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.

1. KAN: Kolmogorov–Arnold NetworksOral1,156 citations
2. SAM 2: Segment Anything in Images and VideosOral846 citations
3. WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-InstructOral414 citations
4. CogVideoX: Text-to-Video Diffusion Models with An Expert TransformerPoster383 citations
5. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for CodePoster224 citations
6. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsPoster209 citations
7. Show-o: One Single Transformer to Unify Multimodal Understanding and GenerationPoster164 citations
8. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive AttacksPoster161 citations
9. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding ModelsSpotlight158 citations
10. MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelsPoster152 citations
11. Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal ModelOral150 citations
12. Scaling and evaluating sparse autoencodersOral138 citations
13. Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP ResearchersPoster127 citations
14. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex InstructionsOral114 citations
15. Generative Representational Instruction TuningPoster113 citations
16. Training Language Models to Self-Correct via Reinforcement LearningOral113 citations
17. Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with NothingPoster111 citations
18. Generative Verifiers: Reward Modeling as Next-Token PredictionPoster107 citations
19. JudgeLM: Fine-tuned Large Language Models are Scalable JudgesSpotlight107 citations
20. Self-Play Preference Optimization for Language Model AlignmentPoster105 citations
21. mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language ModelsPoster101 citations
22. Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language ModelsOral100 citations
23. Advancing LLM Reasoning Generalists with Preference TreesPoster92 citations
24. Mixture-of-Agents Enhances Large Language Model CapabilitiesSpotlight90 citations
25. The Unreasonable Ineffectiveness of the Deeper LayersPoster90 citations
26. SpinQuant: LLM Quantization with Learned RotationsPoster87 citations
27. To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningPoster80 citations
28. Depth Pro: Sharp Monocular Metric Depth in Less Than a SecondPoster77 citations
29. Physics of Language Models: Part 3.2, Knowledge ManipulationPoster76 citations
30. Deconstructing Denoising Diffusion Models for Self-Supervised LearningPoster75 citations
31. MonST3R: A Simple Approach for Estimating Geometry in the Presence of MotionSpotlight68 citations
32. VILA-U: a Unified Foundation Model Integrating Visual Understanding and GenerationPoster67 citations
33. LongVILA: Scaling Long-Context Visual Language Models for Long VideosPoster65 citations
34. RDT-1B: a Diffusion Foundation Model for Bimanual ManipulationPoster65 citations
35. RouteLLM: Learning to Route LLMs from Preference DataPoster63 citations
36. OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video GenerationPoster62 citations
37. Physics of Language Models: Part 3.3, Knowledge Capacity Scaling LawsSpotlight62 citations
38. Pyramidal Flow Matching for Efficient Video Generative ModelingPoster62 citations
39. LLaMA-Omni: Seamless Speech Interaction with Large Language ModelsPoster61 citations
40. Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of EncodersSpotlight59 citations
41. Rewarding Progress: Scaling Automated Process Verifiers for LLM ReasoningSpotlight59 citations
42. Towards Semantic Equivalence of Tokenization in Multimodal LLMPoster59 citations
43. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous AgentsPoster58 citations
44. Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ThinkOral58 citations
45. Eliciting Human Preferences with Language ModelsPoster57 citations
46. On the self-verification limitations of large language models on reasoning and planning tasksPoster57 citations
47. Safety Alignment Should be Made More Than Just a Few Tokens DeepOral57 citations
48. Automated Design of Agentic SystemsPoster56 citations
49. Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary ResolutionPoster56 citations
50. Vision-LSTM: xLSTM as Generic Vision BackbonePoster56 citations
51. Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like ArchitecturesSpotlight53 citations
52. Diffusion Models Are Real-Time Game EnginesPoster52 citations
53. MUSE: Machine Unlearning Six-Way Evaluation for Language ModelsPoster52 citations
54. MuirBench: A Comprehensive Benchmark for Robust Multi-image UnderstandingPoster52 citations
55. Retrieval Head Mechanistically Explains Long-Context FactualityOral51 citations
56. Mutual Reasoning Makes Smaller LLMs Stronger Problem-SolverPoster50 citations
57. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language ModelsPoster50 citations
58. Repetition Improves Language Model EmbeddingsPoster50 citations
59. Justice or Prejudice? Quantifying Biases in LLM-as-a-JudgePoster49 citations
60. World Model on Million-Length Video And Language With Blockwise RingAttentionPoster47 citations
61. Differential TransformerOral44 citations
62. ColPali: Efficient Document Retrieval with Vision Language ModelsPoster43 citations
63. Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language ModelingPoster43 citations
64. AFlow: Automating Agentic Workflow GenerationOral41 citations
65. MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?Poster41 citations
66. OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction DataPoster41 citations
67. Kolmogorov-Arnold TransformerPoster40 citations
68. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI AgentsOral40 citations
69. Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling PerformancePoster39 citations
70. SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion TransformersOral39 citations
71. Improved Techniques for Optimization-Based Jailbreaking on Large Language ModelsPoster38 citations
72. LLM-SR: Scientific Equation Discovery via Programming with Large Language ModelsOral38 citations
73. VD3D: Taming Large Video Diffusion Transformers for 3D Camera ControlPoster38 citations
74. Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHFPoster37 citations
75. MeshAnything: Artist-Created Mesh Generation with Autoregressive TransformersPoster37 citations
76. SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model CompressionPoster37 citations
77. WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language ModelingPoster37 citations
78. AgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsPoster36 citations
79. CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLPoster36 citations
80. Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative IntelligenceSpotlight36 citations
81. SafeDiffuser: Safe Planning with Diffusion Probabilistic ModelsPoster36 citations
82. VideoPhy: Evaluating Physical Commonsense for Video GenerationPoster36 citations
83. Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous TokensPoster35 citations
84. Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning ProcessPoster35 citations
85. DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsPoster34 citations
86. JudgeBench: A Benchmark for Evaluating LLM-Based JudgesPoster34 citations
87. MotionClone: Training-Free Motion Cloning for Controllable Video GenerationPoster34 citations
88. SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View ConsistencyPoster34 citations
89. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language ModelsOral33 citations
90. Data Scaling Laws in Imitation Learning for Robotic ManipulationOral33 citations
91. EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGEPoster33 citations
92. Lotus: Diffusion-based Visual Foundation Model for High-quality Dense PredictionPoster33 citations
93. Matryoshka Multimodal ModelsPoster33 citations
94. Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal SamplingPoster33 citations
95. Diffusion Policy Policy OptimizationPoster32 citations
96. HelpSteer2-Preference: Complementing Ratings with PreferencesPoster32 citations
97. OpenHands: An Open Platform for AI Software Developers as Generalist AgentsPoster32 citations
98. Adam-mini: Use Fewer Learning Rates To Gain MorePoster31 citations
99. AgentStudio: A Toolkit for Building General Virtual AgentsPoster31 citations
100. HART: Efficient Visual Generation with Hybrid Autoregressive TransformerPoster31 citations
101. MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec TransformerPoster31 citations
102. The Geometry of Categorical and Hierarchical Concepts in Large Language ModelsOral31 citations
103. Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHFPoster31 citations
104. Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal ControlSpotlight30 citations
105. Language models scale reliably with over-training and on downstream tasksPoster30 citations
106. MLE-bench: Evaluating Machine Learning Agents on Machine Learning EngineeringOral30 citations
107. Tamper-Resistant Safeguards for Open-Weight LLMsPoster30 citations
108. Towards Principled Evaluations of Sparse Autoencoders for Interpretability and ControlPoster30 citations
109. Does Refusal Training in LLMs Generalize to the Past Tense?Poster29 citations
110. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language ModelPoster29 citations
111. HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion ModelsPoster29 citations
112. Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion DependencyOral29 citations
113. MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuningPoster29 citations
114. MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout GuidancePoster29 citations
115. OS-ATLAS: Foundation Action Model for Generalist GUI AgentsSpotlight29 citations
116. Deep Compression Autoencoder for Efficient High-Resolution Diffusion ModelsPoster28 citations
117. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMsPoster28 citations
118. MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language ModelsPoster28 citations
119. MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for MedicinePoster27 citations
120. Planning in Natural Language Improves LLM Search for Code GenerationSpotlight27 citations
121. RegMix: Data Mixture as Regression for Language Model Pre-trainingSpotlight27 citations
122. A Decade's Battle on Dataset Bias: Are We There Yet?Oral26 citations
123. BOND: Aligning LLMs with Best-of-N DistillationPoster26 citations
124. Learn Your Reference Model for Real Good AlignmentPoster26 citations
125. Real-Time Video Generation with Pyramid Attention BroadcastPoster26 citations
126. Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language ModelsSpotlight26 citations
127. DreamBench++: A Human-Aligned Benchmark for Personalized Image GenerationPoster25 citations
128. Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation SystemsPoster25 citations
129. Inference Scaling for Long-Context Retrieval Augmented GenerationOral25 citations
130. Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with ChecklistPoster25 citations
131. MMAU: A Massive Multi-Task Audio Understanding and Reasoning BenchmarkSpotlight25 citations
132. Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference ModelsPoster25 citations
133. RNNs are not Transformers (Yet): The Key Bottleneck on In-Context RetrievalPoster25 citations
134. Unlocking Guidance for Discrete State-Space Diffusion and Flow ModelsPoster25 citations
135. Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based AgentsPoster24 citations
136. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive RetrievalSpotlight24 citations
137. Building Math Agents with Multi-Turn Iterative Preference LearningPoster24 citations
138. Language Models Learn to Mislead Humans via RLHFPoster24 citations
139. Lean-STaR: Learning to Interleave Thinking and ProvingSpotlight24 citations
140. Making Text Embedders Few-Shot LearnersPoster24 citations
141. MovieDreamer: Hierarchical Generation for Coherent Long Visual SequencesPoster24 citations
142. Scaling Laws for PrecisionOral24 citations
143. Training-free Camera Control for Video GenerationPoster24 citations
144. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality DocumentsPoster24 citations
145. A Sanity Check for AI-generated Image DetectionPoster23 citations
146. Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language ModelsPoster23 citations
147. RazorAttention: Efficient KV Cache Compression Through Retrieval HeadsPoster23 citations
148. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?Poster23 citations
149. Simplifying, Stabilizing and Scaling Continuous-time Consistency ModelsOral23 citations
150. ToolACE: Winning the Points of LLM Function CallingPoster23 citations
151. Agent S: An Open Agentic Framework that Uses Computers Like a HumanPoster22 citations
152. Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?Poster22 citations
153. EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh GenerationPoster22 citations
154. Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion ModelSpotlight22 citations
155. Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot VideosPoster22 citations
156. Test of Time: A Benchmark for Evaluating LLMs on Temporal ReasoningPoster22 citations
157. Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of ExpertsSpotlight22 citations
158. ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video GenerationPoster22 citations
159. AI Sandbagging: Language Models can Strategically Underperform on EvaluationsPoster21 citations
160. AlphaEdit: Null-Space Constrained Knowledge Editing for Language ModelsOral21 citations
161. Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion ModelOral21 citations
162. DiscoveryBench: Towards Data-Driven Discovery with Large Language ModelsPoster21 citations
163. Image and Video Tokenization with Binary Spherical QuantizationPoster21 citations
164. LLaRA: Supercharging Robot Learning Data for Vision-Language PolicyPoster21 citations
165. MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative DecodingPoster21 citations
166. Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical SamplingPoster21 citations
167. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific DiscoveryPoster21 citations
168. Weak to Strong Generalization for Large Language Models with Multi-capabilitiesPoster21 citations
169. gRNAde: Geometric Deep Learning for 3D RNA inverse designSpotlight21 citations
170. Do LLM Agents Have Regret? A Case Study in Online Learning and GamesPoster20 citations
171. FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language ModelsPoster20 citations
172. ImageFolder: Autoregressive Image Generation with Folded TokensPoster20 citations
173. Latent Action Pretraining from VideosPoster20 citations
174. MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data EnginePoster20 citations
175. McEval: Massively Multilingual Code EvaluationPoster20 citations
176. No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed ImagesOral20 citations
177. Physics-Informed Diffusion ModelsPoster20 citations
178. SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationPoster20 citations
179. Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsOral20 citations
180. Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean DataPoster20 citations
181. AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationPoster19 citations
182. Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence AnalysisPoster19 citations
183. AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMsSpotlight19 citations
184. Bootstrapping Language Models with DPO Implicit RewardsPoster19 citations
185. Consistency Models Made EasyPoster19 citations
186. Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts ModelsPoster19 citations
187. Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image AnimationPoster19 citations
188. LLMs Know More Than They Show: On the Intrinsic Representation of LLM HallucinationsPoster19 citations
189. Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGPoster19 citations
190. NVS-Solver: Video Diffusion Model as Zero-Shot Novel View SynthesizerPoster19 citations
191. Semantic Image Inversion and Editing using Rectified Stochastic Differential EquationsPoster19 citations
192. Strong Model CollapseSpotlight19 citations
193. AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic ManipulationPoster18 citations
194. CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlSpotlight18 citations
195. CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsPoster18 citations
196. DEEM: Diffusion models serve as the eyes of large language models for image perceptionSpotlight18 citations
197. Diffusion Feedback Helps CLIP See BetterPoster18 citations
198. Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language ModelsPoster18 citations
199. LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Spotlight18 citations
200. MindSearch: Mimicking Human Minds Elicits Deep AI SearcherPoster18 citations
201. SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion ModelsSpotlight18 citations
202. Safety Layers in Aligned Large Language Models: The Key to LLM SecurityPoster18 citations
203. Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language ModelsPoster18 citations
204. ThinK: Thinner Key Cache by Query-Driven PruningSpotlight18 citations
205. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding TasksPoster18 citations
206. 4K4DGen: Panoramic 4D Generation at 4K ResolutionSpotlight17 citations
207. Arithmetic Without Algorithms: Language Models Solve Math with a Bag of HeuristicsPoster17 citations
208. CFG++: Manifold-constrained Classifier Free Guidance for Diffusion ModelsPoster17 citations
209. Chain-of-Action: Faithful and Multimodal Question Answering through Large Language ModelsPoster17 citations
210. ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code GenerationPoster17 citations
211. Controlling Space and Time with Diffusion ModelsPoster17 citations
212. LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenPoster17 citations
213. Large Language Models Assume People are More Rational than We Really arePoster17 citations
214. Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety TuningPoster17 citations
215. MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language ModelsPoster17 citations
216. Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image SynthesisPoster17 citations
217. Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and AdaptivityPoster17 citations
218. PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial OptimizationPoster17 citations
219. RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and StyleOral17 citations
220. Simplifying Deep Temporal Difference LearningSpotlight17 citations
221. T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory StitchingPoster17 citations
222. T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance DesignPoster17 citations
223. Visual Agents as Fast and Slow ThinkersPoster17 citations
224. WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the WildSpotlight17 citations
225. 3D Vision-Language Gaussian SplattingPoster16 citations
226. Accelerating Inference of Retrieval-Augmented Generation via Sparse Context SelectionPoster16 citations
227. BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation ExperimentsPoster16 citations
228. Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent SystemsPoster16 citations
229. D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution RefinementSpotlight16 citations
230. DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language ModelsPoster16 citations
231. FreDF: Learning to Forecast in the Frequency DomainPoster16 citations
232. OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in CodePoster16 citations
233. OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with TextSpotlight16 citations
234. OmniRe: Omni Urban Scene ReconstructionSpotlight16 citations
235. One Step Diffusion via Shortcut ModelsOral16 citations
236. Regularization by Texts for Latent Diffusion Inverse SolversSpotlight16 citations
237. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference AccelerationPoster16 citations
238. Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order OptimizerPoster16 citations
239. $R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical ReasoningSpotlight15 citations
240. Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi DecodingPoster15 citations
241. Diffusion-based Neural Network Weights GenerationPoster15 citations
242. Dynamic Diffusion TransformerPoster15 citations
243. Gated Delta Networks: Improving Mamba2 with Delta RulePoster15 citations
244. Language-Image Models with 3D UnderstandingPoster15 citations
245. Machine Unlearning Fails to Remove Data Poisoning AttacksPoster15 citations
246. On the expressiveness and spectral bias of KANsPoster15 citations
247. Process Reward Model with Q-value RankingsPoster15 citations
248. Rectified Diffusion: Straightness Is Not Your Need in Rectified FlowPoster15 citations
249. Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented GenerationPoster15 citations
250. Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A BenchmarkPoster15 citations
251. Variational Best-of-N AlignmentPoster15 citations
252. Animate-X: Universal Character Image Animation with Enhanced Motion RepresentationPoster14 citations
253. Backtracking Improves Generation SafetyOral14 citations
254. ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG CapabilitiesPoster14 citations
255. EG4D: Explicit Generation of 4D Object without Score DistillationPoster14 citations
256. Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and EfficiencyPoster14 citations
257. Improving Pretraining Data Using Perplexity CorrelationsPoster14 citations
258. Is In-Context Learning Sufficient for Instruction Following in LLMs?Poster14 citations
259. MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMsPoster14 citations
260. MagicPIG: LSH Sampling for Efficient LLM GenerationSpotlight14 citations
261. On the Relation between Trainability and Dequantization of Variational Quantum Learning ModelsPoster14 citations
262. Pangea: A Fully Open Multilingual Multimodal LLM for 39 LanguagesPoster14 citations
263. Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language ModelsPoster14 citations
264. Round and Round We Go! What makes Rotary Positional Encodings useful?Poster14 citations
265. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative RefinementPoster14 citations
266. Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic ProcessesSpotlight14 citations
267. Towards Realistic Data Generation for Real-World Super-ResolutionPoster14 citations
268. AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web AgentsPoster13 citations
269. An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual PixelsPoster13 citations
270. Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning AgentPoster13 citations
271. CBQ: Cross-Block Quantization for Large Language ModelsSpotlight13 citations
272. Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference OptimizationSpotlight13 citations
273. Depth Any Video with Scalable Synthetic DataPoster13 citations
274. Dissecting Adversarial Robustness of Multimodal LM AgentsPoster13 citations
275. DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control AgentPoster13 citations
276. GameGen-X: Interactive Open-world Game Video GenerationPoster13 citations
277. GoodDrag: Towards Good Practices for Drag Editing with Diffusion ModelsPoster13 citations
278. Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation ModelsPoster13 citations
279. Learning How Hard to Think: Input-Adaptive Allocation of LM ComputationPoster13 citations
280. MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in VideosPoster13 citations
281. MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model EvaluationPoster13 citations
282. Scaling Large Language Model-based Multi-Agent CollaborationPoster13 citations
283. Speculative RAG: Enhancing Retrieval Augmented Generation through DraftingPoster13 citations
284. TestGenEval: A Real World Unit Test Generation and Test Completion BenchmarkPoster13 citations
285. Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful PerturbationOral12 citations
286. CEB: Compositional Evaluation Benchmark for Fairness in Large Language ModelsSpotlight12 citations
287. DPLM-2: A Multimodal Diffusion Protein Language ModelPoster12 citations
288. DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchPoster12 citations
289. Eliminating Position Bias of Language Models: A Mechanistic ApproachPoster12 citations
290. EmbodiedSAM: Online Segment Any 3D Thing in Real TimeOral12 citations
291. Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language ModelsPoster12 citations
292. Fantastic Copyrighted Beasts and How (Not) to Generate ThemPoster12 citations
293. Graph Sparsification via Mixture of GraphsSpotlight12 citations
294. Hymba: A Hybrid-head Architecture for Small Language ModelsSpotlight12 citations
295. Interpreting and Editing Vision-Language Representations to Mitigate HallucinationsPoster12 citations
296. IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image GenerationPoster12 citations
297. Large Scale Knowledge WashingPoster12 citations
298. Long Context Compression with Activation BeaconPoster12 citations
299. MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific HypothesesPoster12 citations
300. Multiagent Finetuning: Self Improvement with Diverse Reasoning ChainsPoster12 citations
301. O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal AssumptionsPoster12 citations
302. On Targeted Manipulation and Deception when Optimizing LLMs for User FeedbackPoster12 citations
303. Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human ratingSpotlight12 citations
304. SG-I2V: Self-Guided Trajectory Control in Image-to-Video GenerationPoster12 citations
305. Sequential Controlled Langevin DiffusionsPoster12 citations
306. Tighter Privacy Auditing of DP-SGD in the Hidden State Threat ModelPoster12 citations
307. Towards Interpreting Visual Information Processing in Vision-Language ModelsPoster12 citations
308. Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and MethodologyPoster12 citations
309. Training on the Test Task Confounds Evaluation and EmergenceOral12 citations
310. VisualAgentBench: Towards Large Multimodal Models as Visual Foundation AgentsPoster12 citations
311. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web NavigationPoster12 citations
312. A New Perspective on Shampoo's PreconditionerPoster11 citations
313. ALLaM: Large Language Models for Arabic and EnglishPoster11 citations
314. Adaptive Data Optimization: Dynamic Sample Selection with Scaling LawsPoster11 citations
315. Adversarial Search Engine Optimization for Large Language ModelsPoster11 citations
316. AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web TutorialsSpotlight11 citations
317. Autoregressive Video Generation without Vector QuantizationPoster11 citations
318. Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual UnderstandingPoster11 citations
319. CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency PatchingPoster11 citations
320. Can Large Language Models Understand Symbolic Graphics Programs?Spotlight11 citations
321. Cheating Automatic LLM Benchmarks: Null Models Achieve High Win RatesOral11 citations
322. Combining Induction and Transduction for Abstract ReasoningPoster11 citations
323. ControlAR: Controllable Image Generation with Autoregressive ModelsPoster11 citations
324. Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning TracesPoster11 citations
325. Enhancing End-to-End Autonomous Driving with Latent World ModelPoster11 citations
326. InstantSwap: Fast Customized Concept Swapping across Sharp Shape DifferencesPoster11 citations
327. Intent3D: 3D Object Detection in RGB-D Scans Based on Human IntentionPoster11 citations
328. Inverse Constitutional AI: Compressing Preferences into PrinciplesPoster11 citations
329. LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge DistillationPoster11 citations
330. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryPoster11 citations
331. MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language ModelsPoster11 citations
332. MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language ModelsOral11 citations
333. OGBench: Benchmarking Offline Goal-Conditioned RLPoster11 citations
334. OmniBind: Large-scale Omni Multimodal Representation via Binding SpacesPoster11 citations
335. On Scaling Up 3D Gaussian Splatting TrainingOral11 citations
336. PersonalLLM: Tailoring LLMs to Individual PreferencesPoster11 citations
337. Perturbation-Restrained Sequential Model EditingPoster11 citations
338. Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math ProblemsPoster11 citations
339. PivotMesh: Generic 3D Mesh Generation via Pivot Vertices GuidancePoster11 citations
340. Predictive Inverse Dynamics Models are Scalable Learners for Robotic ManipulationOral11 citations
341. Progress or Regress? Self-Improvement Reversal in Post-trainingPoster11 citations
342. RepoGraph: Enhancing AI Software Engineering with Repository-level Code GraphPoster11 citations
343. SORRY-Bench: Systematically Evaluating Large Language Model Safety RefusalPoster11 citations
344. Synthetic continued pretrainingOral11 citations
345. System 1.x: Learning to Balance Fast and Slow Planning with Language ModelsPoster11 citations
346. TRACE: Temporal Grounding Video LLM via Causal Event ModelingPoster11 citations
347. Theory, Analysis, and Best Practices for Sigmoid Self-AttentionPoster11 citations
348. Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference OptimizationPoster11 citations
349. Training-Free Activation Sparsity in Large Language ModelsSpotlight11 citations
350. Transformers are Universal In-context LearnersPoster11 citations
351. Why Does the Effective Context Length of LLMs Fall Short?Poster11 citations
352. 3D-Properties: Identifying Challenges in DPO and Charting a Path ForwardPoster10 citations
353. A Closer Look at Machine Unlearning for Large Language ModelsPoster10 citations
354. A Transfer Attack to Image WatermarksPoster10 citations
355. ACE: All-round Creator and Editor Following Instructions via Diffusion TransformerPoster10 citations
356. ConFIG: Towards Conflict-free Training of Physics Informed Neural NetworksSpotlight10 citations
357. DeciMamba: Exploring the Length Extrapolation Potential of MambaPoster10 citations
358. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering AgentsPoster10 citations
359. Do I Know This Entity? Knowledge Awareness and Hallucinations in Language ModelsOral10 citations
360. Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You WantPoster10 citations
361. Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer ModelsPoster10 citations
362. Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context SparsificationPoster10 citations
363. Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 TasksPoster10 citations
364. Efficient Alternating Minimization with Applications to Weighted Low Rank ApproximationPoster10 citations
365. EffoVPR: Effective Foundation Model Utilization for Visual Place RecognitionPoster10 citations
366. Energy-Based Diffusion Language Models for Text GenerationPoster10 citations
367. Ensembling Diffusion Models via Adaptive Feature AggregationPoster10 citations
368. GraphRouter: A Graph-based Router for LLM SelectionsPoster10 citations
369. How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral FrameworkPoster10 citations
370. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-SolvingPoster10 citations
371. MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMSPoster10 citations
372. MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly DetectionPoster10 citations
373. Mixture of In-Context Prompters for Tabular PFNsPoster10 citations
374. MuPT: A Generative Symbolic Music Pretrained TransformerPoster10 citations
375. OSCAR: Operating System Control via State-Aware Reasoning and Re-PlanningPoster10 citations
376. OmniEdit: Building Image Editing Generalist Models Through Specialist SupervisionPoster10 citations
377. On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax OptimalityPoster10 citations
378. PAD: Personalized Alignment of LLMs at Decoding-timePoster10 citations
379. PnP-Flow: Plug-and-Play Image Restoration with Flow MatchingPoster10 citations
380. Programming Refusal with Conditional Activation SteeringSpotlight10 citations
381. Scaling FP8 training to trillion-token LLMsSpotlight10 citations
382. Scaling Transformers for Low-Bitrate High-Quality Speech CodingPoster10 citations
383. Self-Evolving Multi-Agent Collaboration Networks for Software DevelopmentPoster10 citations
384. Self-MoE: Towards Compositional Large Language Models with Self-Specialized ExpertsPoster10 citations
385. Stable Segment Anything ModelPoster10 citations
386. Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong GeneralizationPoster10 citations
387. SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-CorrectionPoster10 citations
388. SymmCD: Symmetry-Preserving Crystal Generation with Diffusion ModelsPoster10 citations
389. TabM: Advancing tabular deep learning with parameter-efficient ensemblingPoster10 citations
390. Taming Overconfidence in LLMs: Reward Calibration in RLHFPoster10 citations
391. Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented GenerationPoster10 citations
392. TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningPoster10 citations
393. Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy HessiansPoster10 citations
394. U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical ModelsPoster10 citations
395. 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video GenerationPoster9 citations
396. Adversarial Perturbations Cannot Reliably Protect Artists From Generative AISpotlight9 citations
397. Agents' Room: Narrative Generation through Multi-step CollaborationPoster9 citations
398. Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual BanditsPoster9 citations
399. Autoregressive Pretraining with Mamba in VisionPoster9 citations
400. BALROG: Benchmarking Agentic LLM and VLM Reasoning On GamesPoster9 citations
401. Beyond Autoregression: Discrete Diffusion for Complex Reasoning and PlanningPoster9 citations
402. Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language ModelsSpotlight9 citations
403. COMBO: Compositional World Models for Embodied Multi-Agent CooperationPoster9 citations
404. Can Knowledge Editing Really Correct Hallucinations?Poster9 citations
405. CycleResearcher: Improving Automated Research via Automated ReviewPoster9 citations
406. Data Shapley in One Training RunOral9 citations
407. Differentiable Optimization of Similarity Scores Between Models and BrainsPoster9 citations
408. Diffusion Bridge Implicit ModelsPoster9 citations
409. Does Spatial Cognition Emerge in Frontier Models?Poster9 citations
410. Emergence of a High-Dimensional Abstraction Phase in Language TransformersPoster9 citations
411. ForecastBench: A Dynamic Benchmark of AI Forecasting CapabilitiesPoster9 citations
412. FreeVS: Generative View Synthesis on Free Driving TrajectoryPoster9 citations
413. GOFA: A Generative One-For-All Model for Joint Graph Language ModelingPoster9 citations
414. Grounding Continuous Representations in Geometry: Equivariant Neural FieldsPoster9 citations
415. INCLUDE: Evaluating Multilingual Language Understanding with Regional KnowledgeSpotlight9 citations
416. Improved Convergence Rate for Diffusion Probabilistic ModelsSpotlight9 citations
417. Improving Instruction-Following in Language Models through Activation SteeringPoster9 citations
418. InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized RationalesPoster9 citations
419. LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative DecodingPoster9 citations
420. MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal ModelsPoster9 citations
421. MeteoRA: Multiple-tasks Embedded LoRA for Large Language ModelsPoster9 citations
422. OLMoE: Open Mixture-of-Experts Language ModelsOral9 citations
423. On Evaluating the Durability of Safeguards for Open-Weight LLMsPoster9 citations
424. PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language InstructionsPoster9 citations
425. PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object DetectionPoster9 citations
426. Preble: Efficient Distributed Prompt Scheduling for LLM ServingPoster9 citations
427. Procedural Knowledge in Pretraining Drives Reasoning in Large Language ModelsPoster9 citations
428. Real2Code: Reconstruct Articulated Objects via Code GenerationPoster9 citations
429. Robust LLM safeguarding via refusal feature adversarial trainingPoster9 citations
430. SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATIONSpotlight9 citations
431. STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMsPoster9 citations
432. Scalable Extraction of Training Data from Aligned, Production Language ModelsPoster9 citations
433. ShortcutsBench: A Large-Scale Real-world Benchmark for API-based AgentsPoster9 citations
434. Simple Guidance Mechanisms for Discrete Diffusion ModelsPoster9 citations
435. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information StructurizationPoster9 citations
436. TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion InterpolationOral9 citations
437. TempMe: Video Temporal Token Merging for Efficient Text-Video RetrievalPoster9 citations
438. The AdEMAMix Optimizer: Better, Faster, OlderPoster9 citations
439. Theory on Mixture-of-Experts in Continual LearningSpotlight9 citations
440. TimeMixer++: A General Time Series Pattern Machine for Universal Predictive AnalysisOral9 citations
441. Can LLMs Solve Longer Math Word Problems Better?Poster8 citations
442. Can LLMs Understand Time Series Anomalies?Poster8 citations
443. Deep Learning Alternatives Of The Kolmogorov Superposition TheoremSpotlight8 citations
444. DisPose: Disentangling Pose Guidance for Controllable Human Image AnimationPoster8 citations
445. E(n) Equivariant Topological Neural NetworksPoster8 citations
446. Efficient stagewise pretraining via progressive subnetworksPoster8 citations
447. ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory LearningPoster8 citations
448. Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation ModelsPoster8 citations
449. First-Person Fairness in ChatbotsSpotlight8 citations
450. Frame-Voyager: Learning to Query Frames for Video Large Language ModelsPoster8 citations
451. GOAL: A Generalist Combinatorial Optimization Agent LearnerPoster8 citations
452. GenXD: Generating Any 3D and 4D ScenesPoster8 citations
453. GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-trainingPoster8 citations
454. Group Distributionally Robust Dataset Distillation with Risk MinimizationPoster8 citations
455. Harnessing Diversity for Important Data Selection in Pretraining Large Language ModelsSpotlight8 citations
456. Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language ModelsPoster8 citations
457. Improving Equivariant Networks with Probabilistic Symmetry BreakingPoster8 citations
458. Instruct-SkillMix: A Powerful Pipeline for LLM Instruction TuningPoster8 citations
459. Interleaved Scene Graphs for Interleaved Text-and-Image Generation AssessmentSpotlight8 citations
460. Interpreting the Second-Order Effects of Neurons in CLIPPoster8 citations
461. LARP: Tokenizing Videos with a Learned Autoregressive Generative PriorOral8 citations
462. LVSM: A Large View Synthesis Model with Minimal 3D Inductive BiasOral8 citations
463. LaGeM: A Large Geometry Model for 3D Representation Learning and DiffusionPoster8 citations
464. LeanAgent: Lifelong Learning for Formal Theorem ProvingPoster8 citations
465. Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic EnvironmentsPoster8 citations
466. Learning Dynamics of LLM FinetuningOral8 citations
467. Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-TrainingPoster8 citations
468. LoLCATs: On Low-Rank Linearizing of Large Language ModelsPoster8 citations
469. Looking Backward: Streaming Video-to-Video Translation with Feature BanksPoster8 citations
470. Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusionPoster8 citations
471. Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention CausalityPoster8 citations
472. Model merging with SVD to tie the KnotsPoster8 citations
473. Monitoring Latent World States in Language Models with Propositional ProbesSpotlight8 citations
474. Motion-Agent: A Conversational Framework for Human Motion Generation with LLMsPoster8 citations
475. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World UnderstandingOral8 citations
476. Point-SAM: Promptable 3D Segmentation Model for Point CloudsPoster8 citations
477. Preference Optimization for Reasoning with Pseudo FeedbackSpotlight8 citations
478. REEF: Representation Encoding Fingerprints for Large Language ModelsOral8 citations
479. ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic InterpretabilitySpotlight8 citations
480. Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNsPoster8 citations
481. RevisEval: Improving LLM-as-a-Judge via Response-Adapted ReferencesPoster8 citations
482. Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to AdvancesPoster8 citations
483. SCBench: A KV Cache-Centric Analysis of Long-Context MethodsPoster8 citations
484. Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light TransportOral8 citations
485. SciLitLLM: How to Adapt LLMs for Scientific Literature UnderstandingPoster8 citations
486. Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior PredictionPoster8 citations
487. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse ViewpointsPoster8 citations
488. TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation ModelsPoster8 citations
489. The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political DiscussionsSpotlight8 citations
490. TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic PoliciesPoster8 citations
491. Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement LearningPoster8 citations
492. Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM OutputsOral8 citations
493. Unintentional Unalignment: Likelihood Displacement in Direct Preference OptimizationPoster8 citations
494. Video-STaR: Self-Training Enables Video Instruction Tuning with Any SupervisionPoster8 citations
495. nGPT: Normalized Transformer with Representation Learning on the HyperspherePoster8 citations
496. A Geometric Framework for Understanding Memorization in Generative ModelsSpotlight7 citations
497. Accurate and Scalable Graph Neural Networks via Message InvariancePoster7 citations
498. Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted DataPoster7 citations
499. An Undetectable Watermark for Generative Image ModelsPoster7 citations
500. Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear ProgrammingPoster7 citations
501. Benchmarking Agentic Workflow GenerationPoster7 citations
502. Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity DatasetPoster7 citations
503. CBraMod: A Criss-Cross Brain Foundation Model for EEG DecodingPoster7 citations
504. CREAM: Consistency Regularized Self-Rewarding Language ModelsPoster7 citations
505. Concept Bottleneck Large Language ModelsPoster7 citations
506. ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference TimePoster7 citations
507. Efficient Evolutionary Search Over Chemical Space with Large Language ModelsPoster7 citations
508. Exploring Prosocial Irrationality for LLM Agents: A Social Cognition ViewPoster7 citations
509. Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein DesignPoster7 citations
510. From Tokens to Words: On the Inner Lexicon of LLMsPoster7 citations
511. GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPSPoster7 citations
512. GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian SplattingPoster7 citations
513. Generalizable Human Gaussians from Single-View ImagePoster7 citations
514. Generative Inbetweening: Adapting Image-to-Video Models for Keyframe InterpolationPoster7 citations
515. Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface RepresentationPoster7 citations
516. How to Evaluate Reward Models for RLHFPoster7 citations
517. Human Simulacra: Benchmarking the Personification of Large Language ModelsPoster7 citations
518. ICLR: In-Context Learning of RepresentationsPoster7 citations
519. Instant Policy: In-Context Imitation Learning via Graph DiffusionOral7 citations
520. Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language ModelsPoster7 citations
521. JetFormer: An autoregressive generative model of raw images and textPoster7 citations
522. LICO: Large Language Models for In-Context Molecular OptimizationPoster7 citations
523. Learning Harmonized Representations for Speculative SamplingPoster7 citations
524. Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the dataOral7 citations
525. MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World TasksPoster7 citations
526. MLLM can see? Dynamic Correction Decoding for Hallucination MitigationPoster7 citations
527. MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing AgentsPoster7 citations
528. Measuring And Improving Persuasiveness Of Large Language ModelsPoster7 citations
529. MoDeGPT: Modular Decomposition for Large Language Model CompressionOral7 citations
530. Moral Alignment for LLM AgentsPoster7 citations
531. ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor ReconstructionSpotlight7 citations
532. PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent CollaborationOral7 citations
533. Personalized Visual Instruction TuningPoster7 citations
534. Preference Diffusion for RecommendationPoster7 citations
535. Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave SamplingPoster7 citations
536. Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language ModelPoster7 citations
537. ReSi: A Comprehensive Benchmark for Representational Similarity MeasuresPoster7 citations
538. Reconciling Model Multiplicity for Downstream Decision MakingPoster7 citations
539. Robustness of Quantum Algorithms for Nonconvex OptimizationPoster7 citations
540. SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data SelectionPoster7 citations
541. SPA: 3D Spatial-Awareness Enables Effective Embodied RepresentationPoster7 citations
542. Self-Improving Robust Preference OptimizationPoster7 citations
543. Sparse Autoencoders Reveal Temporal Difference Learning in Large Language ModelsPoster7 citations
544. SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based SpikingPoster7 citations
545. SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal BudgetPoster7 citations
546. Standardizing Structural Causal ModelsPoster7 citations
547. SysCaps: Language Interfaces for Simulation Surrogates of Complex SystemsPoster7 citations
548. TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation DataPoster7 citations
549. TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated WeightsPoster7 citations
550. The 3D-PC: a benchmark for visual perspective taking in humans and machinesPoster7 citations
551. The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modelingPoster7 citations
552. ThinkBot: Embodied Instruction Following with Thought Chain ReasoningPoster7 citations
553. Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-TuningPoster7 citations
554. Uncovering Overfitting in Large Language Model EditingSpotlight7 citations
555. Understanding Factual Recall in Transformers via Associative MemoriesSpotlight7 citations
556. Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to ChaosPoster7 citations
557. Unlocking State-Tracking in Linear RNNs Through Negative EigenvaluesOral7 citations
558. What Makes Large Language Models Reason in (Multi-Turn) Code Generation?Poster7 citations
559. What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Poster7 citations
560. X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at ScaleSpotlight7 citations
561. u-$\mu$P: The Unit-Scaled Maximal Update ParametrizationSpotlight7 citations
562. A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal LanguagePoster6 citations
563. ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial PurificationPoster6 citations
564. ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video GenerationPoster6 citations
565. Adding Conditional Control to Diffusion Models with Reinforcement LearningPoster6 citations
566. Agent-Oriented Planning in Multi-Agent SystemsPoster6 citations
567. AgentSquare: Automatic LLM Agent Search in Modular Design SpacePoster6 citations
568. Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation ModelPoster6 citations
569. AuroraCap: Efficient, Performant Video Detailed Captioning and a New BenchmarkPoster6 citations
570. AvatarGO: Zero-shot 4D Human-Object Interaction Generation and AnimationPoster6 citations
571. Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequencesPoster6 citations
572. Black-Box Detection of Language Model WatermarksPoster6 citations
573. Commit0: Library Generation from ScratchPoster6 citations
574. Competition Dynamics Shape Algorithmic Phases of In-Context LearningSpotlight6 citations
575. Composable Interventions for Language ModelsPoster6 citations
576. Contextual Document EmbeddingsPoster6 citations
577. CrossMPT: Cross-attention Message-passing Transformer for Error Correcting CodesPoster6 citations
578. Deep MMD Gradient Flow without adversarial trainingPoster6 citations
579. DelTA: An Online Document-Level Translation Agent Based on Multi-Level MemoryPoster6 citations
580. Diffusing States and Matching Scores: A New Framework for Imitation LearningPoster6 citations
581. Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?Poster6 citations
582. Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight ForgettingPoster6 citations
583. Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsPoster6 citations
584. Emergence of meta-stable clustering in mean-field transformer modelsOral6 citations
585. Encryption-Friendly LLM ArchitecturePoster6 citations
586. Fast Feedforward 3D Gaussian Splatting CompressionPoster6 citations
587. Fast Summation of Radial Kernels via QMC SlicingPoster6 citations
588. FasterCache: Training-Free Video Diffusion Model Acceleration with High QualityPoster6 citations
589. Federated $Q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication CostPoster6 citations
590. Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language AlignmentPoster6 citations
591. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven InteractionsOral6 citations
592. Graph Neural Preconditioners for Iterative Solutions of Sparse Linear SystemsPoster6 citations
593. Heavy-Tailed Diffusion ModelsPoster6 citations
594. HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View ReconstructionPoster6 citations
595. Highly Efficient Self-Adaptive Reward Shaping for Reinforcement LearningPoster6 citations
596. In-Context Editing: Learning Knowledge from Self-Induced DistributionsPoster6 citations
597. In-context Time Series PredictorPoster6 citations
598. Instructional Segment Embedding: Improving LLM Safety with Instruction HierarchyPoster6 citations
599. LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal ModelsSpotlight6 citations
600. LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and CaptioningPoster6 citations
601. Language Guided Skill DiscoveryPoster6 citations
602. Language Representations Can be What Recommenders Need: Findings and PotentialsOral6 citations
603. LongGenBench: Benchmarking Long-Form Generation in Long Context LLMsPoster6 citations
604. MallowsPO: Fine-Tune Your LLM with Preference DispersionsPoster6 citations
605. Memory MosaicsPoster6 citations
606. Meta Flow Matching: Integrating Vector Fields on the Wasserstein ManifoldPoster6 citations
607. MetaMetrics: Calibrating Metrics for Generation Tasks Using Human PreferencesPoster6 citations
608. MetaOOD: Automatic Selection of OOD Detection ModelsPoster6 citations
609. Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image PyramidPoster6 citations
610. Multi-Robot Motion Planning with Diffusion ModelsSpotlight6 citations
611. Multi-objective Differentiable Neural Architecture SearchPoster6 citations
612. No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion ModelsPoster6 citations
613. On the Identification of Temporal Causal Representation with Instantaneous DependenceOral6 citations
614. OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization ModelingPoster6 citations
615. Pareto Low-Rank Adapters: Efficient Multi-Task Learning with PreferencesPoster6 citations
616. PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform GenerationPoster6 citations
617. Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized ProgrammingPoster6 citations
618. Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image RestorationPoster6 citations
619. ProteinBench: A Holistic Evaluation of Protein Foundation ModelsPoster6 citations
620. Quantifying Generalization Complexity for Large Language ModelsPoster6 citations
621. Reasoning with Latent Thoughts: On the Power of Looped TransformersPoster6 citations
622. SINGAPO: Single Image Controlled Generation of Articulated Parts in ObjectsPoster6 citations
623. SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMsPoster6 citations
624. SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language ModelPoster6 citations
625. SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language ModelsPoster6 citations
626. Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language ModelsSpotlight6 citations
627. Scaling Wearable Foundation ModelsPoster6 citations
628. Selective Attention Improves TransformerPoster6 citations
629. SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningSpotlight6 citations
630. Specialized Foundation Models Struggle to Beat Supervised BaselinesPoster6 citations
631. Speech Robust Bench: A Robustness Benchmark For Speech RecognitionPoster6 citations
632. Statistical Advantages of Perturbing Cosine Router in Mixture of ExpertsPoster6 citations
633. Streaming Video Understanding and Multi-round Interaction with Memory-enhanced KnowledgePoster6 citations
634. Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided SearchPoster6 citations
635. TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference TreesPoster6 citations
636. Timer-XL: Long-Context Transformers for Unified Time Series ForecastingPoster6 citations
637. ToolGen: Unified Tool Retrieval and Calling via GenerationPoster6 citations
638. Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of ExpressivityOral6 citations
639. TorchTitan: One-stop PyTorch native solution for production ready LLM pretrainingPoster6 citations
640. Transformers Provably Solve Parity Efficiently with Chain of ThoughtOral6 citations
641. Trust or Escalate: LLM Judges with Provable Guarantees for Human AgreementOral6 citations
642. Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuningPoster6 citations
643. VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference AccelerationPoster6 citations
644. Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts ReasoningPoster6 citations
645. When does compositional structure yield compositional generalization? A kernel theory.Poster6 citations
646. A Quantum Circuit-Based Compression Perspective for Parameter-Efficient LearningPoster5 citations
647. A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationPoster5 citations
648. A Unified Theory of Quantum Neural Network Loss LandscapesPoster5 citations
649. ARB-LLM: Alternating Refined Binarizations for Large Language ModelsPoster5 citations
650. Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order OptimizationPoster5 citations
651. Active Learning for Neural PDE SolversPoster5 citations
652. Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion ModelsPoster5 citations
653. AgentRefine: Enhancing Agent Generalization through Refinement TuningPoster5 citations
654. An Intelligent Agentic System for Complex Image Restoration ProblemsPoster5 citations
655. Attention as a HypernetworkOral5 citations
656. Better Instruction-Following Through Minimum Bayes RiskSpotlight5 citations
657. BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak AttacksPoster5 citations
658. CG-Bench: Clue-grounded Question Answering Benchmark for Long Video UnderstandingPoster5 citations
659. CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science MasteryPoster5 citations
660. Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?Spotlight5 citations
661. Can Watermarked LLMs be Identified by Users via Crafted Prompts?Spotlight5 citations
662. Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making SystemsPoster5 citations
663. CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale ScenesPoster5 citations
664. Computationally Efficient RL under Linear Bellman Completeness for Deterministic DynamicsOral5 citations
665. DeLLMa: Decision Making Under Uncertainty with Large Language ModelsSpotlight5 citations
666. DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat GenerationPoster5 citations
667. Differentiable Integer Linear ProgrammingSpotlight5 citations
668. Diffusion Models are Evolutionary AlgorithmsPoster5 citations
669. Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical ReasoningPoster5 citations
670. Does SGD really happen in tiny subspaces?Poster5 citations
671. ECHOPulse: ECG Controlled Echocardio-gram Video GenerationPoster5 citations
672. Effective Interplay between Sparsity and Quantization: From Theory to PracticeSpotlight5 citations
673. Efficient Dictionary Learning with Switch Sparse AutoencodersPoster5 citations
674. ElasticTok: Adaptive Tokenization for Image and VideoPoster5 citations
675. Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoningPoster5 citations
676. From Lazy to Rich: Exact Learning Dynamics in Deep Linear NetworksPoster5 citations
677. Generative Monoculture in Large Language ModelsPoster5 citations
678. Grounding by Trying: LLMs with Reinforcement Learning-Enhanced RetrievalPoster5 citations
679. HAMSTER: Hierarchical Action Models for Open-World Robot ManipulationPoster5 citations
680. Hierarchical World Models as Visual Whole-Body Humanoid ControllersPoster5 citations
681. How Does Critical Batch Size Scale in Pre-training?Poster5 citations
682. How Feature Learning Can Improve Neural Scaling LawsSpotlight5 citations
683. How efficient is LLM-generated code? A rigorous & high-standard benchmarkPoster5 citations
684. InterMask: 3D Human Interaction Generation via Collaborative Masked ModelingPoster5 citations
685. Jailbreaking as a Reward Misspecification ProblemPoster5 citations
686. KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal ModelsPoster5 citations
687. Language Models Need Inductive Biases to Count InductivelyPoster5 citations
688. Law of the Weakest Link: Cross Capabilities of Large Language ModelsPoster5 citations
689. LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model MergingPoster5 citations
690. Logically Consistent Language Models via Neuro-Symbolic IntegrationPoster5 citations
691. Long-time asymptotics of noisy SVGD outside the population limitPoster5 citations
692. Longhorn: State Space Models are Amortized Online LearnersPoster5 citations
693. MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph GenerationPoster5 citations
694. MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language ModelsPoster5 citations
695. Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order BoundsPoster5 citations
696. Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool UsageSpotlight5 citations
697. Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic PlanningPoster5 citations
698. Multimodal Situational SafetyPoster5 citations
699. Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional DivergencePoster5 citations
700. NovelQA: Benchmarking Question Answering on Documents Exceeding 200K TokensPoster5 citations
701. OASIS Uncovers: High-Quality T2I Models, Same Old StereotypesSpotlight5 citations
702. OmnixR: Evaluating Omni-modality Language Models on Reasoning across ModalitiesPoster5 citations
703. On the Completeness of Invariant Geometric Deep Learning ModelsPoster5 citations
704. One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single PromptSpotlight5 citations
705. Online Preference Alignment for Language Models via Count-based ExplorationSpotlight5 citations
706. Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap FunctionsPoster5 citations
707. PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent TasksPoster5 citations
708. Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented DiffusionPoster5 citations
709. Post-hoc Reward Calibration: A Case Study on Length BiasPoster5 citations
710. Privacy Auditing of Large Language ModelsPoster5 citations
711. Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language ModelsPoster5 citations
712. Protein Language Model Fitness is a Matter of PreferencePoster5 citations
713. Provable weak-to-strong generalization via benign overfittingPoster5 citations
714. RainbowPO: A Unified Framework for Combining Improvements in Preference OptimizationPoster5 citations
715. Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language ModelPoster5 citations
716. Reconstructive Visual Instruction TuningPoster5 citations
717. Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRAPoster5 citations
718. SONICS: Synthetic Or Not - Identifying Counterfeit SongsPoster5 citations
719. SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language ModelsPoster5 citations
720. STAMP: Scalable Task- And Model-agnostic Collaborative PerceptionPoster5 citations
721. SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent ExplanationsPoster5 citations
722. Selective Aggregation for Low-Rank Adaptation in Federated LearningPoster5 citations
723. Self-Improvement in Language Models: The Sharpening MechanismOral5 citations
724. Simple ReFlow: Improved Techniques for Fast Flow ModelsPoster5 citations
725. Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State FusionPoster5 citations
726. Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingPoster5 citations
727. Spread Preference Annotation: Direct Preference Judgment for Efficient LLM AlignmentOral5 citations
728. Steering Large Language Models between Code Execution and Textual ReasoningPoster5 citations
729. TLDR: Token-Level Detective Reward Model for Large Vision Language ModelsPoster5 citations
730. Text-to-Image Rectified Flow as Plug-and-Play PriorsPoster5 citations
731. Text4Seg: Reimagining Image Segmentation as Text GenerationPoster5 citations
732. The Foundations of Tokenization: Statistical and Computational ConcernsPoster5 citations
733. The Optimization Landscape of SGD Across the Feature Learning StrengthPoster5 citations
734. Towards Foundation Models for Mixed Integer Linear ProgrammingPoster5 citations
735. Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial DecodersPoster5 citations
736. Transformer-Squared: Self-adaptive LLMsPoster5 citations
737. Unifying Causal Representation Learning with the Invariance PrinciplePoster5 citations
738. VSTAR: Generative Temporal Nursing for Longer Dynamic Video SynthesisPoster5 citations
739. Visual Haystacks: A Vision-Centric Needle-In-A-Haystack BenchmarkPoster5 citations
740. YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel CorpusPoster5 citations
741. Your Mixture-of-Experts LLM Is Secretly an Embedding Model for FreeOral5 citations
742. Zero-shot forecasting of chaotic systemsPoster5 citations
743. $\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language ModelsPoster4 citations
744. 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian SplattingPoster4 citations
745. A Formal Framework for Understanding Length Generalization in TransformersPoster4 citations
746. A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial ContextsPoster4 citations
747. A Second-Order Perspective on Model Compositionality and Incremental LearningSpotlight4 citations
748. AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language ModelsPoster4 citations
749. Activation Gradient based Poisoned Sample Detection Against Backdoor AttacksPoster4 citations
750. AdaManip: Adaptive Articulated Object Manipulation Environments and Policy LearningPoster4 citations
751. Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One StepPoster4 citations
752. Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsPoster4 citations
753. Aioli: A Unified Optimization Framework for Language Model Data MixingPoster4 citations
754. Aligning Human Motion Generation with Human PerceptionsPoster4 citations
755. Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language ModelsPoster4 citations
756. Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform CodingSpotlight4 citations
757. Artificial Kuramoto Oscillatory NeuronsOral4 citations
758. Ask, and it shall be given: On the Turing completeness of promptingPoster4 citations
759. Attention layers provably solve single-location regressionPoster4 citations
760. Automated Proof Generation for Rust Code via Self-EvolutionPoster4 citations
761. Automatic Curriculum Expert Iteration for Reliable LLM ReasoningPoster4 citations
762. BIRD: A Trustworthy Bayesian Inference Framework for Large Language ModelsOral4 citations
763. Beyond Linear Approximations: A Novel Pruning Approach for Attention MatrixPoster4 citations
764. Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian DistributionPoster4 citations
765. BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation CapabilitiesPoster4 citations
766. Block Diffusion: Interpolating Between Autoregressive and Diffusion Language ModelsOral4 citations
767. Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis ApproachPoster4 citations
768. Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image GenerationPoster4 citations
769. CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScalePoster4 citations
770. COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 TrainingPoster4 citations
771. Causal Concept Graph Models: Beyond Causal Opacity in Deep LearningPoster4 citations
772. ChemAgent: Self-updating Memories in Large Language Models Improves Chemical ReasoningPoster4 citations
773. CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip DesignPoster4 citations
774. ClassDiffusion: More Aligned Personalization Tuning with Explicit Class GuidancePoster4 citations
775. CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmarkPoster4 citations
776. Computing Circuits Optimization via Model-Based Circuit Genetic EvolutionPoster4 citations
777. ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron PruningPoster4 citations
778. Context-Alignment: Activating and Enhancing LLMs Capabilities in Time SeriesPoster4 citations
779. Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context RelianceOral4 citations
780. Cross-Embodiment Dexterous Grasping with Reinforcement LearningPoster4 citations
781. Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward ModelingPoster4 citations
782. DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEOPoster4 citations
783. DON’T STOP ME NOW: EMBEDDING BASED SCHEDULING FOR LLMSPoster4 citations
784. DaWin: Training-free Dynamic Weight Interpolation for Robust AdaptationPoster4 citations
785. DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily LifeSpotlight4 citations
786. Decomposition Polyhedra of Piecewise Linear FunctionsSpotlight4 citations
787. Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model EnsemblingSpotlight4 citations
788. DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific FactorsPoster4 citations
789. Diffusion Models as Cartoonists: The Curious Case of High Density RegionsPoster4 citations
790. Diffusion On Syntax Trees For Program SynthesisSpotlight4 citations
791. Doubly Optimal Policy Evaluation for Reinforcement LearningPoster4 citations
792. DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous DrivingPoster4 citations
793. Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language BootstrappingOral4 citations
794. ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICYPoster4 citations
795. Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataPoster4 citations
796. Efficient Reinforcement Learning with Large Language Model PriorsPoster4 citations
797. Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family ExpertsPoster4 citations
798. Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion ModelsPoster4 citations
799. Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank StructuresPoster4 citations
800. FaceShot: Bring Any Character into LifePoster4 citations
801. Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction TuningPoster4 citations
802. FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMsSpotlight4 citations
803. Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find ThemPoster4 citations
804. Faster Cascades via Speculative DecodingOral4 citations
805. Few for Many: Tchebycheff Set Scalarization for Many-Objective OptimizationPoster4 citations
806. Flow Matching with General Discrete Paths: A Kinetic-Optimal PerspectiveOral4 citations
807. Formation of Representations in Neural NetworksSpotlight4 citations
808. Fundamental Limitations on Subquadratic Alternatives to TransformersPoster4 citations
809. GenEx: Generating an Explorable WorldPoster4 citations
810. Generating CAD Code with Vision-Language Models for 3D DesignsPoster4 citations
811. Generative Flows on Synthetic Pathway for Drug DesignPoster4 citations
812. Geometry of Lightning Self-Attention: Identifiability and DimensionPoster4 citations
813. HARDMath: A Benchmark Dataset for Challenging Problems in Applied MathematicsPoster4 citations
814. HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain ShiftsPoster4 citations
815. How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern ComprehensionPoster4 citations
816. How many samples are needed to train a deep neural network?Poster4 citations
817. Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph GenerationPoster4 citations
818. HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding HyperspherePoster4 citations
819. I2VControl-Camera: Precise Video Camera Control with Adjustable Motion StrengthPoster4 citations
820. IgGM: A Generative Model for Functional Antibody and Nanobody DesignPoster4 citations
821. Improving Semantic Understanding in Speech Language Models via Brain-tuningPoster4 citations
822. In Search of Forgotten Domain GeneralizationSpotlight4 citations
823. Integrative Decoding: Improving Factuality via Implicit Self-consistencyPoster4 citations
824. Interaction Asymmetry: A General Principle for Learning Composable AbstractionsPoster4 citations
825. Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret LearningOral4 citations
826. Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-ResolutionSpotlight4 citations
827. Knowledge Localization: Mission Not Accomplished? Enter Query Localization!Spotlight4 citations
828. Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal ChoicePoster4 citations
829. Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation DataPoster4 citations
830. Learning Continually by Spectral RegularizationPoster4 citations
831. Learning Evolving Tools for Large Language ModelsPoster4 citations
832. Learning Long Range Dependencies on Graphs via Random WalksPoster4 citations
833. Learning system dynamics without forgettingPoster4 citations
834. Learning to Steer Markovian Agents under Model UncertaintyPoster4 citations
835. Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement LearningPoster4 citations
836. Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models BetterPoster4 citations
837. Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution DetectionPoster4 citations
838. Locality-aware Gaussian Compression for Fast and High-quality RenderingPoster4 citations
839. Looking Inward: Language Models Can Learn About Themselves by IntrospectionPoster4 citations
840. LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer VisionPoster4 citations
841. Many-Objective Multi-Solution TransportPoster4 citations
842. MatExpert: Decomposing Materials Discovery By Mimicking Human ExpertsPoster4 citations
843. MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical CodeSpotlight4 citations
844. Mind the Gap: Examining the Self-Improvement Capabilities of Large Language ModelsOral4 citations
845. MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation ExpertsOral4 citations
846. Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying QuestionsPoster4 citations
847. Modeling dynamic social vision highlights gaps between deep learning and humansPoster4 citations
848. MotherNet: Fast Training and Inference via Hyper-Network TransformersPoster4 citations
849. NarrativeBridge: Enhancing Video Captioning with Causal-Temporal NarrativePoster4 citations
850. Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein GeometryPoster4 citations
851. NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG SignalsPoster4 citations
852. Non-myopic Generation of Language Models for Reasoning and PlanningPoster4 citations
853. Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg ExtrapolationPoster4 citations
854. Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and ReasoningPoster4 citations
855. Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion ModelsPoster4 citations
856. On the Feature Learning in Diffusion ModelsPoster4 citations
857. On the Optimal Memorization Capacity of TransformersPoster4 citations
858. On the Role of Attention Heads in Large Language Model SafetyOral4 citations
859. Open-Set Graph Anomaly Detection via Normal Structure RegularisationPoster4 citations
860. PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemsSpotlight4 citations
861. Presto! Distilling Steps and Layers for Accelerating Music GenerationSpotlight4 citations
862. Probabilistic Conformal Prediction with Approximate Conditional ValidityPoster4 citations
863. PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and VerifyPoster4 citations
864. Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsPoster4 citations
865. RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data RewardsPoster4 citations
866. RecFlow: An Industrial Full Flow Recommendation DatasetPoster4 citations
867. Refine Knowledge of Large Language Models via Adaptive Contrastive LearningPoster4 citations
868. Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative ModelsPoster4 citations
869. Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?Spotlight4 citations
870. Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation ModelsPoster4 citations
871. Revisiting In-context Learning Inference Circuit in Large Language ModelsPoster4 citations
872. Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among PromptsPoster4 citations
873. RobustKV: Defending Large Language Models against Jailbreak Attacks via KV EvictionPoster4 citations
874. Scaling up Masked Diffusion Models on TextPoster4 citations
875. Self-Boosting Large Language Models with Synthetic Preference DataPoster4 citations
876. Shallow diffusion networks provably learn hidden low-dimensional structurePoster4 citations
877. SimPER: A Minimalist Approach to Preference Alignment without HyperparametersPoster4 citations
878. SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video GenerationSpotlight4 citations
879. SmartRAG: Jointly Learn RAG-Related Tasks From the Environment FeedbackPoster4 citations
880. Standard Gaussian Process is All You Need for High-Dimensional Bayesian OptimizationOral4 citations
881. Streaming Video Question-Answering with In-context Video KV-Cache RetrievalPoster4 citations
882. Streamlining Redundant Layers to Compress Large Language ModelsSpotlight4 citations
883. Sufficient Context: A New Lens on Retrieval Augmented Generation SystemsPoster4 citations
884. Syntactic and Semantic Control of Large Language Models via Sequential Monte CarloOral4 citations
885. TULIP: Token-length Upgraded CLIPPoster4 citations
886. Tell me about yourself: LLMs are aware of their learned behaviorsSpotlight4 citations
887. TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric MeshesOral4 citations
888. The Crucial Role of Samplers in Online Direct Preference OptimizationPoster4 citations
889. The Superposition of Diffusion Models Using the Itô Density EstimatorSpotlight4 citations
890. ThermalGaussian: Thermal 3D Gaussian SplattingPoster4 citations
891. TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse AttentionPoster4 citations
892. To Code or Not To Code? Exploring Impact of Code in Pre-trainingPoster4 citations
893. Tool-Planner: Task Planning with Clusters across Multiple ToolsPoster4 citations
894. ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language ModelsPoster4 citations
895. Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image SegmentationSpotlight4 citations
896. Towards Neural Scaling Laws for Time Series Foundation ModelsPoster4 citations
897. Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature HierarchyPoster4 citations
898. UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk EstimatePoster4 citations
899. Vec2Face: Scaling Face Dataset Generation with Loosely Constrained VectorsPoster4 citations
900. Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised DisentanglementPoster4 citations
901. Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMsPoster4 citations
902. Ward: Provable RAG Dataset Inference via LLM WatermarksPoster4 citations
903. Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned ModelSpotlight4 citations
904. WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement LearningPoster4 citations
905. What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian AnalysisSpotlight4 citations
906. What is Wrong with Perplexity for Long-context Language Modeling?Poster4 citations
907. When Attention Sink Emerges in Language Models: An Empirical ViewSpotlight4 citations
908. WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language ModelsPoster4 citations
909. You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANsPoster4 citations
910. Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsPoster4 citations
911. A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate ConvergencePoster3 citations
912. ADAM: An Embodied Causal Agent in Open-World EnvironmentsPoster3 citations
913. AdaGrad under Anisotropic SmoothnessPoster3 citations
914. AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-TuningPoster3 citations
915. Adaptive Deployment of Untrusted LLMs Reduces Distributed ThreatsPoster3 citations
916. Adaptive teachers for amortized samplersPoster3 citations
917. Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open SystemsPoster3 citations
918. Arithmetic Transformers Can Length-Generalize in Both Operand Length and CountPoster3 citations
919. AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular AssemblyPoster3 citations
920. Associative memory and dead neuronsPoster3 citations
921. Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language ModelsPoster3 citations
922. Atlas Gaussians Diffusion for 3D GenerationSpotlight3 citations
923. AtomSurf: Surface Representation for Learning on Protein StructuresPoster3 citations
924. Attention in Large Language Models Yields Efficient Zero-Shot Re-RankersPoster3 citations
925. Attention with Markov: A Curious Case of Single-layer TransformersSpotlight3 citations
926. Backdooring Vision-Language Models with Out-Of-Distribution DataPoster3 citations
927. Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionPoster3 citations
928. Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message PassingPoster3 citations
929. Beyond Model Collapse: Scaling Up with Synthesized Data Requires VerificationPoster3 citations
930. Block Verification Accelerates Speculative DecodingPoster3 citations
931. Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature CompensatorPoster3 citations
932. Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based SamplingSpotlight3 citations
933. CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS CompressionPoster3 citations
934. CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMsPoster3 citations
935. CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionPoster3 citations
936. CipherPrune: Efficient and Scalable Private Transformer InferencePoster3 citations
937. Closed-Form Merging of Parameter-Efficient Modules for Federated Continual LearningPoster3 citations
938. CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form PlanningPoster3 citations
939. Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question AnsweringPoster3 citations
940. Conformal Prediction Sets Can Cause Disparate ImpactSpotlight3 citations
941. Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent FeedbackPoster3 citations
942. Continuous Diffusion for Mixed-Type Tabular DataPoster3 citations
943. Controllable Context Sensitivity and the Knob Behind ItPoster3 citations
944. Controlling Language and Diffusion Models by Transporting ActivationsSpotlight3 citations
945. Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time AnalysisPoster3 citations
946. Convergent Privacy Loss of Noisy-SGD without Convexity and SmoothnessPoster3 citations
947. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code RepairPoster3 citations
948. Cross-Modal Safety Mechanism Transfer in Large Vision-Language ModelsPoster3 citations
949. CtrLoRA: An Extensible and Efficient Framework for Controllable Image GenerationPoster3 citations
950. CubeDiff: Repurposing Diffusion-Based Image Models for Panorama GenerationSpotlight3 citations
951. DELIFT: Data Efficient Language model Instruction Fine-TuningPoster3 citations
952. DSPO: Direct Score Preference Optimization for Diffusion Model AlignmentOral3 citations
953. DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion ControlSpotlight3 citations
954. DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation ModelSpotlight3 citations
955. DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single DemoSpotlight3 citations
956. Deriving Causal Order from Single-Variable Interventions: Guarantees & AlgorithmPoster3 citations
957. Diff-Prompt: Diffusion-Driven Prompt Generator with Mask SupervisionPoster3 citations
958. Differential learning kinetics govern the transition from memorization to generalization during in-context learningSpotlight3 citations
959. Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process DataPoster3 citations
960. Diffusion-Based Planning for Autonomous Driving with Flexible GuidanceOral3 citations
961. Discrete Diffusion Schrödinger Bridge Matching for Graph TransformationPoster3 citations
962. Diversity-Rewarded CFG DistillationPoster3 citations
963. Do LLMs have Consistent Values?Poster3 citations
964. Duoduo CLIP: Efficient 3D Understanding with Multi-View ImagesPoster3 citations
965. Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask LearningPoster3 citations
966. Efficient Policy Evaluation with Safety Constraint for Reinforcement LearningPoster3 citations
967. Efficiently Parameterized Neural Metriplectic SystemsPoster3 citations
968. Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learningPoster3 citations
969. Endless Jailbreaks with Bijection LearningPoster3 citations
970. Estimating the Probabilities of Rare Outputs in Language ModelsSpotlight3 citations
971. Expected Sliced Transport PlansPoster3 citations
972. Failures to Find Transferable Image Jailbreaks Between Vision-Language ModelsPoster3 citations
973. Fair Submodular CoverPoster3 citations
974. Flow matching achieves almost minimax optimal convergencePoster3 citations
975. Fourier Head: Helping Large Language Models Learn Complex Probability DistributionsPoster3 citations
976. Framer: Interactive Frame InterpolationPoster3 citations
977. From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMsPoster3 citations
978. GTR: Improving Large 3D Reconstruction Models through Geometry and Texture RefinementPoster3 citations
979. Gap-Dependent Bounds for Q-Learning using Reference-Advantage DecompositionSpotlight3 citations
980. Generalized Principal-Agent Problem with a Learning AgentSpotlight3 citations
981. Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward PassPoster3 citations
982. Glauber Generative Model: Discrete Diffusion Models via Binary ClassificationPoster3 citations
983. GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine LearningPoster3 citations
984. Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual InformationPoster3 citations
985. GotenNet: Rethinking Efficient 3D Equivariant Graph Neural NetworksPoster3 citations
986. Guaranteed Generation from Large Language ModelsPoster3 citations
987. HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsPoster3 citations
988. Harnessing Webpage UIs for Text-Rich Visual UnderstandingPoster3 citations
989. HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language ModelsOral3 citations
990. High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling LawsSpotlight3 citations
991. IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language ModelPoster3 citations
992. IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph LearningSpotlight3 citations
993. IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image PromptsPoster3 citations
994. IRIS: LLM-Assisted Static Analysis for Detecting Security VulnerabilitiesPoster3 citations
995. Identifiable Exchangeable Mechanisms for Causal Structure and Representation LearningSpotlight3 citations
996. Improved Finite-Particle Convergence Rates for Stein Variational Gradient DescentOral3 citations
997. Improving Data Efficiency via Curating LLM-Driven Rating SystemsPoster3 citations
998. Improving Long-Text Alignment for Text-to-Image Diffusion ModelsPoster3 citations
999. Improving Uncertainty Estimation through Semantically Diverse Language GenerationPoster3 citations
1000. Imputation for prediction: beware of diminishing returns.Spotlight3 citations

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