ICLR 2025 Accepted Papers

The full list of 3,704 papers accepted at ICLR 2025 (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.

1001. Indirect Gradient Matching for Adversarial Robust DistillationPoster3 citations
1002. InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight GenerationPoster3 citations
1003. Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User InterfacePoster3 citations
1004. Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical TasksPoster3 citations
1005. Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational PathologyPoster3 citations
1006. Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representationsPoster3 citations
1007. Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-FaithfulnessPoster3 citations
1008. Jamba: Hybrid Transformer-Mamba Language ModelsPoster3 citations
1009. Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion ModelsPoster3 citations
1010. KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning TasksPoster3 citations
1011. Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language ModelsPoster3 citations
1012. LDAdam: Adaptive Optimization from Low-Dimensional Gradient StatisticsPoster3 citations
1013. Language Model Alignment in Multilingual Trolley ProblemsSpotlight3 citations
1014. Large Convolutional Model Tuning via Filter SubspacePoster3 citations
1015. Latent Space Chain-of-Embedding Enables Output-free LLM Self-EvaluationPoster3 citations
1016. Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language ModelsSpotlight3 citations
1017. Learning General-purpose Biomedical Volume Representations using Randomized SynthesisPoster3 citations
1018. Learning Multi-Index Models with Neural Networks via Mean-Field Langevin DynamicsPoster3 citations
1019. Lightweight Neural App ControlSpotlight3 citations
1020. Lightweight Predictive 3D Gaussian SplatsPoster3 citations
1021. Limits of Deep Learning: Sequence Modeling through the Lens of Complexity TheoryPoster3 citations
1022. LoCoDL: Communication-Efficient Distributed Learning with Local Training and CompressionSpotlight3 citations
1023. Logical Consistency of Large Language Models in Fact-CheckingPoster3 citations
1024. Long-Sequence Recommendation Models Need Decoupled EmbeddingsPoster3 citations
1025. Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNetsPoster3 citations
1026. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference OptimizationPoster3 citations
1027. MAP: Multi-Human-Value Alignment PaletteOral3 citations
1028. MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound GenerationPoster3 citations
1029. MELODI: Exploring Memory Compression for Long ContextsPoster3 citations
1030. MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map ConstructionPoster3 citations
1031. MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language ModelsPoster3 citations
1032. MMTEB: Massive Multilingual Text Embedding BenchmarkPoster3 citations
1033. MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object DetectionOral3 citations
1034. Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model AlignmentPoster3 citations
1035. MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation MethodsPoster3 citations
1036. MarS: a Financial Market Simulation Engine Powered by Generative Foundation ModelPoster3 citations
1037. MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex ProofsPoster3 citations
1038. MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal ProjectionPoster3 citations
1039. MiniPLM: Knowledge Distillation for Pre-training Language ModelsPoster3 citations
1040. Mitigating Memorization in Language ModelsSpotlight3 citations
1041. Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware SubspacePoster3 citations
1042. Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LNPoster3 citations
1043. MixEval-X: Any-to-any Evaluations from Real-world Data MixtureSpotlight3 citations
1044. Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language ModelsPoster3 citations
1045. Mixture of Parrots: Experts improve memorization more than reasoningPoster3 citations
1046. Model-agnostic meta-learners for estimating heterogeneous treatment effects over timePoster3 citations
1047. Multi-Field Adaptive RetrievalSpotlight3 citations
1048. Multimodality Helps Few-shot 3D Point Cloud Semantic SegmentationSpotlight3 citations
1049. NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule GenerationPoster3 citations
1050. NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for RetrievalPoster3 citations
1051. Natural Language Inference Improves Compositionality in Vision-Language ModelsPoster3 citations
1052. Near-Exact Privacy Amplification for Matrix MechanismsPoster3 citations
1053. No Preference Left Behind: Group Distributional Preference OptimizationPoster3 citations
1054. Number Cookbook: Number Understanding of Language Models and How to Improve ItPoster3 citations
1055. On the Benefits of Memory for Modeling Time-Dependent PDEsOral3 citations
1056. On the Byzantine-Resilience of Distillation-Based Federated LearningPoster3 citations
1057. On the Optimization and Generalization of Two-layer Transformers with Sign Gradient DescentSpotlight3 citations
1058. Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance SegmentationOral3 citations
1059. OpenPRM: Building Open-domain Process-based Reward Models with Preference TreesPoster3 citations
1060. Optimal Protocols for Continual Learning via Statistical Physics and Control TheoryPoster3 citations
1061. Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM InferencePoster3 citations
1062. Optimizing Posterior Samples for Bayesian Optimization via RootfindingPoster3 citations
1063. Oscillatory State-Space ModelsOral3 citations
1064. PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass EstimationPoster3 citations
1065. PaPaGei: Open Foundation Models for Optical Physiological SignalsPoster3 citations
1066. ParetoFlow: Guided Flows in Multi-Objective OptimizationPoster3 citations
1067. Perm: A Parametric Representation for Multi-Style 3D Hair ModelingSpotlight3 citations
1068. Persistent Pre-training Poisoning of LLMsPoster3 citations
1069. Personality Alignment of Large Language ModelsPoster3 citations
1070. PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in BenchmarksPoster3 citations
1071. PiCO: Peer Review in LLMs based on Consistency OptimizationPoster3 citations
1072. Population Transformer: Learning Population-level Representations of Neural ActivityOral3 citations
1073. PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness ModelingPoster3 citations
1074. Proactive Agent: Shifting LLM Agents from Reactive Responses to Active AssistancePoster3 citations
1075. Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model UtilityPoster3 citations
1076. Probabilistic Language-Image Pre-TrainingPoster3 citations
1077. Probing the Latent Hierarchical Structure of Data via Diffusion ModelsPoster3 citations
1078. Provable Convergence and Limitations of Geometric Tempering for Langevin DynamicsPoster3 citations
1079. Provably Robust Explainable Graph Neural Networks against Graph Perturbation AttacksPoster3 citations
1080. Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot TransferPoster3 citations
1081. REMEDY: Recipe Merging Dynamics in Large Vision-Language ModelsPoster3 citations
1082. ReMoE: Fully Differentiable Mixture-of-Experts with ReLU RoutingPoster3 citations
1083. Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community RetrievalPoster3 citations
1084. RecDreamer: Consistent Text-to-3D Generation via Uniform Score DistillationPoster3 citations
1085. Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted PhenomenonPoster3 citations
1086. RefactorBench: Evaluating Stateful Reasoning in Language Agents Through CodePoster3 citations
1087. Restructuring Vector Quantization with the Rotation TrickOral3 citations
1088. Rethinking Invariance in In-context LearningPoster3 citations
1089. Rethinking Reward Modeling in Preference-based Large Language Model AlignmentOral3 citations
1090. Robotouille: An Asynchronous Planning Benchmark for LLM AgentsPoster3 citations
1091. Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot DatasetsPoster3 citations
1092. Robustness Reprogramming for Representation LearningSpotlight3 citations
1093. SELF-EVOLVED REWARD LEARNING FOR LLMSPoster3 citations
1094. STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor ScenesPoster3 citations
1095. SaLoRA: Safety-Alignment Preserved Low-Rank AdaptationPoster3 citations
1096. Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy VideoPoster3 citations
1097. Scaling Autonomous Agents via Automatic Reward Modeling And PlanningPoster3 citations
1098. Scaling Diffusion Language Models via Adaptation from Autoregressive ModelsPoster3 citations
1099. Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model PretrainingPoster3 citations
1100. Second Order Bounds for Contextual Bandits with Function ApproximationPoster3 citations
1101. Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D ScenesPoster3 citations
1102. Solving Video Inverse Problems Using Image Diffusion ModelsPoster3 citations
1103. Sort-free Gaussian Splatting via Weighted Sum RenderingPoster3 citations
1104. Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical PerformancePoster3 citations
1105. Structure Language Models for Protein Conformation GenerationPoster3 citations
1106. TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning BenchmarksSpotlight3 citations
1107. Task-Adaptive Pretrained Language Models via Clustered-Importance SamplingPoster3 citations
1108. Text2PDE: Latent Diffusion Models for Accessible Physics SimulationPoster3 citations
1109. The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noisePoster3 citations
1110. The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGDPoster3 citations
1111. The Pitfalls of Memorization: When Memorization Hurts GeneralizationPoster3 citations
1112. Think while You Generate: Discrete Diffusion with Planned DenoisingPoster3 citations
1113. TopoDiffusionNet: A Topology-aware Diffusion ModelPoster3 citations
1114. Towards Understanding the Universality of Transformers for Next-Token PredictionPoster3 citations
1115. Towards Universality: Studying Mechanistic Similarity Across Language Model ArchitecturesPoster3 citations
1116. Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck PerspectivePoster3 citations
1117. Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-ContextPoster3 citations
1118. Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization AnalysisPoster3 citations
1119. Training-Free Diffusion Model Alignment with Sampling DemonsPoster3 citations
1120. Understanding Long Videos with Multimodal Language ModelsPoster3 citations
1121. Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic SamplersPoster3 citations
1122. Unified Parameter-Efficient Unlearning for LLMsPoster3 citations
1123. Unlocking the Potential of Model Calibration in Federated LearningPoster3 citations
1124. Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMsPoster3 citations
1125. VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot ManipulationPoster3 citations
1126. Valid Conformal Prediction for Dynamic GNNsPoster3 citations
1127. Verifying Properties of Binary Neural Networks Using Sparse Polynomial OptimizationPoster3 citations
1128. VibeCheck: Discover and Quantify Qualitative Differences in Large Language ModelsPoster3 citations
1129. VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web TasksPoster3 citations
1130. VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot PlanningSpotlight3 citations
1131. Watermark Anything With Localized MessagesPoster3 citations
1132. Weak-to-Strong Generalization Through the Data-Centric LensPoster3 citations
1133. Weighted-Reward Preference Optimization for Implicit Model FusionPoster3 citations
1134. What Are Good Positional Encodings for Directed Graphs?Poster3 citations
1135. What Makes a Good Diffusion Planner for Decision Making?Spotlight3 citations
1136. What Matters in Learning from Large-Scale Datasets for Robot ManipulationPoster3 citations
1137. XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement LearningPoster3 citations
1138. Your Weak LLM is Secretly a Strong Teacher for AlignmentPoster3 citations
1139. A Coefficient Makes SVRG EffectivePoster2 citations
1140. A Probabilistic Perspective on Unlearning and Alignment for Large Language ModelsOral2 citations
1141. A Watermark for Order-Agnostic Language ModelsPoster2 citations
1142. A-Bench: Are LMMs Masters at Evaluating AI-generated Images?Poster2 citations
1143. AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web TextOral2 citations
1144. API Pack: A Massive Multi-Programming Language Dataset for API Call GenerationPoster2 citations
1145. Accessing Vision Foundation Models via ImageNet-1KPoster2 citations
1146. ActionReasoningBench: Reasoning about Actions with and without Ramification ConstraintsPoster2 citations
1147. Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?Poster2 citations
1148. Adaptive Length Image Tokenization via Recurrent AllocationPoster2 citations
1149. Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of NoisePoster2 citations
1150. AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language ModelsPoster2 citations
1151. Adversarial Machine UnlearningPoster2 citations
1152. Agent Skill Acquisition for Large Language Models via CycleQDPoster2 citations
1153. Aligned Better, Listen Better for Audio-Visual Large Language ModelsPoster2 citations
1154. Aligning Language Models with Demonstrated FeedbackPoster2 citations
1155. Aligning Visual Contrastive learning models via Preference OptimizationPoster2 citations
1156. An Evolved Universal Transformer MemoryPoster2 citations
1157. Analytic DAG Constraints for Differentiable DAG LearningPoster2 citations
1158. Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement LearningPoster2 citations
1159. AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile SensorsPoster2 citations
1160. Are Large Vision Language Models Good Game Players?Poster2 citations
1161. As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback LossPoster2 citations
1162. B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught ReasonersPoster2 citations
1163. BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural DynamicsPoster2 citations
1164. BadJudge: Backdoor Vulnerabilities of LLM-As-A-JudgePoster2 citations
1165. Benchmarking LLMs' Judgments with No Gold StandardPoster2 citations
1166. Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error MitigationPoster2 citations
1167. Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?Poster2 citations
1168. Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judgePoster2 citations
1169. Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintsPoster2 citations
1170. Biologically Plausible Brain Graph TransformerPoster2 citations
1171. BirdSet: A Large-Scale Dataset for Audio Classification in Avian BioacousticsSpotlight2 citations
1172. Boltzmann priors for Implicit Transfer OperatorsPoster2 citations
1173. Both Ears Wide Open: Towards Language-Driven Spatial Audio GenerationSpotlight2 citations
1174. Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI ResponsesPoster2 citations
1175. Breaking the Reclustering Barrier in Centroid-based Deep ClusteringPoster2 citations
1176. Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationPoster2 citations
1177. CBGBench: Fill in the Blank of Protein-Molecule Complex Binding GraphSpotlight2 citations
1178. CPSample: Classifier Protected Sampling for Guarding Training Data During DiffusionPoster2 citations
1179. CTSyn: A Foundation Model for Cross Tabular Data GenerationPoster2 citations
1180. Can Textual Gradient Work in Federated Learning?Poster2 citations
1181. CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationPoster2 citations
1182. Capturing the Temporal Dependence of Training Data InfluenceOral2 citations
1183. Catastrophic Failure of LLM Unlearning via QuantizationPoster2 citations
1184. ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple DomainsPoster2 citations
1185. Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG AlignmentPoster2 citations
1186. CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and RerankingPoster2 citations
1187. Comparing noisy neural population dynamics using optimal transport distancesOral2 citations
1188. Compositional simulation-based inference for time seriesPoster2 citations
1189. Computational Explorations of Total Variation DistanceSpotlight2 citations
1190. Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention GatePoster2 citations
1191. ContextGNN: Beyond Two-Tower Recommendation SystemsPoster2 citations
1192. Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video GroundingPoster2 citations
1193. Continuous Ensemble Weather Forecasting with Diffusion modelsPoster2 citations
1194. Contractive Dynamical Imitation Policies for Efficient Out-of-Sample RecoveryPoster2 citations
1195. Contrastive Learning from Synthetic Audio DoppelgängersPoster2 citations
1196. Convergence and Implicit Bias of Gradient Descent on Continual Linear ClassificationPoster2 citations
1197. Copyright-Protected Language Generation via Adaptive Model FusionOral2 citations
1198. Correlated Proxies: A New Definition and Improved Mitigation for Reward HackingSpotlight2 citations
1199. Counterfactual Concept Bottleneck ModelsPoster2 citations
1200. Cross-Entropy Is All You Need To Invert the Data Generating ProcessOral2 citations
1201. Cut Your Losses in Large-Vocabulary Language ModelsOral2 citations
1202. DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single ImagePoster2 citations
1203. DOPL: Direct Online Preference Learning for Restless Bandits with Preference FeedbackPoster2 citations
1204. DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language ModelsPoster2 citations
1205. DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?Poster2 citations
1206. DarkBench: Benchmarking Dark Patterns in Large Language ModelsOral2 citations
1207. Data Selection via Optimal Control for Language ModelsOral2 citations
1208. Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data PoisoningPoster2 citations
1209. DataGen: Unified Synthetic Dataset Generation via Large Language ModelsPoster2 citations
1210. DataMan: Data Manager for Pre-training Large Language ModelsPoster2 citations
1211. DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM InferenceSpotlight2 citations
1212. Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence GuaranteesSpotlight2 citations
1213. Deep Linear Probe Generators for Weight Space LearningPoster2 citations
1214. DeepGate4: Efficient and Effective Representation Learning for Circuit Design at ScalePoster2 citations
1215. DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-trainingPoster2 citations
1216. Denoising Task Difficulty-based Curriculum for Training Diffusion ModelsPoster2 citations
1217. Denoising as Adaptation: Noise-Space Domain Adaptation for Image RestorationPoster2 citations
1218. Detecting Backdoor Samples in Contrastive Language Image PretrainingPoster2 citations
1219. DiffPuter: Empowering Diffusion Models for Missing Data ImputationSpotlight2 citations
1220. Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement LearningPoster2 citations
1221. DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image GenerationPoster2 citations
1222. Disentangling Representations through Multi-task LearningPoster2 citations
1223. Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?Poster2 citations
1224. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMsOral2 citations
1225. Do LLMs ``know'' internally when they follow instructions?Poster2 citations
1226. Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?Poster2 citations
1227. Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with ImaginationPoster2 citations
1228. Efficient Inference for Large Language Model-based Generative RecommendationPoster2 citations
1229. Efficient and Accurate Explanation Estimation with Distribution CompressionSpotlight2 citations
1230. Elucidating the Preconditioning in Consistency DistillationPoster2 citations
1231. Enhancing Learning with Label Differential Privacy by Vector ApproximationSpotlight2 citations
1232. Epistemic Monte Carlo Tree SearchPoster2 citations
1233. EqNIO: Subequivariant Neural Inertial OdometryPoster2 citations
1234. Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative StudyPoster2 citations
1235. Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model EnsemblesPoster2 citations
1236. Exploring Local Memorization in Diffusion Models via Bright Ending AttentionSpotlight2 citations
1237. Exploring the Design Space of Visual Context Representation in Video MLLMsPoster2 citations
1238. Expressivity of Neural Networks with Random Weights and Learned BiasesPoster2 citations
1239. Extending Mercer's expansion to indefinite and asymmetric kernelsPoster2 citations
1240. Feature-Based Online Bilateral TradePoster2 citations
1241. FlashMask: Efficient and Rich Mask Extension of FlashAttentionPoster2 citations
1242. Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural NetworksPoster2 citations
1243. FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language ModelsPoster2 citations
1244. Flow Matching with Gaussian Process Priors for Probabilistic Time Series ForecastingPoster2 citations
1245. Following the Human Thread in Social NavigationSpotlight2 citations
1246. Forgetting Transformer: Softmax Attention with a Forget GatePoster2 citations
1247. Forking Paths in Neural Text GenerationPoster2 citations
1248. Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language ModelsPoster2 citations
1249. FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded SamplingPoster2 citations
1250. From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and GenerationPoster2 citations
1251. From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample EfficiencyPoster2 citations
1252. GEVRM: Goal-Expressive Video Generation Model For Robust Visual ManipulationPoster2 citations
1253. GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse RenderingPoster2 citations
1254. GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero CostPoster2 citations
1255. GMValuator: Similarity-based Data Valuation for Generative ModelsPoster2 citations
1256. GROOT-2: Weakly Supervised Multimodal Instruction Following AgentsPoster2 citations
1257. GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian SplattingPoster2 citations
1258. GameArena: Evaluating LLM Reasoning through Live Computer GamesPoster2 citations
1259. Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object DetectionPoster2 citations
1260. Generalization Bounds and Model Complexity for Kolmogorov–Arnold NetworksPoster2 citations
1261. Generating Freeform Endoskeletal RobotsSpotlight2 citations
1262. Generative Classifiers Avoid Shortcut SolutionsPoster2 citations
1263. GraphArena: Evaluating and Exploring Large Language Models on Graph ComputationPoster2 citations
1264. Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion ModelsPoster2 citations
1265. HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech SynthesisPoster2 citations
1266. Herald: A Natural Language Annotated Lean 4 DatasetPoster2 citations
1267. HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous EnvironmentPoster2 citations
1268. High-Precision Dichotomous Image Segmentation via Probing Diffusion CapacityPoster2 citations
1269. Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive ExtensionPoster2 citations
1270. Hyper-ConnectionsPoster2 citations
1271. I Can Hear You: Selective Robust Training for Deepfake Audio DetectionPoster2 citations
1272. ImDy: Human Inverse Dynamics from Imitated ObservationsPoster2 citations
1273. ImProver: Agent-Based Automated Proof OptimizationPoster2 citations
1274. Image Watermarks are Removable using Controllable Regeneration from Clean NoisePoster2 citations
1275. ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene ImaginationPoster2 citations
1276. Immunogenicity Prediction with Dual Attention Enables Vaccine Target SelectionPoster2 citations
1277. Implicit In-context LearningPoster2 citations
1278. Improved Training Technique for Latent Consistency ModelsPoster2 citations
1279. Influence Functions for Scalable Data Attribution in Diffusion ModelsOral2 citations
1280. Intelligence at the Edge of ChaosPoster2 citations
1281. Interference Among First-Price Pacing Equilibria: A Bias and Variance AnalysisPoster2 citations
1282. IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement LearningPoster2 citations
1283. LLM Unlearning via Loss Adjustment with Only Forget DataPoster2 citations
1284. LLMs Can Plan Only If We Tell ThemPoster2 citations
1285. LaMPlace: Learning to Optimize Cross-Stage Metrics in Macro PlacementOral2 citations
1286. LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov SubspacePoster2 citations
1287. Language Imbalance Driven Rewarding for Multilingual Self-improvingPoster2 citations
1288. Lasso Bandit with Compatibility Condition on Optimal ArmPoster2 citations
1289. Last-Iterate Convergence Properties of Regret-Matching Algorithms in GamesPoster2 citations
1290. Layout-your-3D: Controllable and Precise 3D Generation with 2D BlueprintPoster2 citations
1291. LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware GridPoster2 citations
1292. Learning Distributions of Complex Fluid Simulations with Diffusion Graph NetworksOral2 citations
1293. Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent CooperationPoster2 citations
1294. Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose EstimationPoster2 citations
1295. Learning Spatial-Semantic Features for Robust Video Object SegmentationPoster2 citations
1296. Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed MethodsPoster2 citations
1297. Learning local equivariant representations for quantum operatorsSpotlight2 citations
1298. Learning stochastic dynamics from snapshots through regularized unbalanced optimal transportOral2 citations
1299. Learning to Discretize Denoising Diffusion ODEsOral2 citations
1300. Learning to Solve Differential Equation Constrained Optimization ProblemsSpotlight2 citations
1301. Locality Alignment Improves Vision-Language ModelsPoster2 citations
1302. Looped Transformers for Length GeneralizationPoster2 citations
1303. MA-RLHF: Reinforcement Learning from Human Feedback with Macro ActionsPoster2 citations
1304. MAST: model-agnostic sparsified trainingPoster2 citations
1305. MIND: Math Informed syNthetic Dialogues for Pretraining LLMsPoster2 citations
1306. MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex QuestionsOral2 citations
1307. MaestroMotif: Skill Design from Artificial Intelligence FeedbackOral2 citations
1308. Measuring Non-Adversarial Reproduction of Training Data in Large Language ModelsPoster2 citations
1309. Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to RefuseOral2 citations
1310. Mechanistic Permutability: Match Features Across LayersPoster2 citations
1311. MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt SynthesisPoster2 citations
1312. Metalic: Meta-Learning In-Context with Protein Language ModelsPoster2 citations
1313. Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated OptimizationPoster2 citations
1314. Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural NetworksPoster2 citations
1315. Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language ModelsSpotlight2 citations
1316. Mixture of Attentions For Speculative DecodingPoster2 citations
1317. MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of ShardsPoster2 citations
1318. Model Editing as a Robust and Denoised variant of DPO: A Case Study on ToxicityPoster2 citations
1319. Model Equality Testing: Which Model is this API Serving?Poster2 citations
1320. MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy SpectraPoster2 citations
1321. Montessori-Instruct: Generate Influential Training Data Tailored for Student LearningPoster2 citations
1322. Morphing Tokens Draw Strong Masked Image ModelsPoster2 citations
1323. MorphoDiff: Cellular Morphology Painting with Diffusion ModelsSpotlight2 citations
1324. MrSteve: Instruction-Following Agents in Minecraft with What-Where-When MemoryPoster2 citations
1325. NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model InternalsPoster2 citations
1326. NeRAF: 3D Scene Infused Neural Radiance and Acoustic FieldsPoster2 citations
1327. Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks?Poster2 citations
1328. Nesterov acceleration in benignly non-convex landscapesSpotlight2 citations
1329. Neuron based Personality Trait Induction in Large Language ModelsPoster2 citations
1330. Neuroplastic Expansion in Deep Reinforcement LearningPoster2 citations
1331. OATS: Outlier-Aware Pruning Through Sparse and Low Rank DecompositionPoster2 citations
1332. OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?Poster2 citations
1333. OPTAMI: Global Superlinear Convergence of High-order MethodsPoster2 citations
1334. OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution FittingPoster2 citations
1335. OmniKV: Dynamic Context Selection for Efficient Long-Context LLMsPoster2 citations
1336. OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics GenerationPoster2 citations
1337. On Calibration of LLM-based Guard Models for Reliable Content ModerationPoster2 citations
1338. On a Connection Between Imitation Learning and RLHFPoster2 citations
1339. On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking FunctionsPoster2 citations
1340. On the Crucial Role of Initialization for Matrix FactorizationPoster2 citations
1341. On the Hölder Stability of Multiset and Graph Neural NetworksOral2 citations
1342. Open-Vocabulary Customization from CLIP via Data-Free Knowledge DistillationOral2 citations
1343. Open-World Reinforcement Learning over Long Short-Term ImaginationOral2 citations
1344. OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?Poster2 citations
1345. Operator Deep Smoothing for Implied VolatilityPoster2 citations
1346. Optimal Strong Regret and Violation in Constrained MDPs via Policy OptimizationPoster2 citations
1347. Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based SamplingPoster2 citations
1348. Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion ModelSpotlight2 citations
1349. PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision TransformerPoster2 citations
1350. PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic AlignmentPoster2 citations
1351. PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMSPoster2 citations
1352. Physics-Informed Deep Inverse Operator Networks for Solving PDE Inverse ProblemsPoster2 citations
1353. PolaFormer: Polarity-aware Linear Attention for Vision TransformersPoster2 citations
1354. Precedence-Constrained Winter Value for Effective Graph Data ValuationPoster2 citations
1355. Prioritized Generative ReplayOral2 citations
1356. Progressive Compositionality in Text-to-Image Generative ModelsSpotlight2 citations
1357. Progressive Compression with Universally Quantized Diffusion ModelsOral2 citations
1358. Progressive Mixed-Precision Decoding for Efficient LLM InferencePoster2 citations
1359. Progressive distillation induces an implicit curriculumOral2 citations
1360. Protecting against simultaneous data poisoning attacksPoster2 citations
1361. Proteina: Scaling Flow-based Protein Structure Generative ModelsOral2 citations
1362. Provably Accurate Shapley Value Estimation via Leverage Score SamplingSpotlight2 citations
1363. Provence: efficient and robust context pruning for retrieval-augmented generationPoster2 citations
1364. Quantum-PEFT: Ultra parameter-efficient fine-tuningPoster2 citations
1365. REFINE: Inversion-Free Backdoor Defense via Model ReprogrammingPoster2 citations
1366. RFWave: Multi-band Rectified Flow for Audio Waveform ReconstructionPoster2 citations
1367. RMB: Comprehensively benchmarking reward models in LLM alignmentPoster2 citations
1368. ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLPoster2 citations
1369. Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-TuningPoster2 citations
1370. Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM GuidanceSpotlight2 citations
1371. ReAttention: Training-Free Infinite Context with Finite Attention ScopePoster2 citations
1372. ReGenesis: LLMs can Grow into Reasoning Generalists via Self-ImprovementOral2 citations
1373. Reasoning of Large Language Models over Knowledge Graphs with Super-RelationsPoster2 citations
1374. Reflective Gaussian SplattingPoster2 citations
1375. Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHFPoster2 citations
1376. RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataPoster2 citations
1377. Residual Stream Analysis with Multi-Layer SAEsPoster2 citations
1378. Residual-MPPI: Online Policy Customization for Continuous ControlPoster2 citations
1379. Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go BeyondPoster2 citations
1380. Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and OptimizationPoster2 citations
1381. Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)Poster2 citations
1382. Revisiting Random Walks for Learning on GraphsSpotlight2 citations
1383. RuAG: Learned-rule-augmented Generation for Large Language ModelsPoster2 citations
1384. SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIPPoster2 citations
1385. SAVA: Scalable Learning-Agnostic Data ValuationPoster2 citations
1386. STAFF: Speculative Coreset Selection for Task-Specific Fine-tuningPoster2 citations
1387. STAR: Synthesis of Tailored ArchitecturesOral2 citations
1388. SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video UnderstandingSpotlight2 citations
1389. SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference AccelerationPoster2 citations
1390. Samba: Synchronized Set-of-Sequences Modeling for Multiple Object TrackingSpotlight2 citations
1391. ScImage: How good are multimodal large language models at scientific text-to-image generation?Poster2 citations
1392. Scalable Bayesian Learning with posteriorsPoster2 citations
1393. Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical PhysicsPoster2 citations
1394. Scaling Laws for Downstream Task Performance in Machine TranslationPoster2 citations
1395. Scaling Speech-Text Pre-training with Synthetic Interleaved DataPoster2 citations
1396. Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion ModelsPoster2 citations
1397. Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement LearningPoster2 citations
1398. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity ReductionSpotlight2 citations
1399. Searching for Optimal Solutions with LLMs via Bayesian OptimizationPoster2 citations
1400. Second-Order Min-Max Optimization with Lazy HessiansOral2 citations
1401. See What You Are Told: Visual Attention Sink in Large Multimodal ModelsPoster2 citations
1402. Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language ModelsPoster2 citations
1403. Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering VectorsPoster2 citations
1404. SiReRAG: Indexing Similar and Related Information for Multihop ReasoningPoster2 citations
1405. Simulating Human-like Daily Activities with Desire-driven AutonomyPoster2 citations
1406. Size-Generalizable RNA Structure Evaluation by Exploring Hierarchical GeometriesPoster2 citations
1407. Skill Expansion and Composition in Parameter SpacePoster2 citations
1408. SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion PredictionPoster2 citations
1409. Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language ModelPoster2 citations
1410. Sparse autoencoders reveal selective remapping of visual concepts during adaptationPoster2 citations
1411. Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMsPoster2 citations
1412. Strategic Classification With ExternalitiesPoster2 citations
1413. Streamlining Prediction in Bayesian Deep LearningPoster2 citations
1414. Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector AblationPoster2 citations
1415. SyllableLM: Learning Coarse Semantic Units for Speech Language ModelsPoster2 citations
1416. Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic DataPoster2 citations
1417. T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular DataPoster2 citations
1418. TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential DynamicsPoster2 citations
1419. TIPS: Text-Image Pretraining with Spatial awarenessPoster2 citations
1420. Tailoring Mixup to Data for CalibrationPoster2 citations
1421. Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking DynamicsPoster2 citations
1422. TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task TypesPoster2 citations
1423. Temporal Reasoning Transfer from Text to VideoPoster2 citations
1424. The Complexity of Two-Team Polymatrix Games with Independent AdversariesOral2 citations
1425. The Same but Different: Structural Similarities and Differences in Multilingual Language ModelingPoster2 citations
1426. Think Then React: Towards Unconstrained Action-to-Reaction Motion GenerationPoster2 citations
1427. TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series ForecastingPoster2 citations
1428. TokenFormer: Rethinking Transformer Scaling with Tokenized Model ParametersSpotlight2 citations
1429. TopoLM: brain-like spatio-functional organization in a topographic language modelOral2 citations
1430. TopoNets: High performing vision and language models with brain-like topographySpotlight2 citations
1431. Toward Guidance-Free AR Visual Generation via Condition Contrastive AlignmentOral2 citations
1432. Towards Optimal Multi-draft Speculative DecodingPoster2 citations
1433. Track-On: Transformer-based Online Point Tracking with MemoryPoster2 citations
1434. Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous DrivingPoster2 citations
1435. Transformers Handle Endogeneity in In-Context Linear RegressionPoster2 citations
1436. Truncated Consistency ModelsPoster2 citations
1437. Tuning Frequency Bias of State Space ModelsSpotlight2 citations
1438. Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample OptimizationPoster2 citations
1439. Tuning-Free Bilevel Optimization: New Algorithms and Convergence AnalysisPoster2 citations
1440. TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video GenerationPoster2 citations
1441. Unbounded: A Generative Infinite Game of Character Life SimulationPoster2 citations
1442. Uncertainty modeling for fine-tuned implicit functionsPoster2 citations
1443. Underdamped Diffusion Bridges with Applications to SamplingPoster2 citations
1444. Unearthing Skill-level Insights for Understanding Trade-offs of Foundation ModelsPoster2 citations
1445. UniGEM: A Unified Approach to Generation and Property Prediction for MoleculesPoster2 citations
1446. Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and SearchPoster2 citations
1447. Vector-ICL: In-context Learning with Continuous Vector RepresentationsPoster2 citations
1448. ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion SamplerPoster2 citations
1449. Video In-context Learning: Autoregressive Transformers are Zero-Shot Video ImitatorsPoster2 citations
1450. VideoGrain: Modulating Space-Time Attention for Multi-Grained Video EditingPoster2 citations
1451. VideoShield: Regulating Diffusion-based Video Generation Models via WatermarkingPoster2 citations
1452. Vision Language Models are In-Context Value LearnersSpotlight2 citations
1453. Wavelet Diffusion Neural OperatorPoster2 citations
1454. WeatherGFM: Learning a Weather Generalist Foundation Model via In-context LearningPoster2 citations
1455. What Makes a Maze Look Like a Maze?Poster2 citations
1456. What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative ModelsPoster2 citations
1457. What should a neuron aim for? Designing local objective functions based on information theoryOral2 citations
1458. Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor AttacksPoster2 citations
1459. Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural CollapseOral2 citations
1460. ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ AttentionPoster2 citations
1461. Zero-shot Model-based Reinforcement Learning using Large Language ModelsPoster2 citations
1462. kNN Attention Demystified: A Theoretical Exploration for Scalable TransformersPoster2 citations
1463. miniCTX: Neural Theorem Proving with (Long-)ContextsOral2 citations
1464. {$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World DomainsPoster2 citations
1465. $InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face RestorationPoster1 citations
1466. (Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep LearningPoster1 citations
1467. 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D WorldsPoster1 citations
1468. 6D Object Pose Tracking in Internet Videos for Robotic ManipulationPoster1 citations
1469. 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric RenderingPoster1 citations
1470. A Benchmark for Semantic Sensitive Information in LLMs OutputsPoster1 citations
1471. A Black Swan Hypothesis: The Role of Human Irrationality in AI SafetyPoster1 citations
1472. A Common Pitfall of Margin-based Language Model Alignment: Gradient EntanglementPoster1 citations
1473. A Conditional Independence Test in the Presence of DiscretizationPoster1 citations
1474. A General Framework for Producing Interpretable Semantic Text EmbeddingsPoster1 citations
1475. A Periodic Bayesian Flow for Material GenerationSpotlight1 citations
1476. A Simple Approach to Unifying Diffusion-based Conditional GenerationPoster1 citations
1477. A Simple yet Effective $\Delta\Delta G$ Predictor is An Unsupervised Antibody Optimizer and ExplainerPoster1 citations
1478. A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or SubgoalsPoster1 citations
1479. A Statistical Framework for Ranking LLM-based ChatbotsPoster1 citations
1480. A Theoretical Framework for Partially-Observed Reward States in RLHFPoster1 citations
1481. A Theory for Token-Level Harmonization in Retrieval-Augmented GenerationPoster1 citations
1482. A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space TranslationsPoster1 citations
1483. A new framework for evaluating model out-of-distribution generalisation for the biochemical domainPoster1 citations
1484. ACES: Automatic Cohort Extraction System for Event-Stream DatasetsPoster1 citations
1485. ADIFF: Explaining audio difference using natural languageSpotlight1 citations
1486. Accelerating Training with Neuron Interaction and Nowcasting NetworksPoster1 citations
1487. ActSafe: Active Exploration with Safety Constraints for Reinforcement LearningPoster1 citations
1488. Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision ProcessesPoster1 citations
1489. Active Task Disambiguation with LLMsSpotlight1 citations
1490. Ada-K Routing: Boosting the Efficiency of MoE-based LLMsPoster1 citations
1491. AdaFisher: Adaptive Second Order Optimization via Fisher InformationPoster1 citations
1492. AdaWM: Adaptive World Model based Planning for Autonomous DrivingPoster1 citations
1493. Adapting Multi-modal Large Language Model to Concept Drift From Pre-training OnwardsPoster1 citations
1494. Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement LearningPoster1 citations
1495. Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language ModelsPoster1 citations
1496. Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training StagesPoster1 citations
1497. Advancing Prompt-Based Methods for Replay-Independent General Continual LearningPoster1 citations
1498. Adversarial Attacks on Data AttributionPoster1 citations
1499. Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured DataPoster1 citations
1500. Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal VideosPoster1 citations
1501. Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time SeriesOral1 citations
1502. Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMsPoster1 citations
1503. An Empirical Analysis of Uncertainty in Large Language Model EvaluationsPoster1 citations
1504. An Engorgio Prompt Makes Large Language Model Babble onPoster1 citations
1505. An Information Criterion for Controlled Disentanglement of Multimodal DataPoster1 citations
1506. An Online Learning Theory of Trading-Volume MaximizationPoster1 citations
1507. AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit TopologiesSpotlight1 citations
1508. AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D ReconstructionPoster1 citations
1509. Approximation algorithms for combinatorial optimization with predictionsSpotlight1 citations
1510. Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and GenerationPoster1 citations
1511. AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context AttributionPoster1 citations
1512. Attributing Culture-Conditioned Generations to Pretraining CorporaPoster1 citations
1513. Audio Large Language Models Can Be Descriptive Speech Quality EvaluatorsPoster1 citations
1514. Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion ModelsPoster1 citations
1515. BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge DistillationPoster1 citations
1516. Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated LearningPoster1 citations
1517. Bayesian Optimization via Continual Variational Last Layer TrainingSpotlight1 citations
1518. Better than Your Teacher: LLM Agents that learn from Privileged AI FeedbackPoster1 citations
1519. Beware of Calibration Data for Pruning Large Language ModelsPoster1 citations
1520. Beyond Autoregression: Fast LLMs via Self-Distillation Through TimePoster1 citations
1521. Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsPoster1 citations
1522. Beyond Random Masking: When Dropout meets Graph Convolutional NetworksPoster1 citations
1523. Beyond Sequence: Impact of Geometric Context for RNA Property PredictionPoster1 citations
1524. Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow NetworksSpotlight1 citations
1525. Bilinear MLPs enable weight-based mechanistic interpretabilitySpotlight1 citations
1526. BingoGuard: LLM Content Moderation Tools with Risk LevelsPoster1 citations
1527. Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing ProblemsPoster1 citations
1528. Bootstrapping Language-Guided Navigation Learning with Self-Refining Data FlywheelPoster1 citations
1529. Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision TransformersPoster1 citations
1530. BrainUICL: An Unsupervised Individual Continual Learning Framework for EEG ApplicationsPoster1 citations
1531. Bridging Compressed Image Latents and Multimodal Large Language ModelsPoster1 citations
1532. Bridging Jensen Gap for Max-Min Group Fairness Optimization in RecommendationPoster1 citations
1533. Bridging the Data Provenance Gap Across Text, Speech, and VideoPoster1 citations
1534. Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic SpaceSpotlight1 citations
1535. Bundle Neural Network for message diffusion on graphsSpotlight1 citations
1536. C-CLIP: Multimodal Continual Learning for Vision-Language ModelPoster1 citations
1537. CAKE: Cascading and Adaptive KV Cache Eviction with Layer PreferencesPoster1 citations
1538. COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate GenerationPoster1 citations
1539. CONTRA: Conformal Prediction Region via Normalizing Flow TransformationPoster1 citations
1540. CR-CTC: Consistency regularization on CTC for improved speech recognitionPoster1 citations
1541. Calibrating Expressions of CertaintyPoster1 citations
1542. Can Generative AI Solve Your In-Context Learning Problem? A Martingale PerspectivePoster1 citations
1543. Can In-context Learning Really Generalize to Out-of-distribution Tasks?Poster1 citations
1544. Can Transformers Do Enumerative Geometry?Poster1 citations
1545. Can Watermarks be Used to Detect LLM IP Infringement For Free?Poster1 citations
1546. Can We Talk Models Into Seeing the World Differently?Poster1 citations
1547. Causal Order: The Key to Leveraging Imperfect Experts in Causal InferencePoster1 citations
1548. CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric AwarenessPoster1 citations
1549. Chain-of-region: Visual Language Models Need Details for Diagram AnalysisPoster1 citations
1550. CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired TransformerPoster1 citations
1551. CoInD: Enabling Logical Compositions in Diffusion ModelsPoster1 citations
1552. CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at InferencePoster1 citations
1553. Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor FusionPoster1 citations
1554. Collab: Controlled Decoding using Mixture of Agents for LLM AlignmentPoster1 citations
1555. ComLoRA: A Competitive Learning Approach for Enhancing LoRAPoster1 citations
1556. Competing Large Language Models in Multi-Agent Gaming EnvironmentsPoster1 citations
1557. Compute-Constrained Data SelectionPoster1 citations
1558. Concept Bottleneck Language Models For Protein DesignPoster1 citations
1559. Concept-ROT: Poisoning Concepts in Large Language Models with Model EditingPoster1 citations
1560. Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution EstimationPoster1 citations
1561. Conditional Testing based on Localized Conformal $p$-valuesPoster1 citations
1562. Consistency Checks for Language Model ForecastersOral1 citations
1563. Consistent Flow Distillation for Text-to-3D GenerationPoster1 citations
1564. Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR DataPoster1 citations
1565. Control-oriented Clustering of Visual Latent RepresentationSpotlight1 citations
1566. Controllable Generation via Locally Constrained ResamplingPoster1 citations
1567. Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained OptimizationPoster1 citations
1568. Controlled LLM Decoding via Discrete Auto-regressive BiasingPoster1 citations
1569. Counterfactual RealizabilitySpotlight1 citations
1570. Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionPoster1 citations
1571. Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset ConstraintPoster1 citations
1572. DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned ModelsSpotlight1 citations
1573. DCT-CryptoNets: Scaling Private Inference in the Frequency DomainPoster1 citations
1574. DEPT: Decoupled Embeddings for Pre-training Language ModelsOral1 citations
1575. DEPfold: RNA Secondary Structure Prediction as Dependency Parsing.Poster1 citations
1576. DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsPoster1 citations
1577. DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories SearchPoster1 citations
1578. DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace EditingPoster1 citations
1579. Data Pruning by Information MaximizationPoster1 citations
1580. Data-adaptive Differentially Private Prompt Synthesis for In-Context LearningPoster1 citations
1581. DataEnvGym: Data Generation Agents in Teacher Environments with Student FeedbackSpotlight1 citations
1582. Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep NetworksPoster1 citations
1583. DebGCD: Debiased Learning with Distribution Guidance for Generalized Category DiscoveryPoster1 citations
1584. Debiasing Mini-Batch Quadratics for Applications in Deep LearningPoster1 citations
1585. Decoding Game: On Minimax Optimality of Heuristic Text Generation StrategiesPoster1 citations
1586. Deep Distributed Optimization for Large-Scale Quadratic ProgrammingPoster1 citations
1587. Deep Weight Factorization: Sparse Learning Through the Lens of Artificial SymmetriesPoster1 citations
1588. Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial ContextsPoster1 citations
1589. Demystifying the Token Dynamics of Deep Selective State Space ModelsSpotlight1 citations
1590. Denoising with a Joint-Embedding Predictive ArchitecturePoster1 citations
1591. Dense Video Object Captioning from Disjoint SupervisionSpotlight1 citations
1592. DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human ReferencesPoster1 citations
1593. DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise ReductionPoster1 citations
1594. Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion ModelsPoster1 citations
1595. DiffGAD: A Diffusion-based Unsupervised Graph Anomaly DetectorPoster1 citations
1596. Differentiation and Specialization of Attention Heads via the Refined Local Learning CoefficientSpotlight1 citations
1597. Diffusion State-Guided Projected Gradient for Inverse ProblemsPoster1 citations
1598. Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion ModelsPoster1 citations
1599. DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image EditingPoster1 citations
1600. Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text MatchingPoster1 citations
1601. Discrete Copula DiffusionPoster1 citations
1602. Discriminating image representations with principal distortionsPoster1 citations
1603. Discriminator-Guided Embodied Planning for LLM AgentPoster1 citations
1604. Distance-Based Tree-Sliced Wasserstein DistancePoster1 citations
1605. Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow MatchingPoster1 citations
1606. Distilling Structural Representations into Protein Sequence ModelsPoster1 citations
1607. Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model InferencePoster1 citations
1608. Distribution-Free Data Uncertainty for Neural Network RegressionPoster1 citations
1609. Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt TuningPoster1 citations
1610. Diverse Preference Learning for Capabilities and AlignmentPoster1 citations
1611. Do Deep Neural Network Solutions Form a Star Domain?Poster1 citations
1612. Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language ModelsPoster1 citations
1613. Do as We Do, Not as You Think: the Conformity of Large Language ModelsOral1 citations
1614. Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion ModelPoster1 citations
1615. Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLSpotlight1 citations
1616. Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter EfficientPoster1 citations
1617. Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initializationPoster1 citations
1618. Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic ScenesPoster1 citations
1619. Dynamical Diffusion: Learning Temporal Dynamics with Diffusion ModelsPoster1 citations
1620. Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMsPoster1 citations
1621. EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM AgentsPoster1 citations
1622. Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay PerspectivePoster1 citations
1623. Efficient Active Imitation Learning with Random Network DistillationPoster1 citations
1624. Efficient Automated Circuit Discovery in Transformers using Contextual DecompositionPoster1 citations
1625. Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale BenchmarkPoster1 citations
1626. Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory StitchingPoster1 citations
1627. Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous GraspingPoster1 citations
1628. Efficient Source-Free Time-Series Adaptation via Parameter Subspace DisentanglementPoster1 citations
1629. Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional DistributionsPoster1 citations
1630. Efficient and Trustworthy Causal Discovery with Latent Variables and Complex RelationsPoster1 citations
1631. Elliptic Loss RegularizationPoster1 citations
1632. EmbedLLM: Learning Compact Representations of Large Language ModelsSpotlight1 citations
1633. Empowering Users in Digital Privacy Management through Interactive LLM-Based AgentsPoster1 citations
1634. Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous InferencePoster1 citations
1635. Enhancing Compositional Text-to-Image Generation with Reliable Random SeedsSpotlight1 citations
1636. Enhancing Language Model Agents using Diversity of ThoughtsPoster1 citations
1637. Enhancing Robust Fairness via Confusional Spectral RegularizationPoster1 citations
1638. Episodic Memories Generation and Evaluation Benchmark for Large Language ModelsPoster1 citations
1639. Erasing Concept Combination from Text-to-Image Diffusion ModelPoster1 citations
1640. Error-quantified Conformal Inference for Time SeriesPoster1 citations
1641. Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal PerspectivePoster1 citations
1642. Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language ModelsPoster1 citations
1643. Exact Community Recovery under Side Information: Optimality of Spectral AlgorithmsPoster1 citations
1644. Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph ForecastingPoster1 citations
1645. Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient ReasonsPoster1 citations
1646. Exploring The Loss Landscape Of Regularized Neural Networks Via Convex DualityOral1 citations
1647. Exposure Bracketing Is All You Need For A High-Quality ImagePoster1 citations
1648. Fast Training of Sinusoidal Neural Fields via Scaling InitializationPoster1 citations
1649. Fast training and sampling of Restricted Boltzmann MachinesPoster1 citations
1650. Faster Algorithms for Structured Linear and Kernel Support Vector MachinesPoster1 citations
1651. Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural NetworksPoster1 citations
1652. Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global ForgettingPoster1 citations
1653. Feedback Favors the Generalization of Neural ODEsOral1 citations
1654. Fengbo: a Clifford Neural Operator pipeline for 3D PDEs in Computational Fluid DynamicsPoster1 citations
1655. Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task ArithmeticPoster1 citations
1656. Fine-tuning can Help Detect Pretraining Data from Large Language ModelsPoster1 citations
1657. Fine-tuning with Reserved Majority for Noise ReductionSpotlight1 citations
1658. FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardwarePoster1 citations
1659. Flat Reward in Policy Parameter Space Implies Robust Reinforcement LearningOral1 citations
1660. FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence InferenceOral1 citations
1661. Fourier Sliced-Wasserstein Embedding for Multisets and MeasuresPoster1 citations
1662. From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal HierarchyPoster1 citations
1663. From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian EstimationPoster1 citations
1664. Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image GenerationPoster1 citations
1665. Fully-inductive Node Classification on Arbitrary GraphsPoster1 citations
1666. GDrag:Towards General-Purpose Interactive Editing with Anti-ambiguity Point DiffusionPoster1 citations
1667. GNNs Getting ComFy: Community and Feature Similarity Guided RewiringPoster1 citations
1668. GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent GenerationSpotlight1 citations
1669. GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt OptimizersPoster1 citations
1670. GenSE: Generative Speech Enhancement via Language Models using Hierarchical ModelingPoster1 citations
1671. Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture PriorsSpotlight1 citations
1672. Generalization through variance: how noise shapes inductive biases in diffusion modelsPoster1 citations
1673. Generalized Behavior Learning from Diverse DemonstrationsPoster1 citations
1674. Generalized Consistency Trajectory Models for Image ManipulationPoster1 citations
1675. Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear BanditsPoster1 citations
1676. Glad: A Streaming Scene Generator for Autonomous DrivingPoster1 citations
1677. Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text DetectionPoster1 citations
1678. Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz EstimatesPoster1 citations
1679. Gradient descent with generalized Newton’s methodPoster1 citations
1680. Gramian Multimodal Representation Learning and AlignmentPoster1 citations
1681. Graph Neural Networks Gone HogwildPoster1 citations
1682. Graph Neural Networks for Edge Signals: Orientation Equivariance and InvariancePoster1 citations
1683. Graph Neural Ricci Flow: Evolving Feature from a Curvature PerspectivePoster1 citations
1684. Graph-Guided Scene Reconstruction from Images with 3D Gaussian SplattingPoster1 citations
1685. GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D ManipulationPoster1 citations
1686. GridMix: Exploring Spatial Modulation for Neural Fields in PDE ModelingOral1 citations
1687. Grokking at the Edge of Numerical StabilityPoster1 citations
1688. Grounding Video Models to Actions through Goal Conditioned ExplorationSpotlight1 citations
1689. Group Downsampling with Equivariant Anti-aliasingPoster1 citations
1690. Group Ligands Docking to Protein PocketsPoster1 citations
1691. Guided Score identity Distillation for Data-Free One-Step Text-to-Image GenerationPoster1 citations
1692. Gyrogroup Batch NormalizationPoster1 citations
1693. HELM: Hierarchical Encoding for mRNA Language ModelingPoster1 citations
1694. HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token MiningPoster1 citations
1695. HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA ExpertsPoster1 citations
1696. HOPE for a Robust Parameterization of Long-memory State Space ModelsPoster1 citations
1697. HR-Extreme: A High-Resolution Dataset for Extreme Weather ForecastingPoster1 citations
1698. Handling Delay in Real-Time Reinforcement LearningPoster1 citations
1699. HeadMap: Locating and Enhancing Knowledge Circuits in LLMsPoster1 citations
1700. Hierarchical Uncertainty Estimation for Learning-based Registration in NeuroimagingPoster1 citations
1701. High-Quality Joint Image and Video Tokenization with Causal VAEPoster1 citations
1702. Higher-Order Graphon Neural Networks: Approximation and Cut DistanceSpotlight1 citations
1703. Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual DataPoster1 citations
1704. Holographic Node Representations: Pre-training Task-Agnostic Node EmbeddingsPoster1 citations
1705. Horizon Generalization in Reinforcement LearningPoster1 citations
1706. How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?Poster1 citations
1707. How Far Are We from True Unlearnability?Poster1 citations
1708. How Much is Unseen Depends Chiefly on Information About the SeenSpotlight1 citations
1709. Human-Aligned Chess With a Bit of SearchPoster1 citations
1710. Humanizing the Machine: Proxy Attacks to Mislead LLM DetectorsPoster1 citations
1711. IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and IlluminationsPoster1 citations
1712. IDInit: A Universal and Stable Initialization Method for Neural Network TrainingPoster1 citations
1713. IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATIONPoster1 citations
1714. IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video SynthesisPoster1 citations
1715. ImpScore: A Learnable Metric For Quantifying The Implicitness Level of SentencesSpotlight1 citations
1716. Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's FormulaPoster1 citations
1717. Improving Graph Neural Networks by Learning Continuous Edge DirectionsPoster1 citations
1718. Improving Neural Optimal Transport via Displacement InterpolationPoster1 citations
1719. In vivo cell-type and brain region classification via multimodal contrastive learningSpotlight1 citations
1720. Infinite-Resolution Integral Noise Warping for Diffusion ModelsPoster1 citations
1721. Information Theoretic Text-to-Image AlignmentPoster1 citations
1722. Injecting Universal Jailbreak Backdoors into LLMs in MinutesPoster1 citations
1723. Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought LeapsPoster1 citations
1724. Input Space Mode Connectivity in Deep Neural NetworksPoster1 citations
1725. InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical SystemsPoster1 citations
1726. Instance-dependent Early StoppingSpotlight1 citations
1727. InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian SplattingPoster1 citations
1728. Intermediate Layer Classifiers for OOD generalizationPoster1 citations
1729. Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMsPoster1 citations
1730. Inverse decision-making using neural amortized Bayesian actorsPoster1 citations
1731. InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical SciencesSpotlight1 citations
1732. Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task LearningPoster1 citations
1733. Is Large-scale Pretraining the Secret to Good Domain Generalization?Poster1 citations
1734. Iterative Label Refinement Matters More than Preference Optimization under Weak SupervisionSpotlight1 citations
1735. Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model AlignmentOral1 citations
1736. KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural NetworksPoster1 citations
1737. KBLaM: Knowledge Base augmented Language ModelPoster1 citations
1738. KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language ModelsPoster1 citations
1739. Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control TasksOral1 citations
1740. Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video GroundingOral1 citations
1741. Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge AcquisitionOral1 citations
1742. Kronecker Mask and Interpretive Prompts are Language-Action Video LearnersPoster1 citations
1743. LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak SupervisionPoster1 citations
1744. LASeR: Towards Diversified and Generalizable Robot Design with Large Language ModelsPoster1 citations
1745. LLMOPT: Learning to Define and Solve General Optimization Problems from ScratchPoster1 citations
1746. Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic LearningPoster1 citations
1747. Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image UnderstandingSpotlight1 citations
1748. Latent Bayesian Optimization via Autoregressive Normalizing FlowsOral1 citations
1749. Layerwise Recurrent Router for Mixture-of-ExpertsPoster1 citations
1750. Learnable Expansion of Graph Operators for Multi-Modal Feature FusionPoster1 citations
1751. Learning 3D Perception from Others' PredictionsPoster1 citations
1752. Learning Clustering-based Prototypes for Compositional Zero-Shot LearningPoster1 citations
1753. Learning Color Equivariant RepresentationsPoster1 citations
1754. Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video RetrievalPoster1 citations
1755. Learning Interpretable Hierarchical Dynamical Systems Models from Time Series DataPoster1 citations
1756. Learning LLM-as-a-Judge for Preference AlignmentPoster1 citations
1757. Learning Molecular Representation in a CellPoster1 citations
1758. Learning from Imperfect Human Feedback: A Tale from Corruption-Robust DuelingPoster1 citations
1759. Learning the Complexity of Weakly Noisy Quantum StatesPoster1 citations
1760. Learning to Communicate Through Implicit Communication ChannelsPoster1 citations
1761. Learning to Contextualize Web Pages for Enhanced Decision Making by LLM AgentsPoster1 citations
1762. Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie GroupsPoster1 citations
1763. Lift Your Molecules: Molecular Graph Generation in Latent Euclidean SpacePoster1 citations
1764. Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion ModelsPoster1 citations
1765. Linear Representations of Political Perspective Emerge in Large Language ModelsOral1 citations
1766. Linear Transformer Topological Masking with Graph Random FeaturesPoster1 citations
1767. LocoVR: Multiuser Indoor Locomotion Dataset in Virtual RealityPoster1 citations
1768. Logicbreaks: A Framework for Understanding Subversion of Rule-based InferencePoster1 citations
1769. Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-MakingPoster1 citations
1770. LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference OptimizationPoster1 citations
1771. MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLSpotlight1 citations
1772. MANTRA: The Manifold Triangulations AssemblagePoster1 citations
1773. MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model ConstructionPoster1 citations
1774. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied AgentsPoster1 citations
1775. MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMsPoster1 citations
1776. MLPs Learn In-Context on Regression and Classification TasksPoster1 citations
1777. MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning SegmentationPoster1 citations
1778. MTSAM: Multi-Task Fine-Tuning for Segment Anything ModelPoster1 citations
1779. MVTokenFlow: High-quality 4D Content Generation using Multiview Token FlowPoster1 citations
1780. Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuningPoster1 citations
1781. Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU NetworksPoster1 citations
1782. MambaExtend: A Training-Free Approach to Improve Long Context Extension of MambaPoster1 citations
1783. MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for MambaPoster1 citations
1784. ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement TasksPoster1 citations
1785. Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated ImagesPoster1 citations
1786. Matrix Product Sketching via Coordinated SamplingPoster1 citations
1787. MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networksPoster1 citations
1788. MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationPoster1 citations
1789. Measuring memorization in RLHF for code completionPoster1 citations
1790. Memory Efficient Transformer Adapter for Dense PredictionsPoster1 citations
1791. Meta-Continual Learning of Neural FieldsPoster1 citations
1792. MetaUrban: An Embodied AI Simulation Platform for Urban MicromobilitySpotlight1 citations
1793. Mind Control through Causal Inference: Predicting Clean Images from Poisoned DataPoster1 citations
1794. Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion ModelsPoster1 citations
1795. Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation ErrorPoster1 citations
1796. Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format AlignmentPoster1 citations
1797. MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse UpcyclingPoster1 citations
1798. Modeling Complex System Dynamics with Flow Matching Across Time and ConditionsSpotlight1 citations
1799. More RLHF, More Trust? On The Impact of Preference Alignment On TrustworthinessOral1 citations
1800. MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete DiffusionSpotlight1 citations
1801. MrT5: Dynamic Token Merging for Efficient Byte-level Language ModelsPoster1 citations
1802. Mufu: Multilingual Fused Learning for Low-Resource Translation with LLMPoster1 citations
1803. Multi-Dimensional Conformal PredictionPoster1 citations
1804. Multi-Perspective Data Augmentation for Few-shot Object DetectionPoster1 citations
1805. Multi-Scale Fusion for Object RepresentationPoster1 citations
1806. Multi-agent cooperation through learning-aware policy gradientsPoster1 citations
1807. Multi-domain Distribution Learning for De Novo Drug DesignPoster1 citations
1808. Multi-session, multi-task neural decoding from distinct cell-types and brain regionsSpotlight1 citations
1809. Multilevel Generative Samplers for Investigating Critical PhenomenaPoster1 citations
1810. Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation LearningPoster1 citations
1811. NEAR: A Training-Free Pre-Estimator of Machine Learning Model PerformancePoster1 citations
1812. NatureLM-audio: an Audio-Language Foundation Model for BioacousticsPoster1 citations
1813. Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication EfficiencySpotlight1 citations
1814. Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsPoster1 citations
1815. NetMoE: Accelerating MoE Training through Dynamic Sample PlacementSpotlight1 citations
1816. Neural Approximate Mirror Maps for Constrained Diffusion ModelsPoster1 citations
1817. Neural Context Flows for Meta-Learning of Dynamical SystemsPoster1 citations
1818. Neural Dueling Bandits: Preference-Based Optimization with Human FeedbackPoster1 citations
1819. Neural Eulerian Scene Flow FieldsPoster1 citations
1820. Neural Interactive ProofsPoster1 citations
1821. Neural Phylogeny: Fine-Tuning Relationship Detection among Neural NetworksPoster1 citations
1822. Neural Spacetimes for DAG Representation LearningPoster1 citations
1823. No Need to Talk: Asynchronous Mixture of Language ModelsSpotlight1 citations
1824. NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language ModelsPoster1 citations
1825. Node-Time Conditional Prompt Learning in Dynamic GraphsPoster1 citations
1826. Non-Adversarial Inverse Reinforcement Learning via Successor Feature MatchingPoster1 citations
1827. Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State SamplingPoster1 citations
1828. Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient ClippingPoster1 citations
1829. Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text ClassificationSpotlight1 citations
1830. OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner FrameworkPoster1 citations
1831. Offline Hierarchical Reinforcement Learning via Inverse OptimizationPoster1 citations
1832. Offline Model-Based Optimization by Learning to RankPoster1 citations
1833. On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance RepresentationPoster1 citations
1834. On the Expressive Power of Sparse Geometric MPNNsPoster1 citations
1835. On the Expressiveness of Rational ReLU Neural Networks With Bounded DepthSpotlight1 citations
1836. On the Fourier analysis in the SO(3) space : the EquiLoPO NetworkPoster1 citations
1837. On the Modeling Capabilities of Large Language Models for Sequential Decision MakingPoster1 citations
1838. On the Transfer of Object-Centric Representation LearningPoster1 citations
1839. Once-for-All: Controllable Generative Image Compression with Dynamic Granularity AdaptationPoster1 citations
1840. One for all and all for one: Efficient computation of partial Wasserstein distances on the linePoster1 citations
1841. Online Reinforcement Learning in Non-Stationary Context-Driven EnvironmentsSpotlight1 citations
1842. Optimal Transport for Time Series ImputationPoster1 citations
1843. Optimality and Adaptivity of Deep Neural Features for Instrumental Variable RegressionPoster1 citations
1844. Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein DesignPoster1 citations
1845. Optimizing Backward Policies in GFlowNets via Trajectory Likelihood MaximizationPoster1 citations
1846. Out-of-distribution Generalization for Total Variation based Invariant Risk MinimizationPoster1 citations
1847. Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution DetectionPoster1 citations
1848. P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKSPoster1 citations
1849. PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement LearningPoster1 citations
1850. POGEMA: A Benchmark Platform for Cooperative Multi-Agent PathfindingPoster1 citations
1851. Pacmann: Efficient Private Approximate Nearest Neighbor SearchPoster1 citations
1852. ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion ModelsPoster1 citations
1853. Parameter Expanded Stochastic Gradient Markov Chain Monte CarloPoster1 citations
1854. Partially Observed Trajectory Inference using Optimal Transport and a Dynamics PriorPoster1 citations
1855. PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction HypothesisPoster1 citations
1856. PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational AutoencodersPoster1 citations
1857. PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano PerformanceSpotlight1 citations
1858. Plastic Learning with Deep Fourier FeaturesPoster1 citations
1859. Poison-splat: Computation Cost Attack on 3D Gaussian SplattingSpotlight1 citations
1860. Policy Decorator: Model-Agnostic Online Refinement for Large Policy ModelPoster1 citations
1861. Polynomial Composition Activations: Unleashing the Dynamics of Large Language ModelsPoster1 citations
1862. PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model PatchesPoster1 citations
1863. Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss FunctionPoster1 citations
1864. Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization FrameworkPoster1 citations
1865. Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple BaselinePoster1 citations
1866. Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language ModelsPoster1 citations
1867. Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-ProbingPoster1 citations
1868. Problem-Parameter-Free Federated LearningOral1 citations
1869. Provable Uncertainty Decomposition via Higher-Order CalibrationSpotlight1 citations
1870. Provable unlearning in topic modeling and downstream tasksPoster1 citations
1871. Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information AmountPoster1 citations
1872. Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution DetectionPoster1 citations
1873. Q-SFT: Q-Learning for Language Models via Supervised Fine-TuningPoster1 citations
1874. Qinco2: Vector Compression and Search with Improved Implicit Neural CodebooksPoster1 citations
1875. Quantum (Inspired) $D^2$-sampling with ApplicationsPoster1 citations
1876. REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New EnvironmentsOral1 citations
1877. REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONSPoster1 citations
1878. REvolve: Reward Evolution with Large Language Models using Human FeedbackPoster1 citations
1879. RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric PerceptionPoster1 citations
1880. RGB-Event ISP: The Dataset and BenchmarkPoster1 citations
1881. RaSA: Rank-Sharing Low-Rank AdaptationPoster1 citations
1882. Random-Set Neural NetworksPoster1 citations
1883. Re-Imagining Multimodal Instruction Tuning: A Representation ViewPoster1 citations
1884. Re-evaluating Open-ended Evaluation of Large Language ModelsPoster1 citations
1885. Real-time design of architectural structures with differentiable mechanics and neural networksPoster1 citations
1886. Realistic Evaluation of Deep Partial-Label Learning AlgorithmsSpotlight1 citations
1887. Recovery of Causal Graph Involving Latent Variables via Homologous SurrogatesPoster1 citations
1888. Reducing Hallucinations in Large Vision-Language Models via Latent Space SteeringSpotlight1 citations
1889. Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic AlignmentPoster1 citations
1890. Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept GenerationPoster1 citations
1891. Regretful Decisions under Label NoisePoster1 citations
1892. Reinforcement Learning from Imperfect Corrective Actions and Proxy RewardsPoster1 citations
1893. Reinforcement learning with combinatorial actions for coupled restless banditsPoster1 citations
1894. RelitLRM: Generative Relightable Radiance for Large Reconstruction ModelsSpotlight1 citations
1895. Rethinking Light Decoder-based Solvers for Vehicle Routing ProblemsPoster1 citations
1896. Rethinking Visual Counterfactual Explanations Through Region ConstraintPoster1 citations
1897. Rethinking the role of frames for SE(3)-invariant crystal structure modelingPoster1 citations
1898. Revealing and Mitigating Over-Attention in Knowledge EditingPoster1 citations
1899. Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned PerturbationsSpotlight1 citations
1900. Revisiting a Design Choice in Gradient Temporal Difference LearningPoster1 citations
1901. Reward Learning from Multiple Feedback TypesPoster1 citations
1902. RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object DetectionPoster1 citations
1903. Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal TransportPoster1 citations
1904. Robust Feature Learning for Multi-Index Models in High DimensionsPoster1 citations
1905. Robust Function-Calling for On-Device Language Model via Function MaskingSpotlight1 citations
1906. Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement LearningPoster1 citations
1907. Robustness Auditing for Linear Regression: To Singularity and BeyondPoster1 citations
1908. SAM-CP: Marrying SAM with Composable Prompts for Versatile SegmentationPoster1 citations
1909. SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental LearningOral1 citations
1910. SEBRA : Debiasing through Self-Guided Bias RankingPoster1 citations
1911. SGD with memory: fundamental properties and stochastic accelerationPoster1 citations
1912. SMI-Editor: Edit-based SMILES Language Model with Fragment-level SupervisionPoster1 citations
1913. SMITE: Segment Me In TimEPoster1 citations
1914. SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEGPoster1 citations
1915. STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy LearningPoster1 citations
1916. Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward HackingPoster1 citations
1917. Scalable Decentralized Learning with TeleportationPoster1 citations
1918. Scalable Decision-Making in Stochastic Environments through Learned Temporal AbstractionSpotlight1 citations
1919. Scalable Mechanistic Neural NetworksPoster1 citations
1920. Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error BarrierSpotlight1 citations
1921. Scaling Optimal LR Across Token HorizonsPoster1 citations
1922. Score-based Self-supervised MRI DenoisingPoster1 citations
1923. Segment Any 3D Object with LanguagePoster1 citations
1924. Self-Supervised Diffusion MRI Denoising via Iterative and Stable RefinementPoster1 citations
1925. Sensor-Invariant Tactile RepresentationPoster1 citations
1926. Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced ReasoningPoster1 citations
1927. Severing Spurious Correlations with Data PruningSpotlight1 citations
1928. Shh, don't say that! Domain Certification in LLMsPoster1 citations
1929. SimpleTM: A Simple Baseline for Multivariate Time Series ForecastingPoster1 citations
1930. Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent LearningPoster1 citations
1931. Singular Subspace Perturbation Bounds via Rectangular Random Matrix DiffusionsPoster1 citations
1932. Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal NoisesPoster1 citations
1933. Solving New Tasks by Adapting Internet Video KnowledgePoster1 citations
1934. Solving hidden monotone variational inequalities with surrogate lossesPoster1 citations
1935. SonicSim: A customizable simulation platform for speech processing in moving sound source scenariosPoster1 citations
1936. SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited LabelsPoster1 citations
1937. Sparse Autoencoders Do Not Find Canonical Units of AnalysisPoster1 citations
1938. Sparse Learning for State Space Models on MobilePoster1 citations
1939. Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent FlowsPoster1 citations
1940. Spherical Tree-Sliced Wasserstein DistancePoster1 citations
1941. Spiking Vision Transformer with Saccadic AttentionPoster1 citations
1942. SplatFormer: Point Transformer for Robust 3D Gaussian SplattingSpotlight1 citations
1943. Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in SportsPoster1 citations
1944. Spreading Out-of-Distribution Detection on GraphsPoster1 citations
1945. Spurious Forgetting in Continual Learning of Language ModelsPoster1 citations
1946. Stabilized Neural Prediction of Potential Outcomes in Continuous TimePoster1 citations
1947. Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte CarloPoster1 citations
1948. Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function ApproximationPoster1 citations
1949. Structural-Entropy-Based Sample Selection for Efficient and Effective LearningPoster1 citations
1950. Student-Informed Teacher TrainingSpotlight1 citations
1951. Subgraph Federated Learning for Local GeneralizationOral1 citations
1952. SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head AvatarsPoster1 citations
1953. Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scenePoster1 citations
1954. Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task LearningPoster1 citations
1955. Sylber: Syllabic Embedding Representation of Speech from Raw AudioPoster1 citations
1956. Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description lengthPoster1 citations
1957. SynFlowNet: Design of Diverse and Novel Molecules with Synthesis ConstraintsSpotlight1 citations
1958. SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuningPoster1 citations
1959. Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone EnsemblingPoster1 citations
1960. Systematic Outliers in Large Language ModelsPoster1 citations
1961. Systematic Relational Reasoning With Epistemic Graph Neural NetworksPoster1 citations
1962. TASAR: Transfer-based Attack on Skeletal Action RecognitionPoster1 citations
1963. TEASER: Token Enhanced Spatial Modeling for Expressions ReconstructionPoster1 citations
1964. TODO: Enhancing LLM Alignment with Ternary PreferencesPoster1 citations
1965. TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement LearningSpotlight1 citations
1966. Test-time Adaptation for Image Compression with Distribution RegularizationPoster1 citations
1967. Test-time Alignment of Diffusion Models without Reward Over-optimizationSpotlight1 citations
1968. The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired ModalitiesPoster1 citations
1969. The Computational Complexity of Circuit Discovery for Inner InterpretabilitySpotlight1 citations
1970. The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text GenerationPoster1 citations
1971. The KoLMogorov Test: Compression by Code GenerationPoster1 citations
1972. The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language ModelPoster1 citations
1973. The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and ModalitiesPoster1 citations
1974. The Utility and Complexity of In- and Out-of-Distribution Machine UnlearningPoster1 citations
1975. Tight Clusters Make Specialized ExpertsPoster1 citations
1976. Time-to-Event Pretraining for 3D Medical ImagingPoster1 citations
1977. TimeInf: Time Series Data Contribution via Influence FunctionsPoster1 citations
1978. Token Statistics Transformer: Linear-Time Attention via Variational Rate ReductionSpotlight1 citations
1979. Topological Schrödinger Bridge MatchingSpotlight1 citations
1980. Toward Exploratory Inverse Constraint Inference with Generative Diffusion VerifiersPoster1 citations
1981. Toward Generalizing Visual Brain Decoding to Unseen SubjectsPoster1 citations
1982. Toward Understanding In-context vs. In-weight LearningPoster1 citations
1983. Towards Automated Knowledge Integration From Human-Interpretable RepresentationsSpotlight1 citations
1984. Towards Bridging Generalization and Expressivity of Graph Neural NetworksPoster1 citations
1985. Towards Calibrated Deep Clustering NetworkPoster1 citations
1986. Towards General-Purpose Model-Free Reinforcement LearningSpotlight1 citations
1987. Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive RepresentationsPoster1 citations
1988. Towards Hierarchical Rectified FlowPoster1 citations
1989. Towards Out-of-Modal Generalization without Instance-level Modal CorrespondencePoster1 citations
1990. Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware OptimizationPoster1 citations
1991. Towards Unified Human Motion-Language Understanding via Sparse Interpretable CharacterizationPoster1 citations
1992. Towards a learning theory of representation alignmentPoster1 citations
1993. Tracking objects that change in appearance with phase synchronyPoster1 citations
1994. Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial ImagesPoster1 citations
1995. Training Free Guided Flow-Matching with Optimal ControlPoster1 citations
1996. Training Language Models on Synthetic Edit Sequences Improves Code SynthesisPoster1 citations
1997. Training Neural Networks as Recognizers of Formal LanguagesPoster1 citations
1998. Transformers Struggle to Learn to SearchPoster1 citations
1999. Tree of Attributes Prompt Learning for Vision-Language ModelsPoster1 citations
2000. UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language ModelsPoster1 citations

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