OrthogonalityPoster
271. Adaptive Generation of Bias-Eliciting Questions for LLMsPoster
272. Adaptive Group Elicitation via Multi-Turn LLM InteractionsPoster
273. Adaptive Memory Retention in Dynamic GraphsSpotlight
274. Adaptive Momentum and Nonlinear Damping for Neural Network TrainingPoster
275. Adaptive Multi-Round Allocation with Stochastic ArrivalsPoster
276. Adaptive Multiscale Binary Expansion Tests for IndependencePoster
277. Adaptive Node Feature Selection for Graph Neural NetworksPoster
278. Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean EmbeddingsPoster
279. Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy SystemsPoster
280. Adaptive Policy Backbone via Shared NetworkSpotlight
281. Adaptive Preconditioners Trigger Loss Spikes in AdamPoster
282. Adaptive Probe-based Steering for Robust LLM JailbreakingPoster
283. Adaptive Protein TokenizationPoster
284. Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned NavigationPoster
285. Adaptive Querying with AI Persona PriorsPoster
286. Adaptive Recurrent Message Passing for Test Time Computing on GraphsPoster
287. Adaptive Reinforcement Learning for Unobservable Random DelaysPoster
288. Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision-Language ModelsPoster
289. Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded SchedulerPoster
290. Adaptive Symmetry Discovery for Dynamical System IdentificationPoster
291. Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static BenchmarksSpotlight
292. Adaptive Time Series Reasoning via Segment SelectionPoster
293. Adaptive Token Refinement in Long-Tailed Large Vision-Language Models Fine-TuningPoster
294. Adaptive Utilization of Low-Rank Adaptation via Conditioned GatingPoster
295. Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy AnalysisPoster
296. Adaptive Volumetric Mechanical Property Fields Invariant to ResolutionPoster
297. Adaptively Grouped Contextual Bandits for Heterogeneous Human-AI Decision Making with Conformal Prediction SetsPoster
298. Adaptively Robust Resettable StreamingPoster
299. Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation LearningPoster
300. Addressing Semantic Blind Spots in Text-to-SQL via Component Pre-generation and AST Matching RewardsPoster
301. AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement LearningPoster
302. Advancing Analytic Class-Incremental Learning through Vision-Language CalibrationPoster
303. Advancing LLM Reasoning with Natural Language and Numerical FeedbackSpotlight
304. Advancing SVD-based LLM Compression via Layer-Wise Error Model SearchPoster
305. Advantage Collapse in Group Relative Policy Optimization: Diagnosis and MitigationPoster
306. Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion ModelsPoster
307. AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree SearchPoster
308. Adversarial Attack and Defense for Denoising Diffusion SamplingPoster
309. Adversarial Attacks and Robust Training for Hypergraph Neural NetworksPoster
310. Adversarial Flow ModelsPoster
311. Adversarial Latent Embedding Repair for LLM Continual LearningPoster
312. Adversarial Reinforcement Learning for Robust Diffusion Large Language Model UnlearningPoster
313. Adversarial Robustness of Implicit Neural Representation-Based ClassifiersPoster
314. Adversarial Training for Process Reward ModelsPoster
315. Adversarial Vulnerability from Interference Between Features in SuperpositionPoster
316. Adversarially Robust Approximate Furthest NeighborPoster
317. Adversarially Robust Control of Conditional Value-at-Risk via Kelly Conformal InferencePoster
318. AesFormer: Transform Everyday Photos into Beautiful MemoriesPoster
319. AffIn-Space: Learning Affine-Invariant Representations for 3D Spatial Understanding with MLLMsPoster
320. Affine-Equivariant Kernel Space Encoding for NeRF EditingPoster
321. Affine-Scaled Attention: Towards Flexible and Stable Transformer AttentionPoster
322. Agent JIT Compilation for Latency-Optimizing Computer-Use Agent Planning and SchedulingPoster
323. Agent Learning via Early ExperiencePoster
324. Agent Primitives: Reuseable Latent Building Blocks for Multi-Agent SystemsPoster
325. Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement LearningPoster
326. Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement LearningPoster
327. Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language ReasoningOral
328. AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code GenerationPoster
329. AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval AgentPoster
330. AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment CorruptionsPoster
331. AgentLAB: Benchmarking LLM Agents against Long-Horizon AttacksPoster
332. AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy ConditionPoster
333. AgentScore: Autoformulation of Deployable Clinical Scoring SystemsPoster
334. AgentSelect: Benchmark for Narrative Query-to-Agent RecommendationPoster
335. AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-SpeechPoster
336. AgentTailor: A Semantic-Aware LLM-Based Multi-Agent System with Actor-Critic StructurePoster
337. AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM AgentsPoster
338. AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic WebPoster
339. AgentXRay: White-Boxing Agentic Systems via Workflow ReconstructionPoster
340. Agentic Confidence CalibrationPoster
341. Agentic Framework for Epidemiological ModelingPoster
342. Agentic Model Predictive Questioning Control in Visual DesignPoster
343. Agentic Monte Carlo: Reinforcement Learning for Black-Box LLM AgentsPoster
344. Agentic Proposing: Enhancing Large language Model Reasoning via Compositional Skill SynthesisPoster
345. Aggregate Models, Not Explanations: Improving Feature Importance EstimationPoster
346. Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM AgentsPoster
347. Aitchison Embeddings for Learning Compositional Graph RepresentationsPoster
348. Alethia: a Foundational Encoder for Voice DeepfakesPoster
349. AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical AlgorithmsSpotlight
350. Algorithmic Primitives and Compositional Geometry of Reasoning in Language ModelsPoster
351. Algorithmic Recourse of In-Context Learning for Tabular DataPoster
352. AliMark: Enhancing Robustness of Sentence-Level Watermarks Against Text ParaphrasingPoster
353. AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMsPoster
354. Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate NetworksPoster
355. Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned TangentsPoster
356. AlignVid: Taming Visual Dominance via Training-Free Attention Modulation in Text-guided Image-to-Video GenerationPoster
357. AlignedNorm: Prompting Vision–Language Models via Coupled Prompt FieldPoster
358. Aligning Datasets and Models for Weight Space LearningPoster
359. Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMsPoster
360. Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignmentSpotlight
361. Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned BiasesPoster
362. Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training TrajectoriesPoster
363. Alignment-Aware DecodingPoster
364. Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion ModelsSpotlight
365. Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned KernelsSpotlight
366. All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMsPoster
367. All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear DimensionPoster
368. Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view ClusteringPoster
369. Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPOPoster
370. Allocating Variance to Maximize ExpectationPoster
371. AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompositional Verifiable RewardPoster
372. AlphaRouter: Token-level Routing Between SLM and LLM with Reinforcement Learning and Tree SearchPoster
373. Alterbute: Editing Intrinsic Attributes of Objects in ImagesPoster
374. Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-TrainingPoster
375. AmbiRefer3D: 3D Visual Grounding with Referential AmbiguityPoster
376. Ambient Dataloops: Generative Models for Dataset RefinementPoster
377. Ambiguous Strategic ClassificationPoster
378. Amodal Instance Segmentation with IRAIS Dataset for Sim-to-Real TransferPoster
379. Amortized Maximum Inner Product Search with Learned Support FunctionsPoster
380. Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior EstimationPoster
381. Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label DisambiguationPoster
382. An Algebraic View of the Expressivity of Recurrent Language ModelsPoster
383. An Approximation Algorithm for Graph Label SelectionPoster
384. An Asymmetric Latent Factorization-of-Tensors Model for Relation ExtractionPoster
385. An Efficient Joint Learning Approach for Item Response TheoryPoster
386. An Embarrasingly Simple Way to Optimize Orthogonal Matrices at ScalePoster
387. An Empirical Study of Memory Poisoning Defenses for LLM AgentsPoster
388. An Empirical Study on the Resilience of Partial Merging to Model Clone AttacksPoster
389. An Evidential Route to Asymptotic Bayes Optimality under SparsityPoster
390. An Exploration of Non-Euclidean Gradient Descent: Muon and its Many VariantsPoster
391. An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear SystemsPoster
392. An Exterior Method for Nonnegative Matrix FactorizationPoster
393. An In-Depth Study on Deep Learning Model CloningPoster
394. An Information-Theoretic Criterion for Efficient Data SynthesisPoster
395. An Interactive Paradigm for Deep ResearchPoster
396. An Odd Estimator for Shapley ValuesPoster
397. An analytic theory of convolutional neural network inverse problems solversPoster
398. AnalogVerifier: A Neuro-Symbolic Framework for Analog Circuit VerificationPoster
399. Analytic Bijections for Smooth and Interpretable Normalizing FlowsPoster
400. Anatomy of Massive Activations and Attention SinksPoster
401. Anchor-Final Self-Supervision Drives Hallucination-Aware Optimization in Large Vision-Language ModelsPoster
402. Anchor-guided Hypergraph Condensation with Dual-level DiscriminationPoster
403. Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained RectificationPoster
404. Anchoring Self-Play for Code RepairPoster
405. Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement LearningPoster
406. Annotations Mitigate Post-Training Mode CollapsePoster
407. AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly DetectionPoster
408. Anomaly-Preference Image GenerationPoster
409. Anti-Aliasing Matters: A Dynamic Network for Time Series ForecastingPoster
410. Anti-Backdoor Coreset Selection via Cumulative EntropyPoster
411. Anti-causal domain generalization: Leveraging unlabeled dataPoster
412. Antidistillation FingerprintingPoster
413. Any-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete DiffusionPoster
414. Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and ArchitectureOral
415. Any-dimensional invariant universalityPoster
416. Any2Any: Unified Arbitrary Modality Translation for Remote SensingPoster
417. Any3D-VLA: Enhancing VLA Robustness via Diverse Point CloudsPoster
418. AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral PriorsPoster
419. AnyCanvas: Potential Field Guidance for Training-Free Spatial Control in Text-to-Image DiffusionPoster
420. AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian SurprisePoster
421. AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic InferencePoster
422. Anytime Safe PAC Efficient ReasoningPoster
423. Anytime-Valid Inference Under Outcome Delay: A Design-Based ApproachPoster
424. Anytime-Valid Inference for Online Ranking of Large Language ModelsPoster
425. AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-UsePoster
426. Approximate Equivariance via Projection-Based RegularisationPoster
427. Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph ApproachPoster
428. Approximate Proportionality in Online Fair DivisionPoster
429. Approximating Drift-Diffusion Models for User Decisions under Nudging and External InformationPoster
430. Approximating f -Divergences with Rank StatisticsPoster
431. Approximation Bounds for Transformer Networks with Application to RegressionPoster
432. Approximation Error Upper and Lower Bounds for Hölder Class with TransformersPoster
433. Approximation Preserving CoresetsPoster
434. Approximation Theory for Lipschitz Continuous TransformersPoster
435. Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-TrainingPoster
436. ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM ReasoningPoster
437. Arboreal Neural NetworkPoster
438. ArcDAE: Asymmetric Rectified Contrastive Diffusion Autoencoder for Unified Representation LearningPoster
439. ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive MarginPoster
440. Architecture Matters for Multi-Agent SecurityPoster
441. Are Common Substructures Transferable? Understanding Transferability in Graph Pretraining under Riemannian GeometryPoster
442. Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value ApproachPoster
443. Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference EvaluationsPoster
444. Are Large Reasoning Models Interruptible?Poster
445. Are Object-Centric Representations Better At Compositional Generalization?Poster
446. Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM ReasoningPoster
447. Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examinationOral
448. Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?Poster
449. Are Your Agents Upward Deceivers?Poster
450. ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative RankingPoster
451. Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head PosesPoster
452. Around the World in Eighty Ratings? Quantifying the Salience of Geo-Cultural Values for Pluralistic AlignmentPoster
453. Artemis: Structured Visual Reasoning for Perception Policy LearningPoster
454. Artificial Hippocampus Networks for Efficient Long-Context ModelingPoster
455. Ask Less, See More: Communication-Conditioned Token Pruning for Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language ModelsPoster
456. Assistive Prompt Mediation: Evaluating Language Models Under Accessibility ConstraintsPoster
457. Asymmetric Contrastive Objectives for Efficient Phenotypic ScreeningPoster
458. Asymmetric Multi-View Clustering with Hyperbolic Uncertainty ModelingSpotlight
459. Asymmetric Perturbation in Solving Bilinear Saddle-Point OptimizationOral
460. Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable RewardsPoster
461. Asymmetric conformal prediction with penalized kernel sum-of-squaresPoster
462. Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential PrivacySpotlight
463. Asymptotic Theory of Iterated Empirical Risk Minimization, with Applications to Active LearningPoster
464. Asymptotic Universal Alignment: A New Alignment Framework via Test-Time ScalingPoster
465. Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical HarmonicsPoster
466. Asymptotically Optimal Sequential Testing with Markovian DataPoster
467. AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse DecodingPoster
468. At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer GeneralizationPoster
469. AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image PromptersPoster
470. AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Material StructuresPoster
471. Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial AlignmentPoster
472. Attacks on Machine-Text Detectors Retain Stylistic FingerprintsPoster
473. Attend to Anything: Foundation Model for Unified Human Attention ModelingPoster
474. Attention Hijacking: Backdooring Text Dataset Distillation via Semantic AnchorsPoster
475. Attention Illuminates LLM Reasoning: The Uncovered Preplan-and-Anchor Rhythm Enables Fine-Grained Policy OptimizationPoster
476. Attention Implements the Fisher Geometry of Exponential FamiliesPoster
477. Attention Projection Mixing with Exogenous AnchorsPoster
478. Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head CollapsePoster
479. Attention Sinks as Internal Signals for Hallucination Detection in Large Language ModelsPoster
480. Attention Sinks in Diffusion Transformers: A Causal AnalysisPoster
481. Attention with Routed-Memory for Learnable Sparse ControlPoster
482. Attention's forward pass and Frank-WolfePoster
483. Attentive Multi-Layer Fusion for Vision TransformersPoster
484. Attn-QAT: 4-Bit Attention With Quantization-Aware TrainingPoster
485. Attributed Network Alignment: Statistical Limits and Efficient AlgorithmPoster
486. Attribution-Guided and Coverage-Maximized Pruning for Structural MoE CompressionSpotlight
487. AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio ReasoningPoster
488. AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion ForcingPoster
489. AudioMosaic: Contrastive Masked Audio Representation LearningPoster
490. Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional AttributionsPoster
491. AugMask: Score-Based Generative Modeling of Incomplete Tabular Data via Augmentation and MaskingPoster
492. AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference ServingPoster
493. Auto-regressive In-context Demonstration SelectionPoster
494. AutoBaxBuilder: Bootstrapping Code Security BenchmarkingPoster
495. AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk EvaluationPoster
496. AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure DesignPoster
497. AutoMat: Physics-Guided Agentic Reasoning for Solving Ill-Posed Inverse Microscopy ProblemsPoster
498. AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous DrivingPoster
499. AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical FunctionsPoster
500. AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-TuningPoster
501. AutoRAS: Learning Robust Agentic Systems with Primitive RepresentationsPoster
502. AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from InteractionsPoster
503. AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) AgentsPoster
504. AutoTool: Dynamic Tool Selection and Integration for Agentic ReasoningPoster
505. AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit SchematicPoster
506. AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State MachinesPoster
507. Autobidding Auctions with LLM-Powered CreativesPoster
508. Automata-Conditioned Cooperative Multi-Agent Reinforcement LearningPoster
509. Automated Formal Proofs of Combinatorial Identities via Wilf–Zeilberger Guidance and LLMsSpotlight
510. Automatic Layer Selection for Hallucination DetectionPoster
511. Automatic Pruning Discovery for Large Language ModelsPoster
512. Automatic Unsupervised Ensemble Outlier Model SelectionPoster
513. Automatically Finding Reward Model BiasesPoster
514. Autoregression with Self-Token PredictionPoster
515. Autoregressive Boltzmann GeneratorsSpotlight
516. Autoregressive Direct Preference OptimizationPoster
517. Autoregressive Image Generation with Masked Bit ModelingPoster
518. Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token PredictionPoster
519. Autoregressive, Yet Revisable: In Decoding Revision for Secure Code GenerationPoster
520. AvAtar: Learning to Align via Active Optimal TransportPoster
521. Avoid What You Know: Divergent Trajectory Balance for GFlowNetsPoster
522. Awakening Visual Reasoning: Mitigating Post-Training Failure in Vision-Text CompressionPoster
523. Axiomatic Atlas: A Prescriptive Framework for Neural Architecture DesignPoster
524. A²RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark GenerationPoster
525. B-Spar: Bayesian Sparse-Reward Modeling for RL-based Image EditingPoster
526. BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector FieldsPoster
527. BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric DebatePoster
528. BAS: Bridging Adam and SignSGD for Memory-Efficient LLM TrainingPoster
529. BAT: Better Audio Transformer Guided by Convex Gated ProbingPoster
530. BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal StepsPoster
531. BEDTime: A Unified Benchmark for Automatically Describing Time SeriesPoster
532. BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic FeedbackPoster
533. BEST: Benchmarking Efficiency in Space and Time for LLM-Generated CodePoster
534. BESplit: Bias-Compensated Split Federated Learning with Evidential AggregationPoster
535. BFTS: Thompson Sampling with Bayesian Additive Regression TreesSpotlight
536. BIOARC: Discovering Optimal Neural Architectures for Biological Foundation ModelsPoster
537. BIT-LLM: Brain Instruction Tuned LLM with persistent Cross-Attention for fMRI-to-Text DecodingPoster
538. BLIPs: Bayesian Learned Interatomic PotentialsPoster
539. BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model PretrainingPoster
540. BLOCK-EM: Preventing Emergent Misalignment via Latent BlockingPoster
541. BM^2: Coupled Schrödinger Bridge MatchingPoster
542. BOCLOAK: Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot DetectionPoster
543. BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward ModelsPoster
544. BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language ModelsPoster
545. BPL: Generalizable Deepfake Detection via Bias-only Pair-aware LearningPoster
546. BRIDGE: Predicting Human Task Completion Time From Model PerformancePoster
547. BRIDGE: Triangular Fixed-Point Refinement for Long-Horizon Persona ConsistencyPoster
548. BTSP-CAM: A Brain-Inspired Geometric Memory for Class-Incremental LearningPoster
549. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained PerceptionPoster
550. BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor AttacksPoster
551. BabyVision: Visual Reasoning Beyond LanguagePoster
552. Backjump-on-Graph: Empowering LLMs with Reinforced Retrospective Exploration for Agentic KG ReasoningPoster
553. Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?Poster
554. Backward SDE–Based Diffusion for Physics-Constrained GenerationPoster
555. Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal ReasoningOral
556. Baguan-TS: dual in-context learning model for time series forecasting with covariatesPoster
557. Balanced LoRA: Removing Parameter Invariance to Accelerate ConvergencePoster
558. Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield PerspectivePoster
559. Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural NetworksPoster
560. Balancing Understanding and Generation in Discrete Diffusion ModelsSpotlight
561. Balancing plasticity and stability with Fast and Slow Successor FeaturesPoster
562. BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement LearningPoster
563. Bandit Social Leaning Dynamics with Exploration EpisodesPoster
564. Barriers to Counterfactual Credit Attribution for Autoregressive ModelsPoster
565. Base Models Know How to Reason, Thinking Models Learn WhenSpotlight
566. Batch Normalization for Neural Networks on Complex DomainsPoster
567. Batched Contextual ReinforcementPoster
568. Batched First-Order Methods for Parallel LP Solving in MIPPoster
569. Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot ClassificationPoster
570. Bayesian Gated Non-Negative Contrastive LearningPoster
571. Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal EmbeddingsPoster
572. Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model PriorsPoster
573. Bayesian Tensor Decomposition with Diffusion Model PriorPoster
574. Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurementsPoster
575. Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language ModelsPoster
576. BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model InferencePoster
577. Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement LearningPoster
578. Being More Lightweight and Practical: Mini-sized Contrastive Learning Pre-trained Models for Fine-grained Traffic TaskPoster
579. Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation SteeringPoster
580. Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor GraphsPoster
581. Benchmarking Agent Memory in Interdependent Multi-Session Agentic TasksPoster
582. Benchmarking Dense and Indiscernible Object Counting with BlueberriesPoster
583. Benchmarking LLM-Assisted Blue Teaming via Standardized Threat HuntingPoster
584. Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather ForecastingPoster
585. Benchmarking Reward Hack Detection in Code Environments via Contrastive AnalysisPoster
586. Benchmarking World-Model Learning with Environment-Level QueriesPoster
587. Benchmarking and Enhancing VLM for Compressed Image UnderstandingPoster
588. Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual GenerationPoster
589. Benchmarking at the Edge of ComprehensionOral
590. Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc TeamworkPoster
591. Benchmarking the Scientific Mind: Toward Evaluation of Complex-Reasoning Biomedical VQAPoster
592. Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image RestorationPoster
593. Benign Overfitting in Adversarial Training for Vision TransformersPoster
594. Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow MatchingPoster
595. Best-of-Both-Worlds for Heavy-Tailed Markov Decision ProcessesPoster
596. Better, Faster: Harnessing Self-Improvement in Large Reasoning ModelsPoster
597. Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent SystemsPoster
598. Betting on PredictionsPoster
599. Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic RegressionPoster
600. Beyond Accuracy: Latent Perturbations for Cognitive-Aware DiagnosisPoster
601. Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?Poster
602. Beyond Additive Decompositions: Interpretability Through SeparabilityPoster
603. Beyond Attention Imbalance: Mitigating Hallucinations via Spectral SurgeryPoster
604. Beyond Benchmarks: Toward Causally Faithful Evaluation of Large Language ModelsPoster
605. Beyond Binary: Continuous State Optimization with Graph-Structured ObjectivesPoster
606. Beyond Blind Noising: Disentangled Visual Rectification for Hallucination Mitigation in MLLMsPoster
607. Beyond Buffer Limits: Energy-Based Data Reassembly for Continual LearningPoster
608. Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language ModelsPoster
609. Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell SnapshotsPoster
610. Beyond Correctness: Distance-Based Social Dynamics of Multi-Agent DebatePoster
611. Beyond Description: Federated Adaptation via Semantic-Visual Prototype AlignmentPoster
612. Beyond Detection: A Structure-Aware Framework for Scene Text TrackingPoster
613. Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-supervised LearningPoster
614. Beyond Drift: Stabilizing Subjective LLM Evaluation with Information-Theoretic RubricsPoster
615. Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy OptimizationPoster
616. Beyond Euclidean Summaries: Online Change Point Detection for Distribution-Valued DataPoster
617. Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge GraphsPoster
618. Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier MonitoringPoster
619. Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series ForecastingPoster
620. Beyond First-order Asymptotics in Sequential Mean TestingSpotlight
621. Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality ConflictsPoster
622. Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at ScalePoster
623. Beyond Generative Priors: Minority Sampling with JEPA-Guided DiffusionPoster
624. Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor LearningSpotlight
625. Beyond Hamming: Query-Aware Decoding of Binary Cosine SketchesPoster
626. Beyond Heuristics: Learnable Density Control for 3D Gaussian SplattingPoster
627. Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View ClusteringPoster
628. Beyond Independent Genes: Learning Module-Inductive Representations for Gene Perturbation PredictionPoster
629. Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical ImagingPoster
630. Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGCPoster
631. Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability ContinuumSpotlight
632. Beyond Logits: Coherent Hallucination Mitigation via Attention Contrastive DecodingPoster
633. Beyond Logits: Metastable Latent Dynamics for Sample-Efficient Best-of-N Selection in LLMsPoster
634. Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text ClusteringPoster
635. Beyond Magnitude: Scale-Invariant Evidential Fusion for Multi-View ClassificationPoster
636. Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order InformationPoster
637. Beyond Majority Voting: Self-Reflective Test-Time Reinforcement Learning for LLM ReasoningPoster
638. Beyond Mode Collapse: Distribution Matching for Diverse ReasoningPoster
639. Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network DesignPoster
640. Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series ForecastingPoster
641. Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token InteractionsPoster
642. Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVRPoster
643. Beyond Perplexity: UTF-8 Validity in Byte-aware Language ModelsPoster
644. Beyond Pixel Context Windows: Neural World Simulators with Persistent 3D StatePoster
645. Beyond Pixels: Mining Compressed Domain Artifacts for Efficient AI-Generated Video DetectionPoster
646. Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series DistillationPoster
647. Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental LearningPoster
648. Beyond Policy Training: Recursive Solution Search from Unannotated VideosPoster
649. Beyond Prediction: Tail-Aware Scheduling for LLM InferencePoster
650. Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive ProgrammingPoster
651. Beyond Procedure: Substantive Fairness in Conformal PredictionPoster
652. Beyond Rational Illusion: Behaviorally Realistic Strategic ClassificationPoster
653. Beyond ReLU: Bifurcation, Oversmoothing, and Topological PriorsSpotlight
654. Beyond Reactivity: Proactive Adaptive Conformal Inference for Online LLM FactualityPoster
655. Beyond Rewards in RL for Cyber DefencePoster
656. Beyond Sample-Level Forgetting: Improving Reliability in Multimodal UnlearningPoster
657. Beyond Scalar Rewards: Learning from Text Feedback in LLM Post-TrainingPoster
658. Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and StabilityPoster
659. Beyond Single Embedding: Modeling User Preferences as Distribution in Federated RecommendationPoster
660. Beyond Single-View Indexing: Structure-Aware Multi-View Retrieval for Knowledge-Based VQAPoster
661. Beyond Soft Labels: Unifying Dataset Pruning and Distillation for Efficient Large-scale CompressionPoster
662. Beyond Softmax: A Natural Parameterization for Categorical Random VariablesPoster
663. Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision TransformersPoster
664. Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web ServicesPoster
665. Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQLPoster
666. Beyond Structural Symmetries: Linear Mode Connectivity via Neuron IdentifiabilityPoster
667. Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-ExpertsPoster
668. Beyond Temperature: Hyperfitting as a Late-Stage Geometric ExpansionPoster
669. Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal ControlPoster
670. Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?Poster
671. Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-SolvingSpotlight
672. Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement LearningPoster
673. Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph LearningPoster
674. Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement LearningPoster
675. Beyond Unidirectional Bias: Reciprocal Perspective Calibration in Scene Graph GenerationPoster
676. Beyond VLM-Based Rewards: Diffusion-Native Latent Reward ModelingPoster
677. Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential DiscountingPoster
678. Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented AgentsPoster
679. Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet TrainingPoster
680. Beyond the Trade-off: Unifying Fairness and Performance in Federated LearningPoster
681. Bi-Anchor Interpolation Solver for Accelerating Generative ModelingPoster
682. BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition FrameworkPoster
683. BiRQA: Bidirectional Robust Quality Assessment for ImagesPoster
684. BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel OptimizationPoster
685. BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement LearningPoster
686. Bias in Zeroth-Order Normal Estimation for Decision-Based AttacksPoster
687. Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE ConstraintsPoster
688. Biased Generalization in Diffusion ModelsSpotlight
689. Biases in the Blind Spot: Detecting What LLMs Fail to MentionPoster
690. Bilevel Optimization over Saddle Points of Zero-Sum Markov GamesPoster
691. Bilinear Bandits with Partially Observable FeaturesPoster
692. Bimodal masked language modeling for bulk RNA-seq and DNA methylation representation learningPoster
693. Bio-Inspired Self-Supervised Learning for Wrist-worn IMU SignalsPoster
694. Bio-Vision-Inspired Spiking Neural Networks for Object Detection with Event CamerasPoster
695. BioAgent Bench: An AI Agent Evaluation Suite for BioinformaticsPoster
696. BioDynaSpec: Harmonic-Guided Spatio-Spectral Autoregressive Diffusion for Protein Dynamics GenerationPoster
697. BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-SeriesPoster
698. BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation ModelsPoster
699. Bioacoustic Geolocation: Species Sounds as Geographic SignalsPoster
700. Biologically plausible heavy-tailed connectivity enhances generalizations on cognitive tasks in recurrent neural networksPoster
701. Bipartite Graph Attention-based Clustering for Large-scale scRNA-seq DataPoster
702. Bits That Count: Quantifying and Predicting Capabilities of Language ModelsPoster
703. BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual EvaluationPoster
704. Black-Box Assisted Regression: Phase Transitions and Minimax OptimalityPoster
705. Black-Box Combinatorial Optimization with Order-Invariant Reinforcement LearningPoster
706. Black-Box Detection of LLM-Generated Text Using Generalized Jensen Shannon DivergencePoster
707. Blending Neural Control Density Functions for Stabilization and SafetyPoster
708. Blending Supervised and Reinforcement Fine-Tuning with Prefix SamplingPoster
709. Block Rotation is All You Need for MXFP4 QuantizationPoster
710. Block-wise Codeword Embedding for Reliable Multi-bit Text WatermarkingPoster
711. Blocking the Leakage: Manifold-Aware Gradient Projection for Long-Horizon Test-Time AdaptationPoster
712. BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AIPoster
713. Boost the Identity-Preserving Embedding for Consistent Visual GenerationPoster
714. Boosting CVaR Policy Optimization with Quantile GradientsPoster
715. Boosting Monocular Metric Depth Estimation via Bokeh RenderingPoster
716. Boosting Video Diffusion Models via Masked Autoencoders as TokenizersPoster
717. Boosting World Models Learning via Latent-Space Value AlignmentPoster
718. Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting AgentPoster
719. Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and EditingPoster
720. Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized LearningPoster
721. Bottleneck-Guided Spectral Subgoals For Offline Goal-Conditioned RLPoster
722. Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural DisentanglementPoster
723. Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language ModelsPoster
724. Box Thirding: Anytime Best Arm Identification under Insufficient SamplingPoster
725. BrainJanus: A Foundation Model for Unified Understanding and Generation across Brain, Vision, and LanguagePoster
726. Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNetsPoster
727. Branching Diffusion for Point Processes in Time and SpacePoster
728. Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement LearningPoster
729. Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual ReasonersPoster
730. Breaking Manifold Continuity: Vector Quantized Modeling for Real-Centric Deepfake DetectionPoster
731. Breaking Multi-Task Curse: Reward-Weighted Evolution for Black-Box Many-Task OptimizationPoster
732. Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct ModelsPoster
733. Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model RestorationPoster
734. Breaking the Computational Barrier: Provably Efficient Actor–Critic for Low-Rank MDPsPoster
735. Breaking the Echo Chamber: A Dynamic Ensemble Pruning Perspective on MoEPoster
736. Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM ReasoningPoster
737. Breaking the Factorization Barrier in Diffusion Language ModelsPoster
738. Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation ModulationPoster
739. Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference PassagesPoster
740. Breaking the Reversal Curse in Autoregressive Language Models via Identity BridgeSpotlight
741. Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency TransformPoster
742. Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RLPoster
743. Breaking the Simplification Bottleneck in Amortized Neural Symbolic RegressionPoster
744. Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental LearningPoster
745. Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete TimePoster
746. Brep2Shape: Boundary and Shape Representation Alignment via Self-supervised TransformersPoster
747. Bridging Dynamics and Data: A Unified Diffusion Framework for Mechanistically-Informed Epidemic ForecastingPoster
748. Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code TranslationPoster
749. Bridging Functional and Representational Similarity via Usable InformationPoster
750. Bridging Local–Global Dissonance: Learning from Compressive Measurements for Hyperspectral ReconstructionPoster
751. Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-TrainingPoster
752. Bridging RGB and RAW: Single-step Deterministic Flow with Homogeneous Aligned GuidancePoster
753. Bridging Scaling Laws to On-Policy Reinforcement Learning via Adaptive Batch ScalingPoster
754. Bridging Spherical Black-Box OptimizersPoster
755. Bridging Structure and Semantics: Uncertainty-Modulated Dual-Path Diffusion for Robust Text-Attributed Graph LearningPoster
756. Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series ForecastingPoster
757. Bridging Tokens and Geometry: Token-wise 3D Supervision for CAD GenerationPoster
758. Bridging Your Imagination with Audio-Video Generation via a Unified DirectorPoster
759. Bridging the Gap Between Average and Discounted TD LearningPoster
760. Bridging the Gap in Autonomous Science: The Corpus and Benchmark for Biological Protocol ReasoningPoster
761. Bridging the Grounding Gap in VideoQA via Typed Memory for Language-based Belief-State ReasoningPoster
762. Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice QuestionsPoster
763. Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQAPoster
764. Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language ModelsPoster
765. Bring Future Vision: Dynamic Computation Allocation Guided by Lightweight Feature ForecasterPoster
766. Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive PromptingPoster
767. Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at ScalePoster
768. BroRL: Scaling Reinforcement Learning via Broadened ExplorationPoster
769. Broadening the Backdoor Basin: Understanding LLM Backdoors Collapse and Making Backdoors PersistentPoster
770. BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMsSpotlight
771. BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement LearningPoster
772. Budget-Constrained Step-Leve Diffusion CachingPoster
773. Budget-Efficient Attacks and Robustness Training for Cooperative MARLPoster
774. Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement AuctionsPoster
775. Budgeted Active Experimentation for Treatment Effect Estimation from Observational and Randomized DataPoster
776. BuildArena: A Physics‑Aligned Interactive Benchmark of LLMs for Engineering ConstructionPoster
777. Building Better Deception Probes Using Targeted Instruction PairsPoster
778. Building Reliable Long-Form Generation via Hallucination Rejection SamplingPoster
779. Building Social World Model with Large Language ModelsPoster
780. Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample ContaminationSpotlight
781. Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural NetworksPoster
782. Butterworth as Attention: Anisotropic Spectral Gating for PansharpeningPoster
783. Byte Pair Encoding for Efficient Time Series ForecastingPoster
784. C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse AutoencodersPoster
785. CACR: Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal ReasoningPoster
786. CADFit: Precise Mesh-to-CAD Program Generation with Hybrid OptimizationPoster
787. CALM Before the STORM: Unlocking Native Reasoning for Optimization ModelingPoster
788. CAMEL: Confidence-Gated Reflection for Reward ModelingPoster
789. CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary LearningPoster
790. CANDI: Hybrid Discrete-Continuous Diffusion ModelsPoster
791. CAOS: Conformal Aggregation of One-Shot PredictorsPoster
792. CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective TrainingPoster
793. CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy EstimationPoster
794. CARE: Adaptive Calibration for Reliable RecommendationsPoster
795. CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy LabelsPoster
796. CARE: Confounder-Aware Aggregation for Reliable LLM EvaluationPoster
797. CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data OptimizationPoster
798. CAST: Modeling Visual State Transitions for Consistent Video RetrievalPoster
799. CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMsOral
800. CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative TournamentsPoster
801. CAffNet: Hard Constraint-Affine Neural NetworksPoster
802. CB-SLICE: Concept-Based Interpretable Error Slice DiscoveryPoster
803. CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion ModelsPoster
804. CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph RecommendationPoster
805. CE$^4$L: Continual Ego, Exo, and Ego-Exo LearningPoster
806. CELL: A Causal Perspective for Fairness-aware Graph AdaptationPoster
807. CFPO : Counterfactual Policy Optimization For Multimodal ReasoningPoster
808. CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language ModelsPoster
809. CGRiC: Compositional Risk Certification for Structured LLM OutputsPoster
810. CGSVD: Cascaded Granular Singular Value Decomposition for Large Language Model CompressionPoster
811. CHB: A Diagnostic Toolkit for Hardness-Aware Clustering EvaluationPoster
812. CHESS: Chebyshev Spectral Synthesis for Trajectory CondensationPoster
813. CIRBench: Evaluating Large Language Models as LLVM IR OptimizersSpotlight
814. CL-GCL: Comprehensive and Lightweight Graph Contrastive LearningPoster
815. CLAA: Cross-Layer Attention Aggregation for Accelerating LLM PrefillPoster
816. CLAM-Bench: Benchmarking LLM Agents for Library-Scale Cross-Architecture MigrationPoster
817. CLARITree: Cholesky and Lookahead Accelerations for Regression with Interpretable Piecewise Linear TreesPoster
818. CLASP: Online learning algorithms for Convex Losses And Squared PenaltiesPoster
819. CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Subtitle RemovalOral
820. CLIMB: Taming the LoRA Residency Cliff in Multi-LoRA ServingPoster
821. CLINIC : Evaluating Multilingual Trustworthiness in Language Models for HealthcarePoster
822. CLINIC: Towards High-quality Graph Out-Of-Distribution DetectionPoster
823. CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language ModelsPoster
824. CLoVE: Personalized Federated Learning through Clustering of Loss Vector EmbeddingsPoster
825. CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal InstructionPoster
826. COBRA: Contribution-Based Bayesian Rank Allocation for Parameter-Efficient Fine-TuningPoster
827. CODiff: One-Step Diffusion Model for Camouflaged Object DetectionPoster
828. COFT: Counterfactual–Conformal Decoding for Fair Chain‑of‑Thought Reasoning in Large Language ModelsPoster
829. COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and SmoothingPoster
830. COLLIE: Guiding Skill Discovery in Semantically Coherent Latent SpacePoster
831. CONGA:Confidence-and-Gradient-Aware Learning Rate Schedule for Test Time AdaptationPoster
832. CONTEXTOR: Contextualized High-order Contrastive LearningPoster
833. CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware VirtualizationSpotlight
834. COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving GraphsPoster
835. CORAL: Uncertainty-Aware Regulation of Exposure Concentration in Recommender SystemsPoster
836. CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal RepresentationsPoster
837. CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation DetectionPoster
838. CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systemsPoster
839. CPMöbius: Iterative Coach–Player Reasoning for Data-Free Reinforcement LearningPoster
840. CRAG: Can 3D Generative Models Help 3D Assembly?Poster
841. CRAMER: Control via Request-Aware Masking for Editing RecommendersPoster
842. CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction AttacksPoster
843. CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing AgentsPoster
844. CSD: Content-aware Speculative Decoding for Efficient Image GenerationPoster
845. CSG: Cognitive Structure Generation for Intelligent EducationPoster
846. CSOR: Coreset Selection for Object Re-identification via Class PruningPoster
847. CSPLoRA: Confidence-Guided Structure Planning for Low-Rank AdaptationPoster
848. CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement LearningSpotlight
849. CUARewardBench: Benchmark for Evaluating Reward Models on Computer-using Agent TrajectoriesPoster
850. CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLMPoster
851. CURE: Consistency-under-Unified Semantic Regularization for Generalized Category DiscoveryPoster
852. CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series ClassificationPoster
853. CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided RegularizationPoster
854. CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security VulnerabilityOral
855. CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image PerceptionPoster
856. CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot ManipulationPoster
857. Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte CarloPoster
858. CacheEdit: Efficient Multi-round Image Editing via Adaptive Token-wise Reuse.Poster
859. CalPro: Prior-Aware Evidential Conformal Prediction with Structure-Aware Sensitivity Bounds for Protein StructuresPoster
860. CaliDist: Calibrating Large Language Models via Behavioral Robustness to DistractionPoster
861. Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQAPoster
862. Calibrated Multimodal Representation Learning with Missing ModalitiesPoster
863. Calibrated Preference Learning: The Case of Label RankingPoster
864. Calibrated Test-Time Guidance for Bayesian InferencePoster
865. Calibrating Conservatism for Scalable OversightPoster
866. Calibrating Decision Robustness via Inverse Conformal Risk ControlPoster
867. Calibrating Generative Models to Distributional ConstraintsPoster
868. Calibrating Uncertainty for Zero-Shot Adversarial CLIPPoster
869. CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry PriorsPoster
870. Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGradPoster
871. Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool UsePoster
872. Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?Poster
873. Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language ModelsPoster
874. Can LLM Agents Stick to the Script? Modeling Commitment in Interactive NarrativesPoster
875. Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of ThoughtPoster
876. Can LLMs Reason Structurally? Benchmarking via the lens of Data StructuresPoster
877. Can Large Language Models Generalize Procedures Across Representations?Poster
878. Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?Poster
879. Can Muon Fine-tune Adam-Pretrained Models?Poster
880. Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity ControlPoster
881. Can Simple Denoising Improve Uniform State Diffusion Models?Poster
882. Can VLMs Diagnose and Recover from VLA Manipulation Faults?Poster
883. Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space ReconstructionPoster
884. Can local learning match self-supervised backpropagation?Poster
885. Can vision language models learn intuitive physics from interaction?Poster
886. Capability-Oriented Training Induced Alignment RiskPoster
887. Capacitated Fair-Range Clustering: Hardness and Approximation AlgorithmsPoster
888. Capacity without Access: Reinterpreting the Mid-Depth Spectral Plateau in LLMsPoster
889. Capacity-Agnostic Parameter Isolation for Continual Graph LearningPoster
890. Capacity-Aware Mixture Law Enables Efficient LLM Data OptimizationPoster
891. Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination MitigationPoster
892. Caracal: Causal Architecture via Spectral MixingPoster
893. Cardinality-Invariant Neural Operator Policies for Scalable PDE ControlPoster
894. Cardio-mmFlow: A Gaussian-Prior-Free Physics-Informed Flow Matching Framework for Electrocardiogram to mmWave Radar Synthesis.Poster
895. Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type FeaturesPoster
896. CatFlow: Co-generation of Slab-Adsorbate Systems via Flow MatchingPoster
897. Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM WatermarkingSpotlight
898. Categorical Flow MapsPoster
899. Categorical Reparameterization with Denoising Diffusion modelsPoster
900. CauScale: Neural Causal Discovery at ScalePoster
901. CauSciBench: Evaluating LLM Causal Inference for Scientific ResearchPoster
902. CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation FunctionsPoster
903. Causal Attention with Lookahead KeysPoster
904. Causal Dependency-Aware Unsupervised Routing for Large Reasoning ModelsPoster
905. Causal Detection of Multi-Step LLM Agent AttacksPoster
906. Causal Direct Preference Optimization for Distributionally Robust Generative RecommendationPoster
907. Causal Discovery for Irregularly Time Series with Consistency GuaranteesPoster
908. Causal Disentangled Anchor Learning for Scalable Fair Multi-view ClusteringPoster
909. Causal Effect Identifiability in the Presence of Latent Confounders Without Auxiliary VariablesPoster
910. Causal Feature Learning via Generalized Rayleigh QuotientsPoster
911. Causal Fine-Tuning under Latent Confounded ShiftPoster
912. Causal Flow Q-Learning for Robust Offline Reinforcement LearningPoster
913. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Video GenerationPoster
914. Causal Identification from Counterfactual Data: Completeness and Bounding ResultsPoster
915. Causal Matrix Completion under Multiple Treatments via Mixed Synthetic Nearest NeighborsPoster
916. Causal Modeling of Selection in EvolutionSpotlight
917. Causal Preference ElicitationPoster
918. Causal Representation Learning with Optimal Compression and Complex TreatmentsPoster
919. Causal Structure Learning for Sparse Matrix Fill-in ReductionPoster
920. Causal discovery for time series with endogenous context variablesPoster
921. Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual GenerationPoster
922. Causal-EPIG: Causally Aligned Active CATE EstimationPoster
923. Causal-JEPA: Learning World Models through Object-Level Latent InterventionsPoster
924. Causal-aware Anomaly Detection for Tabular DataPoster
925. CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal AttributionPoster
926. CausalGame: Benchmarking Causal Thinking of LLM Agents in GamesOral
927. CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine LearningPoster
928. CausalX: A Unified and Causally-Interpretable Plug-and-Play Model for Multi-modal Spatio-Temporal ForecastingPoster
929. CausalXRL: Explainable Reinforcement Learning through Causal Graph ReasoningPoster
930. Causally Evaluating the Learnability of Formal Language TasksPoster
931. CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative PerceptionPoster
932. Causes and Consequences of Representational Similarity in Machine Learning ModelsPoster
933. CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware AlignmentPoster
934. Cello: A Universal Cell-wise Feature Aggregation framework for Reliable Pathology Images AnalysisPoster
935. Censoring with Plausible Deniability: Asymmetric Local Privacy for Multi-Category CDF EstimationPoster
936. CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic CodingPoster
937. Cerebellar-Inspired Residual Control for Fault Recovery: From Inference-Time Adaptation to Structural ConsolidationPoster
938. Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive SmoothingPoster
939. Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoEPoster
940. Certificate-Guided Pruning for Stochastic Lipschitz OptimizationPoster
941. Certificates for Complex-Compatible Learned Cochain LaplaciansPoster
942. Certified Circuits: Stability Guarantees for Mechanistic CircuitsPoster
943. Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized SmoothingPoster
944. Certifying Capabilities from Finite Tests: When Is It Possible?Spotlight
945. Certifying Graph Neural Networks Against Label and Structure PoisoningPoster
946. Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video UnderstandingPoster
947. Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RLPoster
948. Chain-of-Thought Gradient DescentPoster
949. Chain-of-Thought Reasoning In The Wild Is Not Always FaithfulPoster
950. Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed SamplingSpotlight
951. Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate ForecastingPoster
952. ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale AwarenessPoster
953. Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk MinimizationPoster
954. Characterizing Agents in ProductionOral
955. Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot DeploymentPoster
956. Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable ModelingPoster
957. Characterizing, Evaluating, and Optimizing Complex ReasoningOral
958. ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart EditingPoster
959. Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language ModelsPoster
960. Cheap2Rich: A Multi-Fidelity Framework for Data Assimilation and System Identification of Multiscale Physics - Rotating Detonation EnginesPoster
961. Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-dimensional Control TasksOral
962. Chiral Symmetry Breaking in Transformers: A Group-Equivariant Framework for Solving the Reversal Curse via Adjoint Manifold MappingsPoster
963. Chunk-Guided Q-LearningPoster
964. Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language ModelsPoster
965. CircuitPrint: Mechanistic Circuit Fingerprints for Large Language ModelsPoster
966. CiteGuard: Conformal False-Discovery Control for Faithful Retrieval-Augmented GenerationPoster
967. Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD GenerationPoster
968. Class-Conditional Distribution Balancing for Group Robust ClassificationPoster
969. Class-Grouped-Normalized-Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated LearningPoster
970. Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label LearningPoster
971. ClimateAR: Multi-Scale Autoregressive Generative Modeling for Seasonal-to-Interannual Climate ForecastingPoster
972. ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic EducationSpotlight
973. Clipped Q-Learning: Your Value Clipping Is Secretly A Robust OperatorPoster
974. Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary SignalsPoster
975. Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RLPoster
976. Clipping Makes Distributed and Federated Asynchronous SGD Robust to StragglersPoster
977. Closing the Expression Gap in LLM Instructions via Socratic QuestioningPoster
978. Closing the Loop: Universal Repository Representation with RPG-EncoderPoster
979. Closing the Sim-to-Real Gap in Non-Markovian Spreading Processes via GPU-Accelerated Distributional RLPoster
980. Clover: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient EstimationPoster
981. Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time SeriesPoster
982. Clustered Influence FunctionsPoster
983. Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph LearningPoster
984. Clustering in Deep Stochastic TransformersSpotlight
985. Co-Evolving Latent Action World ModelsPoster
986. Co-Generative De Novo Functional Protein DesignPoster
987. Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM AgentsPoster
988. CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement LearningPoster
989. CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation SteeringPoster
990. CoCoQuant: Breaking the Bandwidth Wall via Co-Optimized Communication and Computation QuantizationPoster
991. CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI ReviewersPoster
992. CoDA-Bench: Can Code Agents Handle Data-Intensive Tasks?Poster
993. CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator TransformerOral
994. CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image GenerationPoster
995. CoFrGeNet: Continued Fraction Architectures for Language GenerationPoster
996. CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series ForecastingPoster
997. CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly DetectionPoster
998. CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous DrivingPoster
999. CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream TasksPoster
1000. CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities ReasoningPoster

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