Total Papers: 3687

Split into 100 parts for better browsing

1. Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution

2. Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

3. Joint Graph Rewiring and Feature Denoising via Spectral Resonance

4. AFlow: Automating Agentic Workflow Generation

5. DSPO: Direct Score Preference Optimization for Diffusion Model Alignment

6. Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

7. Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

8. OLMoE: Open Mixture-of-Experts Language Models

9. Learning to Discretize Denoising Diffusion ODEs

10. When Selection Meets Intervention: Additional Complexities in Causal Discovery

11. Scaling Laws for Precision

12. Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

13. Progressive distillation induces an implicit curriculum

14. Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

15. Open-World Reinforcement Learning over Long Short-Term Imagination

16. Faster Cascades via Speculative Decoding

17. DEPT: Decoupled Embeddings for Pre-training Language Models

18. CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

19. When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers

20. Learning to Search from Demonstration Sequences

21. Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks

22. Capturing the Temporal Dependence of Training Data Influence

23. Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

24. Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport

25. Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

26. Robustness Inspired Graph Backdoor Defense

27. Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective

28. Scaling and evaluating sparse autoencoders

29. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

30. Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

31. Learning Dynamics of LLM Finetuning

32. Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games

33. MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

34. Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

35. Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

36. Do as We Do, Not as You Think: the Conformity of Large Language Models

37. Linear Representations of Political Perspective Emerge in Large Language Models

38. Rethinking Reward Modeling in Preference-based Large Language Model Alignment

39. Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

40. PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

41. Consistency Checks for Language Model Forecasters

42. Towards a Complete Logical Framework for GNN Expressiveness

43. On Scaling Up 3D Gaussian Splatting Training

44. Data Scaling Laws in Imitation Learning for Robotic Manipulation

45. MaestroMotif: Skill Design from Artificial Intelligence Feedback

46. DarkBench: Benchmarking Dark Patterns in Large Language Models

47. On the Benefits of Memory for Modeling Time-Dependent PDEs

48. ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding

49. CAX: Cellular Automata Accelerated in JAX

50. Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

51. Artificial Kuramoto Oscillatory Neurons

52. Transformers Provably Solve Parity Efficiently with Chain of Thought

53. Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

54. Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

55. Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

56. WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

57. LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

58. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

59. Learning and aligning single-neuron invariance manifolds in visual cortex

60. Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

61. Copyright-Protected Language Generation via Adaptive Model Fusion

62. Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

63. Feedback Schrödinger Bridge Matching

64. Root Cause Analysis of Anomalies in Multivariate Time Series through Granger Causal Discovery

65. Instant Policy: In-Context Imitation Learning via Graph Diffusion

66. GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation

67. Training on the Test Task Confounds Evaluation and Emergence

68. Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation

69. Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

70. AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

71. Second-Order Min-Max Optimization with Lazy Hessians

72. Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

73. Cross-Entropy Is All You Need To Invert the Data Generating Process

74. On the Role of Attention Heads in Large Language Model Safety

75. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

76. Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport

77. Composing Unbalanced Flows for Flexible Docking and Relaxation

78. A Computational Framework for Modeling Emergence of Color Vision in the Human Brain

79. Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

80. BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

81. Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection

82. Influence Functions for Scalable Data Attribution in Diffusion Models

83. Language Representations Can be What Recommenders Need: Findings and Potentials

84. Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

85. Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free

86. Emergence of meta-stable clustering in mean-field transformer models

87. Data Selection via Optimal Control for Language Models

88. Feedback Favors the Generalization of Neural ODEs

89. Comparing noisy neural population dynamics using optimal transport distances

90. Subgraph Federated Learning for Local Generalization

91. RB-Modulation: Training-Free Stylization using Reference-Based Modulation

92. The Geometry of Categorical and Hierarchical Concepts in Large Language Models

93. TopoLM: brain-like spatio-functional organization in a topographic language model

94. Problem-Parameter-Free Federated Learning

95. Latent Bayesian Optimization via Autoregressive Normalizing Flows

96. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

97. ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

98. LaMPlace: Learning to Optimize Cross-Stage Metrics in Macro Placement

99. MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

100. On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding

101. Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

102. EmbodiedSAM: Online Segment Any 3D Thing in Real Time

103. Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

104. LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

105. Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding

106. Self-Improvement in Language Models: The Sharpening Mechanism

107. Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

108. LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

109. Reasoning Elicitation in Language Models via Counterfactual Feedback

110. Attention as a Hypernetwork

111. Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

112. Learning Randomized Algorithms with Transformers

113. Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

114. HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models

115. Proteina: Scaling Flow-based Protein Structure Generative Models

116. REEF: Representation Encoding Fingerprints for Large Language Models

117. A Decade's Battle on Dataset Bias: Are We There Yet?

118. Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

119. Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

120. ECD: A Machine Learning Benchmark for Predicting Enhanced-Precision Electronic Charge Density in Crystalline Inorganic Materials

121. Generator Matching: Generative modeling with arbitrary Markov processes

122. Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration

123. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

124. LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

125. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

126. Advantage Alignment Algorithms

127. RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

128. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

129. Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

130. Steering Protein Family Design through Profile Bayesian Flow

131. Unlearning-based Neural Interpretations

132. On the Hölder Stability of Multiset and Graph Neural Networks

133. No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

134. KAN: Kolmogorov–Arnold Networks

135. Differential Transformer

136. One Step Diffusion via Shortcut Models

137. FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

138. A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules

139. REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments

140. Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

141. MAP: Multi-Human-Value Alignment Palette

142. SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers

143. Learning to Discover Regulatory Elements for Gene Expression Prediction

144. Simplifying, Stabilizing and Scaling Continuous-time Consistency Models

145. TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

146. ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design

147. miniCTX: Neural Theorem Proving with (Long-)Contexts

148. Residual Deep Gaussian Processes on Manifolds

149. Accelerated training through iterative gradient propagation along the residual path

150. Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

151. Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

152. AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

153. STAR: Synthesis of Tailored Architectures

154. MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

155. SAM 2: Segment Anything in Images and Videos

156. Data Shapley in One Training Run

157. Oscillatory State-Space Models

158. Restructuring Vector Quantization with the Rotation Trick

159. MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions

160. GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling

161. More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

162. Population Transformer: Learning Population-level Representations of Neural Activity

163. Inference Scaling for Long-Context Retrieval Augmented Generation

164. Proxy Denoising for Source-Free Domain Adaptation

165. Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

166. Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

167. Retrieval Head Mechanistically Explains Long-Context Factuality

168. MIND over Body: Adaptive Thinking using Dynamic Computation

169. How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning

170. SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups

171. Cut Your Losses in Large-Vocabulary Language Models

172. Interpreting Emergent Planning in Model-Free Reinforcement Learning

173. Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

174. Progressive Compression with Universally Quantized Diffusion Models

175. High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation

176. Training Language Models to Self-Correct via Reinforcement Learning

177. Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation

178. What should a neuron aim for? Designing local objective functions based on information theory

179. Backtracking Improves Generation Safety

180. Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

181. Global Convergence in Neural ODEs: Impact of Activation Functions

182. Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces

183. The Hidden Cost of Waiting for Accurate Predictions

184. DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL

185. The Complexity of Two-Team Polymatrix Games with Independent Adversaries

186. Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series

187. TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

188. MoDeGPT: Modular Decomposition for Large Language Model Compression

189. Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities

190. Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

191. MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

192. Safety Alignment Should be Made More Than Just a Few Tokens Deep

193. Variational Diffusion Posterior Sampling with Midpoint Guidance

194. NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields

195. SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

196. Energy-based Backdoor Defense Against Federated Graph Learning

197. Prioritized Generative Replay

198. A Probabilistic Perspective on Unlearning and Alignment for Large Language Models

199. Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality

200. Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning

201. Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning

202. Compositional Entailment Learning for Hyperbolic Vision-Language Models

203. OptionZero: Planning with Learned Options

204. On the Identification of Temporal Causal Representation with Instantaneous Dependence

205. Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning

206. RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

207. Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation

208. Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

209. TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis

210. ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

211. Synthetic continued pretraining

212. ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

213. LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

214. Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations

215. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

216. Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI

217. MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

218. Robust Function-Calling for On-Device Language Model via Function Masking

219. GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

220. Advantage-Guided Distillation for Preference Alignment in Small Language Models

221. JudgeLM: Fine-tuned Large Language Models are Scalable Judges

222. Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

223. Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

224. Better autoregressive regression with LLMs via regression-aware fine-tuning

225. The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions

226. CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series

227. Tuning Frequency Bias of State Space Models

228. Provably Accurate Shapley Value Estimation via Leverage Score Sampling

229. GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision

230. Diffusion On Syntax Trees For Program Synthesis

231. Effective Interplay between Sparsity and Quantization: From Theory to Practice

232. VLMaterial: Procedural Material Generation with Large Vision-Language Models

233. Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra

234. Test-time Alignment of Diffusion Models without Reward Over-optimization

235. SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

236. Decomposition Polyhedra of Piecewise Linear Functions

237. Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

238. UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

239. SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints

240. Counterfactual Realizability

241. How Much is Unseen Depends Chiefly on Information About the Seen

242. Can Watermarked LLMs be Identified by Users via Crafted Prompts?

243. IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

244. Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

245. On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth

246. Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

247. Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization

248. Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency

249. Knowledge Localization: Mission Not Accomplished? Enter Query Localization!

250. Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors

251. Uncovering Overfitting in Large Language Model Editing

252. Effective post-training embedding compression via temperature control in contrastive training

253. Bundle Neural Network for message diffusion on graphs

254. Benchmarking Predictive Coding Networks -- Made Simple

255. Graph Neural Networks Can (Often) Count Substructures

256. LiveBench: A Challenging, Contamination-Limited LLM Benchmark

257. Emergent Orientation Maps —— Mechanisms, Coding Efficiency and Robustness

258. PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

259. UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization

260. Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization

261. Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

262. Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

263. Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

264. 4K4DGen: Panoramic 4D Generation at 4K Resolution

265. DEEM: Diffusion models serve as the eyes of large language models for image perception

266. Demystifying the Token Dynamics of Deep Selective State Space Models

267. Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

268. GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

269. Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

270. Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision

271. Retri3D: 3D Neural Graphics Representation Retrieval

272. CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

273. Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction

274. Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier

275. Control-oriented Clustering of Visual Latent Representation

276. No Need to Talk: Asynchronous Mixture of Language Models

277. Exploring Local Memorization in Diffusion Models via Bright Ending Attention

278. Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning

279. LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

280. TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

281. Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

282. ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish

283. Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

284. Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding

285. Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

286. OS-ATLAS: Foundation Action Model for Generalist GUI Agents

287. ThinK: Thinner Key Cache by Query-Driven Pruning

288. Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

289. Probabilistic Geometric Principal Component Analysis with application to neural data

290. CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph

291. MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

292. Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model

293. Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions

294. gRNAde: Geometric Deep Learning for 3D RNA inverse design

295. RESuM: A Rare Event Surrogate Model for Physics Detector Design

296. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

297. Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

298. MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

299. Online Reinforcement Learning in Non-Stationary Context-Driven Environments

300. ADIFF: Explaining audio difference using natural language

301. Controlling Language and Diffusion Models by Transporting Activations

302. Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

303. OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

304. Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models

305. Learning local equivariant representations for quantum operators

306. LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

307. MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

308. INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

309. Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

310. Preference Optimization for Reasoning with Pseudo Feedback

311. Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

312. SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

313. AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

314. PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

315. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

316. Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data

317. Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency

318. Modeling Complex System Dynamics with Flow Matching Across Time and Conditions

319. Understanding Factual Recall in Transformers via Associative Memories

320. MixEval-X: Any-to-any Evaluations from Real-world Data Mixture

321. Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

322. Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach

323. MamKO: Mamba-based Koopman operator for modeling and predictive control

324. Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation

325. Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

326. Bayesian Experimental Design Via Contrastive Diffusions

327. Mixture-of-Agents Enhances Large Language Model Capabilities

328. Uncovering Gaps in How Humans and LLMs Interpret Subjective Language

329. Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

330. ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences

331. Representative Guidance: Diffusion Model Sampling with Coherence

332. LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

333. Bilinear MLPs enable weight-based mechanistic interpretability

334. DRoP: Distributionally Robust Data Pruning

335. Vision Language Models are In-Context Value Learners

336. Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data

337. Conformal Prediction Sets Can Cause Disparate Impact

338. PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems

339. Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors

340. Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model

341. Strong Model Collapse

342. CBQ: Cross-Block Quantization for Large Language Models

343. Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

344. Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics

345. BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics

346. Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

347. Training-Free Activation Sparsity in Large Language Models

348. How Feature Learning Can Improve Neural Scaling Laws

349. Beyond Next Token Prediction: Patch-Level Training for Large Language Models

350. Exact Certification of (Graph) Neural Networks Against Label Poisoning

351. Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees

352. Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification

353. X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

354. TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

355. Wasserstein Distances, Neuronal Entanglement, and Sparsity

356. Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture

357. Online Preference Alignment for Language Models via Count-based Exploration

358. Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

359. BodyGen: Advancing Towards Efficient Embodiment Co-Design

360. Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

361. One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

362. Linear SCM Identification in the Presence of Confounders and Gaussian Noise

363. AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

364. NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics

365. MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

366. Harnessing Diversity for Important Data Selection in Pretraining Large Language Models

367. Generating Freeform Endoskeletal Robots

368. DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

369. Dense Video Object Captioning from Disjoint Supervision

370. Targeted Attack Improves Protection against Unauthorized Diffusion Customization

371. A Geometric Framework for Understanding Memorization in Generative Models

372. Recovering Manifold Structure Using Ollivier Ricci Curvature

373. Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

374. Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

375. Fine-tuning with Reserved Majority for Noise Reduction

376. Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models

377. Nesterov acceleration in benignly non-convex landscapes

378. Can Large Language Models Understand Symbolic Graphics Programs?

379. PABBO: Preferential Amortized Black-Box Optimization

380. Learning Transformer-based World Models with Contrastive Predictive Coding

381. Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

382. Competition Dynamics Shape Algorithmic Phases of In-Context Learning

383. DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

384. Topological Schrödinger Bridge Matching

385. Learning-Augmented Frequent Directions

386. Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

387. Learning to Solve Differential Equation Constrained Optimization Problems

388. Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

389. Fair Clustering in the Sliding Window Model

390. Language Model Alignment in Multilingual Trolley Problems

391. Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment

392. Biologically Constrained Barrel Cortex Model Integrates Whisker Inputs and Replicates Key Brain Network Dynamics

393. Linear Mode Connectivity in Differentiable Tree Ensembles

394. AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

395. SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

396. Nonlinear Sequence Embedding by Monotone Variational Inequality

397. On Disentangled Training for Nonlinear Transform in Learned Image Compression

398. InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

399. Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding

400. Regularization by Texts for Latent Diffusion Inverse Solvers

401. First-Person Fairness in Chatbots

402. MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

403. Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

404. Surprising Effectiveness of pretraining Ternary Language Model at Scale

405. Provable Uncertainty Decomposition via Higher-Order Calibration

406. TopoNets: High performing vision and language models with brain-like topography

407. Deep Learning Alternatives Of The Kolmogorov Superposition Theorem

408. Robustness Reprogramming for Representation Learning

409. Attention with Markov: A Curious Case of Single-layer Transformers

410. Higher-Order Graphon Neural Networks: Approximation and Cut Distance

411. Exploring the Camera Bias of Person Re-identification

412. Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

413. Meta-Dynamical State Space Models for Integrative Neural Data Analysis

414. Lean-STaR: Learning to Interleave Thinking and Proving

415. Revisiting Random Walks for Learning on Graphs

416. Progressive Compositionality in Text-to-Image Generative Models

417. ODE-based Smoothing Neural Network for Reinforcement Learning Tasks

418. How to Find the Exact Pareto Front for Multi-Objective MDPs?

419. Easing Training Process of Rectified Flow Models Via Lengthening Inter-Path Distance

420. FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

421. SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

422. Towards General-Purpose Model-Free Reinforcement Learning

423. The Computational Complexity of Circuit Discovery for Inner Interpretability

424. Learning from End User Data with Shuffled Differential Privacy over Kernel Densities

425. VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning

426. Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement

427. Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation

428. MorphoDiff: Cellular Morphology Painting with Diffusion Models

429. LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression

430. Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions

431. SoftCVI: Contrastive variational inference with self-generated soft labels

432. Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity

433. DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

434. u-$\mu$P: The Unit-Scaled Maximal Update Parametrization

435. Instance-dependent Early Stopping

436. Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels

437. Programming Refusal with Conditional Activation Steering

438. Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking

439. Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation

440. SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION

441. A Second-Order Perspective on Model Compositionality and Incremental Learning

442. Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes

443. Formation of Representations in Neural Networks

444. RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression

445. Towards Automated Knowledge Integration From Human-Interpretable Representations

446. Towards Marginal Fairness Sliced Wasserstein Barycenter

447. How new data permeates LLM knowledge and how to dilute it

448. TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

449. Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

450. Anti-Exposure Bias in Diffusion Models

451. Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs

452. 3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation

453. WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

454. Mitigating Memorization in Language Models

455. D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement

456. Following the Human Thread in Social Navigation

457. DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

458. CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

459. A Periodic Bayesian Flow for Material Generation

460. Generalized Principal-Agent Problem with a Learning Agent

461. Efficient and Accurate Explanation Estimation with Distribution Compression

462. Nonlinear multiregion neural dynamics with parametric impulse response communication channels

463. POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition

464. LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models

465. Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

466. OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes

467. TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks

468. Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression

469. Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction

470. PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

471. To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts

472. Active Task Disambiguation with LLMs

473. Systems with Switching Causal Relations: A Meta-Causal Perspective

474. Enhancing Learning with Label Differential Privacy by Vector Approximation

475. Multi-session, multi-task neural decoding from distinct cell-types and brain regions

476. Sparse components distinguish visual pathways & their alignment to neural networks

477. Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating

478. Tell me about yourself: LLMs are aware of their learned behaviors

479. CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

480. Differential learning kinetics govern the transition from memorization to generalization during in-context learning

481. Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression

482. Streamlining Redundant Layers to Compress Large Language Models

483. SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

484. Union-over-Intersections: Object Detection beyond Winner-Takes-All

485. DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization

486. Atlas Gaussians Diffusion for 3D Generation

487. Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

488. Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

489. Presto! Distilling Steps and Layers for Accelerating Music Generation

490. Grounding Video Models to Actions through Goal Conditioned Exploration

491. Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

492. Realistic Evaluation of Deep Partial-Label Learning Algorithms

493. EmbedLLM: Learning Compact Representations of Large Language Models

494. In Search of Forgotten Domain Generalization

495. Learning Equivariant Non-Local Electron Density Functionals

496. Differentiable Integer Linear Programming

497. Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling

498. Poison-splat: Computation Cost Attack on 3D Gaussian Splatting

499. Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

500. Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension

501. AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

502. Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences

503. Scaling FP8 training to trillion-token LLMs

504. Student-Informed Teacher Training

505. Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation

506. Estimating the Probabilities of Rare Outputs in Language Models

507. Imputation for prediction: beware of diminishing returns.

508. Physics-aligned field reconstruction with diffusion bridge

509. Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?

510. $R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

511. Test-time Adaptation for Cross-modal Retrieval with Query Shift

512. Severing Spurious Correlations with Data Pruning

513. Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance

514. Lightweight Neural App Control

515. DeLLMa: Decision Making Under Uncertainty with Large Language Models

516. Multi-Robot Motion Planning with Diffusion Models

517. ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks

518. MagicPIG: LSH Sampling for Efficient LLM Generation

519. Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

520. Hymba: A Hybrid-head Architecture for Small Language Models

521. AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

522. A CLIP-Powered Framework for Robust and Generalizable Data Selection

523. OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents

524. Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models

525. Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies

526. SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

527. When do GFlowNets learn the right distribution?

528. On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

529. Towards a Unified and Verified Understanding of Group-Operation Networks

530. DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

531. Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

532. Quality Measures for Dynamic Graph Generative Models

533. Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations

534. Better Instruction-Following Through Minimum Bayes Risk

535. LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-Tuning

536. Theory on Mixture-of-Experts in Continual Learning

537. Simplifying Deep Temporal Difference Learning

538. What Makes a Good Diffusion Planner for Decision Making?

539. Graph Sparsification via Mixture of Graphs

540. When Attention Sink Emerges in Language Models: An Empirical View

541. TabWak: A Watermark for Tabular Diffusion Models

542. Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition

543. MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

544. Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions

545. Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML

546. BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

547. COPER: Correlation-based Permutations for Multi-View Clustering

548. MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds

549. RegMix: Data Mixture as Regression for Language Model Pre-training

550. Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

551. Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

552. Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

553. Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks

554. ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction

555. Learning from negative feedback, or positive feedback or both

556. Planning in Natural Language Improves LLM Search for Code Generation

557. On Quantizing Neural Representation for Variable-Rate Video Coding

558. DiffPuter: Empowering Diffusion Models for Missing Data Imputation

559. What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis

560. Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space

561. LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models

562. Multi-Field Adaptive Retrieval

563. RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

564. Learning Spatiotemporal Dynamical Systems from Point Process Observations

565. uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

566. The Superposition of Diffusion Models Using the Itô Density Estimator

567. Towards hyperparameter-free optimization with differential privacy

568. Discovering Temporally Compositional Neural Manifolds with Switching Infinite GPFA

569. DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

570. DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

571. CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations

572. High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

573. NetMoE: Accelerating MoE Training through Dynamic Sample Placement

574. Bayesian Optimization via Continual Variational Last Layer Training

575. Fast Uncovering of Protein Sequence Diversity from Structure

576. Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images

577. MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code

578. OmniRe: Omni Urban Scene Reconstruction

579. In vivo cell-type and brain region classification via multimodal contrastive learning

580. Monitoring Latent World States in Language Models with Propositional Probes

581. Universal generalization guarantees for Wasserstein distributionally robust models

582. PETRA: Parallel End-to-end Training with Reversible Architectures

583. ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

584. Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

585. Holistically Evaluating the Environmental Impact of Creating Language Models

586. Adaptive Gradient Clipping for Robust Federated Learning

587. DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

588. Re-Imagining Multimodal Instruction Tuning: A Representation View

589. Inverse decision-making using neural amortized Bayesian actors

590. Designing Concise ConvNets with Columnar Stages

591. MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow

592. Let the Code LLM Edit Itself When You Edit the Code

593. Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

594. Generalizing Reasoning Problems to Longer Lengths

595. Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems

596. Understanding the Stability-based Generalization of Personalized Federated Learning

597. IgGM: A Generative Model for Functional Antibody and Nanobody Design

598. MMTEB: Massive Multilingual Text Embedding Benchmark

599. Ultra-Sparse Memory Network

600. Lines of Thought in Large Language Models

601. Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding

602. Exact Community Recovery under Side Information: Optimality of Spectral Algorithms

603. Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data

604. Deconstructing What Makes a Good Optimizer for Autoregressive Language Models

605. Dataset Ownership Verification in Contrastive Pre-trained Models

606. System 1.x: Learning to Balance Fast and Slow Planning with Language Models

607. Time-to-Event Pretraining for 3D Medical Imaging

608. Semialgebraic Neural Networks: From roots to representations

609. h4rm3l: A Language for Composable Jailbreak Attack Synthesis

610. Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition

611. Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning

612. Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity

613. To Code or Not To Code? Exploring Impact of Code in Pre-training

614. Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

615. Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies

616. Unified Parameter-Efficient Unlearning for LLMs

617. FreSh: Frequency Shifting for Accelerated Neural Representation Learning

618. EvA: Erasing Spurious Correlations with Activations

619. Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

620. RocketEval: Efficient automated LLM evaluation via grading checklist

621. Zero-cost Proxy for Adversarial Robustness Evaluation

622. A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery

623. Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles

624. Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

625. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

626. Differentiable Rule Induction from Raw Sequence Inputs

627. NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer

628. Group Ligands Docking to Protein Pockets

629. Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism

630. SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised Learning

631. EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning

632. Deep Kernel Relative Test for Machine-generated Text Detection

633. Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising

634. GOAL: A Generalist Combinatorial Optimization Agent Learner

635. Integral Performance Approximation for Continuous-Time Reinforcement Learning Control

636. FLOPS: Forward Learning with OPtimal Sampling

637. Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation

638. Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

639. LICO: Large Language Models for In-Context Molecular Optimization

640. SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

641. AutoBencher: Towards Declarative Benchmark Construction

642. DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training

643. ELFS: Label-Free Coreset Selection with Proxy Training Dynamics

644. Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

645. UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

646. Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration

647. Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models

648. On the expressiveness and spectral bias of KANs

649. Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

650. AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements

651. ThermalGaussian: Thermal 3D Gaussian Splatting

652. Scaling Wearable Foundation Models

653. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

654. Language-Image Models with 3D Understanding

655. NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

656. Generative Monoculture in Large Language Models

657. Accelerating Diffusion Transformers with Token-wise Feature Caching

658. Point-SAM: Promptable 3D Segmentation Model for Point Clouds

659. Towards Understanding the Universality of Transformers for Next-Token Prediction

660. Disentangling Representations through Multi-task Learning

661. APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

662. Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

663. Causally Motivated Sycophancy Mitigation for Large Language Models

664. Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron

665. Pacmann: Efficient Private Approximate Nearest Neighbor Search

666. Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

667. ReCogLab: a framework testing relational reasoning & cognitive hypotheses on LLMs

668. MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models

669. HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

670. On the Price of Differential Privacy for Hierarchical Clustering

671. Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers

672. A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations

673. Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

674. Image and Video Tokenization with Binary Spherical Quantization

675. Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

676. Simple, Good, Fast: Self-Supervised World Models Free of Baggage

677. MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation

678. UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

679. Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approach

680. GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks

681. WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

682. RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

683. Quality over Quantity in Attention Layers: When Adding More Heads Hurts

684. Language Agents Meet Causality -- Bridging LLMs and Causal World Models

685. Sort-free Gaussian Splatting via Weighted Sum Rendering

686. Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

687. PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations

688. Boosting Latent Diffusion with Perceptual Objectives

689. HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

690. PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

691. Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

692. InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

693. PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

694. EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models

695. SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models

696. Feature-Based Online Bilateral Trade

697. MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

698. Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

699. SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

700. Revisiting In-context Learning Inference Circuit in Large Language Models

701. Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

702. Vector-ICL: In-context Learning with Continuous Vector Representations

703. A Generic Framework for Conformal Fairness

704. Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

705. MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

706. Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

707. Deep Signature: Characterization of Large-Scale Molecular Dynamics

708. Diffusion Models are Evolutionary Algorithms

709. Structural-Entropy-Based Sample Selection for Efficient and Effective Learning

710. Consistency Models Made Easy

711. Context Steering: Controllable Personalization at Inference Time

712. Reflective Gaussian Splatting

713. Optimal Transport for Time Series Imputation

714. UniRestore3D: A Scalable Framework For General Shape Restoration

715. Endless Jailbreaks with Bijection Learning

716. Learning General-purpose Biomedical Volume Representations using Randomized Synthesis

717. Discrete Distribution Networks

718. EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

719. SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents

720. Language Models Learn to Mislead Humans via RLHF

721. Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer

722. MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

723. Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences

724. (Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning

725. A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals

726. Isometric Regularization for Manifolds of Functional Data

727. Beware of Calibration Data for Pruning Large Language Models

728. SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

729. Active Learning for Neural PDE Solvers

730. Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation Compression

731. SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

732. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

733. Advancing Graph Generation through Beta Diffusion

734. Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires

735. ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning

736. Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement

737. BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

738. Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise

739. Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

740. Learning Evolving Tools for Large Language Models

741. Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

742. A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

743. GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians

744. Improving Instruction-Following in Language Models through Activation Steering

745. Scaling Autonomous Agents via Automatic Reward Modeling And Planning

746. Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

747. PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores

748. Learning to Communicate Through Implicit Communication Channels

749. RESfM: Robust Deep Equivariant Structure from Motion

750. Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators

751. ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

752. Aligning Visual Contrastive learning models via Preference Optimization

753. MGDA Converges under Generalized Smoothness, Provably

754. Making Text Embedders Few-Shot Learners

755. A Solvable Attention for Neural Scaling Laws

756. ST-GCond: Self-supervised and Transferable Graph Dataset Condensation

757. Learning Successor Features with Distributed Hebbian Temporal Memory

758. Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct

759. When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

760. SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs

761. FlashMask: Efficient and Rich Mask Extension of FlashAttention

762. Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

763. On Calibration of LLM-based Guard Models for Reliable Content Moderation

764. TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

765. SBSC: Step-by-Step Coding for Improving Mathematical Olympiad Performance

766. NRGBoost: Energy-Based Generative Boosted Trees

767. Process Reward Model with Q-value Rankings

768. LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases

769. Credit-based self organizing maps: training deep topographic networks with minimal performance degradation

770. Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions

771. LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace

772. Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks?

773. Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

774. Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval

775. SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

776. Tree of Attributes Prompt Learning for Vision-Language Models

777. Expected Return Symmetries

778. Intrinsic User-Centric Interpretability through Global Mixture of Experts

779. LongVILA: Scaling Long-Context Visual Language Models for Long Videos

780. Is Large-scale Pretraining the Secret to Good Domain Generalization?

781. Modeling dynamic social vision highlights gaps between deep learning and humans

782. Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training

783. Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging

784. Counterfactual Concept Bottleneck Models

785. PIED: Physics-Informed Experimental Design for Inverse Problems

786. In-Context Editing: Learning Knowledge from Self-Induced Distributions

787. To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

788. Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field Generation

789. Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation

790. Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models

791. Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control

792. DistillHGNN: A Knowledge Distillation Approach for High-Speed Hypergraph Neural Networks

793. DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

794. Image-level Memorization Detection via Inversion-based Inference Perturbation

795. Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks

796. Benchmarking Agentic Workflow Generation

797. MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation

798. Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language Models

799. Difference-of-submodular Bregman Divergence

800. Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost

801. On the Modeling Capabilities of Large Language Models for Sequential Decision Making

802. Training-free LLM-generated Text Detection by Mining Token Probability Sequences

803. Revolutionizing EMCCD Denoising through a Novel Physics-Based Learning Framework for Noise Modeling

804. $F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos

805. IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning

806. Text4Seg: Reimagining Image Segmentation as Text Generation

807. Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models

808. Scalable Extraction of Training Data from Aligned, Production Language Models

809. DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation

810. SWEb: A Large Web Dataset for the Scandinavian Languages

811. High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

812. MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI

813. Neural Approximate Mirror Maps for Constrained Diffusion Models

814. Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement Learning

815. Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence

816. VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?

817. Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization

818. Differentiable Optimization of Similarity Scores Between Models and Brains

819. Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

820. The Pitfalls of Memorization: When Memorization Hurts Generalization

821. RecFlow: An Industrial Full Flow Recommendation Dataset

822. DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

823. ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination

824. Scaling Laws for Downstream Task Performance in Machine Translation

825. Stochastic Bandits Robust to Adversarial Attacks

826. Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries

827. KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models

828. Long-tailed Adversarial Training with Self-Distillation

829. Latent Radiance Fields with 3D-aware 2D Representations

830. Learning View-invariant World Models for Visual Robotic Manipulation

831. Memory Efficient Transformer Adapter for Dense Predictions

832. Logic-Logit: A Logic-Based Approach to Choice Modeling

833. The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs

834. Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning

835. Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing

836. OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework

837. PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows

838. Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

839. MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

840. Multimodal Quantitative Language for Generative Recommendation

841. Does SGD really happen in tiny subspaces?

842. Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

843. PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

844. Decoupled Subgraph Federated Learning

845. AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

846. Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure

847. Selective Attention Improves Transformer

848. VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

849. Reconciling Model Multiplicity for Downstream Decision Making

850. Unbounded: A Generative Infinite Game of Character Life Simulation

851. Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

852. FlowDec: A flow-based full-band general audio codec with high perceptual quality

853. IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations

854. Towards Certification of Uncertainty Calibration under Adversarial Attacks

855. VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology

856. TODO: Enhancing LLM Alignment with Ternary Preferences

857. Deep Kernel Posterior Learning under Infinite Variance Prior Weights

858. Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data

859. Trajectory-Class-Aware Multi-Agent Reinforcement Learning

860. EG4D: Explicit Generation of 4D Object without Score Distillation

861. The impact of allocation strategies in subset learning on the expressive power of neural networks

862. Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning

863. Weak-to-Strong Generalization Through the Data-Centric Lens

864. VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

865. OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs

866. Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks

867. ScImage: How good are multimodal large language models at scientific text-to-image generation?

868. Discriminating image representations with principal distortions

869. Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

870. The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws

871. Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

872. Data Distillation for extrapolative protein design through exact preference optimization

873. Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models

874. Zero-shot Model-based Reinforcement Learning using Large Language Models

875. Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

876. LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation

877. Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning

878. ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing

879. SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

880. CryoGEN: Generative Energy-based Models for Cryogenic Electron Tomography Reconstruction

881. Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space

882. Score-based Self-supervised MRI Denoising

883. NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens

884. Efficiently Parameterized Neural Metriplectic Systems

885. UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models

886. SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins

887. Dimension Agnostic Neural Processes

888. Benchmarking LLMs' Judgments with No Gold Standard

889. Learning Partial Graph Matching via Optimal Partial Transport

890. Towards Neural Scaling Laws for Time Series Foundation Models

891. Compositional simulation-based inference for time series

892. Jailbreaking as a Reward Misspecification Problem

893. Equivariant Neural Functional Networks for Transformers

894. Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters

895. Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

896. Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithm

897. SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

898. Context-aware Dynamic Pruning for Speech Foundation Models

899. On the Performance Analysis of Momentum Method: A Frequency Domain Perspective

900. PEARL: Towards Permutation-Resilient LLMs

901. RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

902. Near-Exact Privacy Amplification for Matrix Mechanisms

903. A Coefficient Makes SVRG Effective

904. Cross-Embodiment Dexterous Grasping with Reinforcement Learning

905. On Generalization Across Environments In Multi-Objective Reinforcement Learning

906. Composable Interventions for Language Models

907. Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions

908. Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology

909. Accelerating Neural ODEs: A Variational Formulation-based Approach

910. RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization

911. Physics-Informed Diffusion Models

912. ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs

913. Improving Large Language Model Planning with Action Sequence Similarity

914. Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

915. Heavy-Tailed Diffusion Models

916. Rethinking Multiple-Instance Learning From Feature Space to Probability Space

917. KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

918. DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

919. Learning the Complexity of Weakly Noisy Quantum States

920. RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

921. An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

922. BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

923. Rationalizing and Augmenting Dynamic Graph Neural Networks

924. Training-Free Diffusion Model Alignment with Sampling Demons

925. Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation

926. Scaling Long Context Training Data by Long-Distance Referrals

927. Gradient-Free Generation for Hard-Constrained Systems

928. JPEG Inspired Deep Learning

929. A Theory for Token-Level Harmonization in Retrieval-Augmented Generation

930. Dynamic Diffusion Transformer

931. Backdooring Vision-Language Models with Out-Of-Distribution Data

932. Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them

933. MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

934. COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation

935. Precedence-Constrained Winter Value for Effective Graph Data Valuation

936. Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

937. AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

938. Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

939. MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

940. Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation

941. PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

942. Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure

943. GLOMA: Global Video Text Spotting with Morphological Association

944. SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction

945. Diffusion Feedback Helps CLIP See Better

946. SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

947. MiniPLM: Knowledge Distillation for Pre-training Language Models

948. Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings

949. ElasticTok: Adaptive Tokenization for Image and Video

950. ThinkBot: Embodied Instruction Following with Thought Chain Reasoning

951. Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

952. Quantum (Inspired) $D^2$-sampling with Applications

953. Adversarial Generative Flow Network for Solving Vehicle Routing Problems

954. A Simple Approach to Unifying Diffusion-based Conditional Generation

955. Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

956. Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

957. Automated Design of Agentic Systems

958. Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation

959. Sparse Learning for State Space Models on Mobile

960. Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

961. On the Benefits of Attribute-Driven Graph Domain Adaptation

962. Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary

963. Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series

964. U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

965. SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

966. TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation

967. Adversarial Machine Unlearning

968. Adding Conditional Control to Diffusion Models with Reinforcement Learning

969. How efficient is LLM-generated code? A rigorous & high-standard benchmark

970. Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

971. Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

972. Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning

973. Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

974. Flow-based Variational Mutual Information: Fast and Flexible Approximations

975. Towards Learning High-Precision Least Squares Algorithms with Sequence Models

976. MetaMetrics: Calibrating Metrics for Generation Tasks Using Human Preferences

977. Neural Spacetimes for DAG Representation Learning

978. Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

979. BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP

980. Semantix: An Energy-guided Sampler for Semantic Style Transfer

981. Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

982. Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix

983. JetFormer: An autoregressive generative model of raw images and text

984. FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields

985. PiCO: Peer Review in LLMs based on Consistency Optimization

986. Density estimation with LLMs: a geometric investigation of in-context learning trajectories

987. nGPT: Normalized Transformer with Representation Learning on the Hypersphere

988. Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

989. pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

990. CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation

991. C-CLIP: Multimodal Continual Learning for Vision-Language Model

992. Offline Model-Based Optimization by Learning to Rank

993. Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models

994. Aioli: A Unified Optimization Framework for Language Model Data Mixing

995. Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

996. Implicit Neural Surface Deformation with Explicit Velocity Fields

997. Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark

998. Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

999. 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering

1000. One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

1001. Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

1002. MAST: model-agnostic sparsified training

1003. Group Downsampling with Equivariant Anti-aliasing

1004. Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

1005. Flow: Modularized Agentic Workflow Automation

1006. Energy-Based Diffusion Language Models for Text Generation

1007. Understanding Optimization in Deep Learning with Central Flows

1008. Temporal Reasoning Transfer from Text to Video

1009. Your Weak LLM is Secretly a Strong Teacher for Alignment

1010. ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

1011. Adaptive Energy Alignment for Accelerating Test-Time Adaptation

1012. Partial Gromov-Wasserstein Metric

1013. Personalized Visual Instruction Tuning

1014. Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model

1015. DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints

1016. Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

1017. Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

1018. Robust LLM safeguarding via refusal feature adversarial training

1019. MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

1020. What Are Good Positional Encodings for Directed Graphs?

1021. Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs

1022. Language Models Need Inductive Biases to Count Inductively

1023. Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

1024. Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models

1025. Swing-by Dynamics in Concept Learning and Compositional Generalization

1026. An Evolved Universal Transformer Memory

1027. On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

1028. VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

1029. TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

1030. Minimal Impact ControlNet: Advancing Multi-ControlNet Integration

1031. Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints

1032. Training-Free Dataset Pruning for Instance Segmentation

1033. From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy

1034. Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation

1035. Robust Transfer of Safety-Constrained Reinforcement Learning Agents

1036. Online-to-Offline RL for Agent Alignment

1037. Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

1038. Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling

1039. ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

1040. {$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World Domains

1041. Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior

1042. Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks

1043. OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

1044. Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

1045. Learning system dynamics without forgetting

1046. UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition

1047. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

1048. Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

1049. DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image

1050. High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

1051. Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

1052. Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models

1053. CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design

1054. Lossy Compression with Pretrained Diffusion Models

1055. MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling

1056. PaLD: Detection of Text Partially Written by Large Language Models

1057. Graph Transformers Dream of Electric Flow

1058. $InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration

1059. Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

1060. Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers

1061. PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks

1062. Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

1063. Biologically Plausible Brain Graph Transformer

1064. Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

1065. A Causal Lens for Learning Long-term Fair Policies

1066. Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises

1067. Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

1068. N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning

1069. Systematic Outliers in Large Language Models

1070. Protecting against simultaneous data poisoning attacks

1071. SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation

1072. Generating Likely Counterfactuals Using Sum-Product Networks

1073. Metric-Driven Attributions for Vision Transformers

1074. Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

1075. TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting

1076. Exposure Bracketing Is All You Need For A High-Quality Image

1077. Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

1078. Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions

1079. A Statistical Framework for Ranking LLM-based Chatbots

1080. OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

1081. TULIP: Token-length Upgraded CLIP

1082. Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

1083. Gated Delta Networks: Improving Mamba2 with Delta Rule

1084. Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates

1085. Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction

1086. Monte Carlo Planning with Large Language Model for Text-Based Game Agents

1087. What's the Move? Hybrid Imitation Learning via Salient Points

1088. Breaking the Reclustering Barrier in Centroid-based Deep Clustering

1089. Spiking Vision Transformer with Saccadic Attention

1090. Balancing Bias in Two-sided Markets for Fair Stable Matchings

1091. Locality Alignment Improves Vision-Language Models

1092. ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset

1093. Do LLM Agents Have Regret? A Case Study in Online Learning and Games

1094. Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL

1095. PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks

1096. ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble

1097. Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data

1098. Causal Effect Estimation with Mixed Latent Confounders and Post-treatment Variables

1099. Generalized Video Moment Retrieval

1100. How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.

1101. Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling

1102. Decoupled Finetuning for Domain Generalizable Semantic Segmentation

1103. LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

1104. econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians

1105. GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

1106. Laplace Sample Information: Data Informativeness Through a Bayesian Lens

1107. Systematic Relational Reasoning With Epistemic Graph Neural Networks

1108. Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks

1109. CoMotion: Concurrent Multi-person 3D Motion

1110. Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

1111. MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

1112. Do LLMs ``know'' internally when they follow instructions?

1113. Multi-Perspective Data Augmentation for Few-shot Object Detection

1114. Homomorphism Counts as Structural Encodings for Graph Learning

1115. A new framework for evaluating model out-of-distribution generalisation for the biochemical domain

1116. SFESS: Score Function Estimators for $k$-Subset Sampling

1117. How many samples are needed to train a deep neural network?

1118. Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks

1119. HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

1120. VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning

1121. $\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

1122. Forgetting Transformer: Softmax Attention with a Forget Gate

1123. CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark

1124. Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

1125. Rethinking Invariance in In-context Learning

1126. Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

1127. On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

1128. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

1129. AdaFisher: Adaptive Second Order Optimization via Fisher Information

1130. Learning from Imperfect Human Feedback: A Tale from Corruption-Robust Dueling

1131. mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

1132. UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping

1133. Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis

1134. Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference

1135. ESE: Espresso Sentence Embeddings

1136. Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

1137. Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories

1138. Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

1139. Random-Set Neural Networks

1140. SOREL: A Stochastic Algorithm for Spectral Risks Minimization

1141. Encryption-Friendly LLM Architecture

1142. TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data

1143. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

1144. ICLR: In-Context Learning of Representations

1145. Explanations of GNN on Evolving Graphs via Axiomatic Layer edges

1146. Streamlining Prediction in Bayesian Deep Learning

1147. Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models

1148. TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction

1149. Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

1150. Boltzmann priors for Implicit Transfer Operators

1151. Diverse Preference Learning for Capabilities and Alignment

1152. CONTRA: Conformal Prediction Region via Normalizing Flow Transformation

1153. Bayesian WeakS-to-Strong from Text Classification to Generation

1154. Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine

1155. Distribution-Free Data Uncertainty for Neural Network Regression

1156. Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

1157. A Generalist Hanabi Agent

1158. Rethinking Fair Representation Learning for Performance-Sensitive Tasks

1159. Generative Flows on Synthetic Pathway for Drug Design

1160. Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation

1161. FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

1162. XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

1163. Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

1164. Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

1165. NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

1166. Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions

1167. A Benchmark for Semantic Sensitive Information in LLMs Outputs

1168. Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models

1169. Spreading Out-of-Distribution Detection on Graphs

1170. Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks

1171. Solving New Tasks by Adapting Internet Video Knowledge

1172. Learning Causal Alignment for Reliable Disease Diagnosis

1173. Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

1174. GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

1175. Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

1176. Stable Segment Anything Model

1177. Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

1178. Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization

1179. Large (Vision) Language Models are Unsupervised In-Context Learners

1180. ColPali: Efficient Document Retrieval with Vision Language Models

1181. Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning

1182. SpinQuant: LLM Quantization with Learned Rotations

1183. Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding

1184. On the Byzantine-Resilience of Distillation-Based Federated Learning

1185. OMG: Opacity Matters in Material Modeling with Gaussian Splatting

1186. Counterfactual Generative Modeling with Variational Causal Inference

1187. Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

1188. Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

1189. SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

1190. Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift

1191. Support is All You Need for Certified VAE Training

1192. Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

1193. Learning Graph Quantized Tokenizers

1194. Dynamic Low-Rank Sparse Adaptation for Large Language Models

1195. AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

1196. WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

1197. Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

1198. Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

1199. Track-On: Transformer-based Online Point Tracking with Memory

1200. DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

1201. Kernel-based Optimally Weighted Conformal Time-Series Prediction

1202. Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

1203. Adversarial Attacks on Data Attribution

1204. Variance-Reducing Couplings for Random Features

1205. FaceShot: Bring Any Character into Life

1206. Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

1207. TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights

1208. Physics of Language Models: Part 3.2, Knowledge Manipulation

1209. Analytic DAG Constraints for Differentiable DAG Learning

1210. Generative Classifiers Avoid Shortcut Solutions

1211. SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting

1212. Looking into User’s Long-term Interests through the Lens of Conservative Evidential Learning

1213. Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

1214. Strategic Classification With Externalities

1215. EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

1216. ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning

1217. An Effective Manifold-based Optimization Method for Distributionally Robust Classification

1218. ContextGNN: Beyond Two-Tower Recommendation Systems

1219. Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control

1220. Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance

1221. Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

1222. DynFrs: An Efficient Framework for Machine Unlearning in Random Forest

1223. Chunk-Distilled Language Modeling

1224. Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning

1225. Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision Models

1226. Multi-Scale Fusion for Object Representation

1227. MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction

1228. Neural Causal Graph for Interpretable and Intervenable Classification

1229. NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

1230. Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

1231. KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics

1232. The Unreasonable Ineffectiveness of the Deeper Layers

1233. ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

1234. Visual Agents as Fast and Slow Thinkers

1235. Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy

1236. InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

1237. Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

1238. Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

1239. CAMEx: Curvature-aware Merging of Experts

1240. ONLINE EPSILON NET & PIERCING SET FOR GEOMETRIC CONCEPTS

1241. ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler

1242. Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error

1243. Scale-Free Graph-Language Models

1244. YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus

1245. Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

1246. Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

1247. Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

1248. Causal Information Prioritization for Efficient Reinforcement Learning

1249. HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics

1250. Distilling Dataset into Neural Field

1251. TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

1252. Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations

1253. Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems

1254. cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM

1255. PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

1256. Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis

1257. Towards Semantic Equivalence of Tokenization in Multimodal LLM

1258. Linear combinations of latents in generative models: subspaces and beyond

1259. Learning mirror maps in policy mirror descent

1260. A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems

1261. Shedding Light on Time Series Classification using Interpretability Gated Networks

1262. Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging

1263. MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation

1264. Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

1265. Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity

1266. Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation

1267. From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics

1268. TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

1269. Towards Federated RLHF with Aggregated Client Preference for LLMs

1270. Subtask-Aware Visual Reward Learning from Segmented Demonstrations

1271. From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

1272. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

1273. Quamba: A Post-Training Quantization Recipe for Selective State Space Models

1274. Active Learning for Continual Learning: Keeping the Past Alive in the Present

1275. Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation

1276. SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark

1277. Associative memory and dead neurons

1278. Preble: Efficient Distributed Prompt Scheduling for LLM Serving

1279. From Tokens to Lattices: Emergent Lattice Structures in Language Models

1280. Adaptive Length Image Tokenization via Recurrent Allocation

1281. HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

1282. Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs

1283. E(3)-equivariant models cannot learn chirality: Field-based molecular generation

1284. A General Framework for Off-Policy Learning with Partially-Observed Reward

1285. Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection

1286. CipherPrune: Efficient and Scalable Private Transformer Inference

1287. OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

1288. Last Iterate Convergence of Incremental Methods as a Model of Forgetting

1289. Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models

1290. AgentSquare: Automatic LLM Agent Search in Modular Design Space

1291. GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting

1292. DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing

1293. Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

1294. ParetoFlow: Guided Flows in Multi-Objective Optimization

1295. GOFA: A Generative One-For-All Model for Joint Graph Language Modeling

1296. Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming

1297. Diffusion Policy Policy Optimization

1298. Image Watermarks are Removable using Controllable Regeneration from Clean Noise

1299. Coreset Selection via Reducible Loss in Continual Learning

1300. Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax

1301. Is Your Video Language Model a Reliable Judge?

1302. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

1303. AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption

1304. Bridging the Gap Between f-divergences and Bayes Hilbert Spaces

1305. Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View

1306. An Engorgio Prompt Makes Large Language Model Babble on

1307. CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression

1308. Tracking objects that change in appearance with phase synchrony

1309. CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching

1310. Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

1311. Predicate Hierarchies Improve Few-Shot State Classification

1312. Robust Conformal Prediction with a Single Binary Certificate

1313. Is uniform expressivity too restrictive? Towards efficient expressivity of GNNs

1314. SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs

1315. Multi-Dimensional Conformal Prediction

1316. From Promise to Practice: Realizing High-performance Decentralized Training

1317. Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning

1318. Point-based Instance Completion with Scene Constraints

1319. Hidden in the Noise: Two-Stage Robust Watermarking for Images

1320. Unifying Causal Representation Learning with the Invariance Principle

1321. Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

1322. Discrete Codebook World Models for Continuous Control

1323. ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

1324. Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning

1325. CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding

1326. Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning

1327. Task Descriptors Help Transformers Learn Linear Models In-Context

1328. Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods

1329. Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models

1330. Enhancing Robust Fairness via Confusional Spectral Regularization

1331. TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

1332. PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-Task

1333. HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts

1334. Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

1335. DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

1336. Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

1337. Efficient Top-m Data Values Identification for Data Selection

1338. Differentially Private Steering for Large Language Model Alignment

1339. Diversity-Rewarded CFG Distillation

1340. Agent S: An Open Agentic Framework that Uses Computers Like a Human

1341. Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery

1342. Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

1343. Catastrophic Failure of LLM Unlearning via Quantization

1344. RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception

1345. Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?

1346. BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

1347. Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features

1348. Gaussian Mixture Counterfactual Generator

1349. CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling

1350. Enhancing Graph Of Thought: Enhancing Prompts with LLM Rationales and Dynamic Temperature Control

1351. HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

1352. OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

1353. Robust Root Cause Diagnosis using In-Distribution Interventions

1354. Taming Overconfidence in LLMs: Reward Calibration in RLHF

1355. Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection

1356. Ensembles of Low-Rank Expert Adapters

1357. Semi-Parametric Retrieval via Binary Bag-of-Tokens Index

1358. FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware

1359. One for all and all for one: Efficient computation of partial Wasserstein distances on the line

1360. Collapsed Language Models Promote Fairness

1361. InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly

1362. INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning

1363. Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment

1364. Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

1365. Provably Safeguarding a Classifier from OOD and Adversarial Samples

1366. Transformer Block Coupling and its Correlation with Generalization in LLMs

1367. ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning

1368. Addressing Label Shift in Distributed Learning via Entropy Regularization​

1369. Circuit Transformer: A Transformer That Preserves Logical Equivalence

1370. RMB: Comprehensively benchmarking reward models in LLM alignment

1371. MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder

1372. Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness

1373. Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

1374. BenTo: Benchmark Reduction with In-Context Transferability

1375. Boosting the visual interpretability of CLIP via adversarial fine-tuning

1376. Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

1377. No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs

1378. Neural Wave Equation for Irregularly Sampled Sequence Data

1379. Re-evaluating Open-ended Evaluation of Large Language Models

1380. Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

1381. PaPaGei: Open Foundation Models for Optical Physiological Signals

1382. Diffusing States and Matching Scores: A New Framework for Imitation Learning

1383. Ward: Provable RAG Dataset Inference via LLM Watermarks

1384. Node-Time Conditional Prompt Learning in Dynamic Graphs

1385. Safety Layers in Aligned Large Language Models: The Key to LLM Security

1386. StringLLM: Understanding the String Processing Capability of Large Language Models

1387. Open-Set Graph Anomaly Detection via Normal Structure Regularisation

1388. ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning

1389. Beyond single neurons: population response geometry in digital twins of mouse visual cortex

1390. Diffusion State-Guided Projected Gradient for Inverse Problems

1391. AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data

1392. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

1393. CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators

1394. DeeperForward: Enhanced Forward-Forward Training for Deeper and Better Performance

1395. Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems

1396. Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs

1397. Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models

1398. PolaFormer: Polarity-aware Linear Attention for Vision Transformers

1399. Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment

1400. ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents

1401. Learning Long Range Dependencies on Graphs via Random Walks

1402. MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

1403. Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function

1404. RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data

1405. Efficient Dictionary Learning with Switch Sparse Autoencoders

1406. Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

1407. DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

1408. Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context

1409. Personalized Representation from Personalized Generation

1410. CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning

1411. Neural Phylogeny: Fine-Tuning Relationship Detection among Neural Networks

1412. Indirect Gradient Matching for Adversarial Robust Distillation

1413. CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models

1414. Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration

1415. Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

1416. Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods

1417. Quantifying Generalization Complexity for Large Language Models

1418. To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions

1419. The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modeling

1420. An Undetectable Watermark for Generative Image Models

1421. Long-Sequence Recommendation Models Need Decoupled Embeddings

1422. OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

1423. U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models

1424. Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

1425. The AdEMAMix Optimizer: Better, Faster, Older

1426. SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

1427. VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning

1428. AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly

1429. Extending Mercer's expansion to indefinite and asymmetric kernels

1430. Learning Interleaved Image-Text Comprehension in Vision-Language Large Models

1431. Large Language Models can Become Strong Self-Detoxifiers

1432. UniDrive: Towards Universal Driving Perception Across Camera Configurations

1433. HeadMap: Locating and Enhancing Knowledge Circuits in LLMs

1434. AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models

1435. Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

1436. Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation

1437. On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions

1438. ComLoRA: A Competitive Learning Approach for Enhancing LoRA

1439. BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation

1440. Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

1441. EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHING

1442. Competitive Fair Scheduling with Predictions

1443. ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention

1444. Attribute-based Visual Reprogramming for Vision-Language Models

1445. Minimalistic Predictions for Online Class Constraint Scheduling

1446. Diffusion-based Neural Network Weights Generation

1447. OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

1448. Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

1449. Optimizing importance weighting in the presence of sub-population shifts

1450. Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster

1451. Scaling Diffusion Language Models via Adaptation from Autoregressive Models

1452. WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

1453. Noisy Test-Time Adaptation in Vision-Language Models

1454. CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

1455. Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

1456. Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks

1457. Action abstractions for amortized sampling

1458. Risk-Sensitive Variational Actor-Critic: A Model-Based Approach

1459. Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

1460. Connecting Federated ADMM to Bayes

1461. Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

1462. M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model

1463. Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

1464. Sparse autoencoders reveal selective remapping of visual concepts during adaptation

1465. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

1466. The Value of Sensory Information to a Robot

1467. Representational Similarity via Interpretable Visual Concepts

1468. SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

1469. Fast and Accurate Blind Flexible Docking

1470. Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences

1471. Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback

1472. THE ROBUSTNESS OF DIFFERENTIABLE CAUSAL DISCOVERY IN MISSPECIFIED SCENARIOS

1473. Uncertainty modeling for fine-tuned implicit functions

1474. Language models scale reliably with over-training and on downstream tasks

1475. PaCA: Partial Connection Adaptation for Efficient Fine-Tuning

1476. End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler

1477. Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning

1478. REMEDY: Recipe Merging Dynamics in Large Vision-Language Models

1479. Selective Aggregation for Low-Rank Adaptation in Federated Learning

1480. DeciMamba: Exploring the Length Extrapolation Potential of Mamba

1481. LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

1482. Can We Talk Models Into Seeing the World Differently?

1483. ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

1484. Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification

1485. Fast Summation of Radial Kernels via QMC Slicing

1486. Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold

1487. Why In-Context Learning Models are Good Few-Shot Learners?

1488. 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

1489. Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models

1490. Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

1491. DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding

1492. Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

1493. Near-optimal Active Regression of Single-Index Models

1494. The Optimization Landscape of SGD Across the Feature Learning Strength

1495. Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion

1496. EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

1497. Adam-mini: Use Fewer Learning Rates To Gain More

1498. Improving Graph Neural Networks by Learning Continuous Edge Directions

1499. MuPT: A Generative Symbolic Music Pretrained Transformer

1500. Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs

1501. Minimax Optimal Reinforcement Learning with Quasi-Optimism

1502. Interpreting Language Reward Models via Contrastive Explanations

1503. Lipschitz Bandits in Optimal Space

1504. Bootstrapped Model Predictive Control

1505. Disentangling 3D Animal Pose Dynamics with Scrubbed Conditional Latent Variables

1506. Simple Guidance Mechanisms for Discrete Diffusion Models

1507. MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

1508. Language Guided Skill Discovery

1509. Valid Conformal Prediction for Dynamic GNNs

1510. ECHOPulse: ECG Controlled Echocardio-gram Video Generation

1511. SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

1512. Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization

1513. Deep Distributed Optimization for Large-Scale Quadratic Programming

1514. Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

1515. Neural Stochastic Differential Equations for Uncertainty-Aware Offline RL

1516. DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle

1517. Improving Pretraining Data Using Perplexity Correlations

1518. Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

1519. GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack

1520. Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

1521. Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs

1522. TDDBench: A Benchmark for Training data detection

1523. AutoG: Towards automatic graph construction from tabular data

1524. DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

1525. Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

1526. Can Knowledge Editing Really Correct Hallucinations?

1527. OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination

1528. Adversarial Search Engine Optimization for Large Language Models

1529. Causal Representation Learning from Multimodal Biomedical Observations

1530. Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

1531. Mixture Compressor for Mixture-of-Experts LLMs Gains More

1532. Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

1533. Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy

1534. SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

1535. Causal Graphical Models for Vision-Language Compositional Understanding

1536. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

1537. Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection

1538. Privately Counting Partially Ordered Data

1539. Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

1540. Large Language Models are Interpretable Learners

1541. No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data

1542. Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

1543. DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors

1544. Uncertainty-Aware Decoding with Minimum Bayes Risk

1545. GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

1546. Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

1547. PWM: Policy Learning with Multi-Task World Models

1548. SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection

1549. OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?

1550. NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics

1551. GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering

1552. Real-Time Video Generation with Pyramid Attention Broadcast

1553. HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation

1554. Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

1555. Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods

1556. Sharpness-Aware Black-Box Optimization

1557. Model Risk-sensitive Offline Reinforcement Learning

1558. BANGS: Game-theoretic Node Selection for Graph Self-Training

1559. RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval

1560. Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

1561. Sensitivity Verification for Additive Decision Tree Ensembles

1562. An Auditing Test to Detect Behavioral Shift in Language Models

1563. Rethinking the role of frames for SE(3)-invariant crystal structure modeling

1564. Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation

1565. PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

1566. T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data

1567. Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

1568. Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability

1569. Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

1570. Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models

1571. Rethinking Visual Counterfactual Explanations Through Region Constraint

1572. A Conditional Independence Test in the Presence of Discretization

1573. Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

1574. ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models

1575. Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

1576. SCBench: A KV Cache-Centric Analysis of Long-Context Methods

1577. Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

1578. GraphBridge: Towards Arbitrary Transfer Learning in GNNs

1579. Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation

1580. Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

1581. Precise Parameter Localization for Textual Generation in Diffusion Models

1582. LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

1583. MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval

1584. A Truncated Newton Method for Optimal Transport

1585. Depth Any Video with Scalable Synthetic Data

1586. Residual-MPPI: Online Policy Customization for Continuous Control

1587. Efficient Biological Data Acquisition through Inference Set Design

1588. Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining

1589. RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction

1590. Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?

1591. DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

1592. Scalable Influence and Fact Tracing for Large Language Model Pretraining

1593. Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization

1594. Safety Representations for Safer Policy Learning

1595. Integrative Decoding: Improving Factuality via Implicit Self-consistency

1596. CrossMPT: Cross-attention Message-passing Transformer for Error Correcting Codes

1597. Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks

1598. Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

1599. GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring

1600. Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation

1601. Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

1602. Multi-domain Distribution Learning for De Novo Drug Design

1603. Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

1604. ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

1605. Eliminating Position Bias of Language Models: A Mechanistic Approach

1606. CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening

1607. A Unified Theory of Quantum Neural Network Loss Landscapes

1608. Transformer Learns Optimal Variable Selection in Group-Sparse Classification

1609. Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image

1610. Fantastic Copyrighted Beasts and How (Not) to Generate Them

1611. Gramian Multimodal Representation Learning and Alignment

1612. ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

1613. As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss

1614. OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

1615. FIG: Flow with Interpolant Guidance for Linear Inverse Problems

1616. Block Verification Accelerates Speculative Decoding

1617. Weighted-Reward Preference Optimization for Implicit Model Fusion

1618. Simple ReFlow: Improved Techniques for Fast Flow Models

1619. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

1620. UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models

1621. Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference

1622. Efficient Imitation under Misspecification

1623. Learned Reference-based Diffusion Sampler for multi-modal distributions

1624. Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness

1625. CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

1626. Scalable Bayesian Learning with posteriors

1627. $\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee

1628. Teaching Human Behavior Improves Content Understanding Abilities Of VLMs

1629. Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

1630. Enhancing End-to-End Autonomous Driving with Latent World Model

1631. Optimality of Matrix Mechanism on $\ell_p^p$-metric

1632. Can We Ignore Labels in Out of Distribution Detection?

1633. Statistical Advantages of Perturbing Cosine Router in Mixture of Experts

1634. Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

1635. Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

1636. On Evaluating the Durability of Safeguards for Open-Weight LLMs

1637. GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

1638. Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

1639. When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings

1640. LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

1641. Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

1642. What is Wrong with Perplexity for Long-context Language Modeling?

1643. Recovery of Causal Graph Involving Latent Variables via Homologous Surrogates

1644. OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees

1645. Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning

1646. TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models

1647. Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

1648. Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control

1649. MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

1650. API Pack: A Massive Multi-Programming Language Dataset for API Call Generation

1651. Capability Localization: Capabilities Can be Localized rather than Individual Knowledge

1652. Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond

1653. Lasso Bandit with Compatibility Condition on Optimal Arm

1654. Safety-Prioritizing Curricula for Constrained Reinforcement Learning

1655. Action Sequence Augmentation for Action Anticipation

1656. The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

1657. Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo

1658. What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models

1659. TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning

1660. Why Does the Effective Context Length of LLMs Fall Short?

1661. Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations

1662. Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization

1663. Persistent Pre-training Poisoning of LLMs

1664. BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

1665. Disentangled Representation Learning with the Gromov-Monge Gap

1666. Diffusion Bridge Implicit Models

1667. Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

1668. A Meta-Learning Approach to Bayesian Causal Discovery

1669. TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

1670. Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees

1671. Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models

1672. Looking Inward: Language Models Can Learn About Themselves by Introspection

1673. DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation

1674. Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning

1675. Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood

1676. How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?

1677. Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection

1678. Layerwise Recurrent Router for Mixture-of-Experts

1679. On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning

1680. GraphRouter: A Graph-based Router for LLM Selections

1681. Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives

1682. Continuous Ensemble Weather Forecasting with Diffusion models

1683. Generating Physical Dynamics under Priors

1684. DataMan: Data Manager for Pre-training Large Language Models

1685. Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework

1686. UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation

1687. Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

1688. Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models

1689. Matrix Product Sketching via Coordinated Sampling

1690. 3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

1691. Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

1692. Learning Clustering-based Prototypes for Compositional Zero-Shot Learning

1693. BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge

1694. Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

1695. Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy

1696. Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

1697. Beyond Worst-Case Dimensionality Reduction for Sparse Vectors

1698. PAD: Personalized Alignment of LLMs at Decoding-time

1699. Dreamweaver: Learning Compositional World Models from Pixels

1700. Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

1701. Ensembling Diffusion Models via Adaptive Feature Aggregation

1702. Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

1703. Efficient Reinforcement Learning with Large Language Model Priors

1704. Federated Residual Low-Rank Adaptation of Large Language Models

1705. Convex Formulations for Training Two-Layer ReLU Neural Networks

1706. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

1707. When Graph Neural Networks Meet Dynamic Mode Decomposition

1708. TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice

1709. DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural Networks

1710. Learning Diagrams: A Graphical Language for Compositional Training Regimes

1711. Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

1712. Aligned Datasets Improve Detection of Latent Diffusion-Generated Images

1713. Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation

1714. Learning Structured Universe Graph with Outlier OOD Detection for Partial Matching

1715. FACTS: A Factored State-Space Framework for World Modelling

1716. Bootstrapping Language Models with DPO Implicit Rewards

1717. Gaussian Splatting Lucas-Kanade

1718. Improving Deep Regression with Tightness

1719. Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic

1720. Reasoning with Latent Thoughts: On the Power of Looped Transformers

1721. Provable unlearning in topic modeling and downstream tasks

1722. Transformer-Squared: Self-adaptive LLMs

1723. Quantum-PEFT: Ultra parameter-efficient fine-tuning

1724. FOSP: Fine-tuning Offline Safe Policy through World Models

1725. Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

1726. Gaussian-Based Instance-Adaptive Intensity Modeling for Point-Supervised Facial Expression Spotting

1727. Large Scale Knowledge Washing

1728. ImProver: Agent-Based Automated Proof Optimization

1729. SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

1730. Offline Hierarchical Reinforcement Learning via Inverse Optimization

1731. FreeVS: Generative View Synthesis on Free Driving Trajectory

1732. Training Free Exponential Context Extension via Cascading KV Cache

1733. Tool-Planner: Task Planning with Clusters across Multiple Tools

1734. Generalizable Human Gaussians from Single-View Image

1735. Calibrating Expressions of Certainty

1736. MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks

1737. Sequential Controlled Langevin Diffusions

1738. MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures

1739. Locality-aware Gaussian Compression for Fast and High-quality Rendering

1740. SyllableLM: Learning Coarse Semantic Units for Speech Language Models

1741. PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos

1742. In-context Time Series Predictor

1743. CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning

1744. Large Language Models Assume People are More Rational than We Really are

1745. DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEO

1746. Policy Design in Long-run Welfare Dynamics

1747. MallowsPO: Fine-Tune Your LLM with Preference Dispersions

1748. Morphing Tokens Draw Strong Masked Image Models

1749. Hybrid Regularization Improves Diffusion-based Inverse Problem Solving

1750. Not All Language Model Features Are One-Dimensionally Linear

1751. CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

1752. GSE: Group-wise Sparse and Explainable Adversarial Attacks

1753. Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions

1754. Denoising with a Joint-Embedding Predictive Architecture

1755. Controlling Space and Time with Diffusion Models

1756. Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

1757. MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

1758. Gyrogroup Batch Normalization

1759. Identifying latent state transitions in non-linear dynamical systems

1760. Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval

1761. Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions

1762. Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions

1763. Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis

1764. VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning

1765. Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification

1766. Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

1767. Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy

1768. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

1769. Towards Interpreting Visual Information Processing in Vision-Language Models

1770. On-the-fly Preference Alignment via Principle-Guided Decoding

1771. GeoILP: A Synthetic Dataset to Guide Large-Scale Rule Induction

1772. Certified Robustness Under Bounded Levenshtein Distance

1773. How to Evaluate Reward Models for RLHF

1774. Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond

1775. From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation

1776. Efficient Learning with Sine-Activated Low-Rank Matrices

1777. Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

1778. Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

1779. Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics

1780. Accelerating Training with Neuron Interaction and Nowcasting Networks

1781. CViT: Continuous Vision Transformer for Operator Learning

1782. eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels

1783. CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

1784. Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

1785. ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

1786. Adversarial Latent Feature Augmentation for Fairness

1787. Find A Winning Sign: Sign Is All We Need to Win the Lottery

1788. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

1789. Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

1790. Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

1791. REvolve: Reward Evolution with Large Language Models using Human Feedback

1792. DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

1793. Interaction Asymmetry: A General Principle for Learning Composable Abstractions

1794. CoInD: Enabling Logical Compositions in Diffusion Models

1795. Beyond FVD: An Enhanced Evaluation Metrics for Video Generation Distribution Quality

1796. Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models

1797. Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models

1798. A New Perspective on Shampoo's Preconditioner

1799. Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks

1800. Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models

1801. On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

1802. Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization

1803. Are Large Vision Language Models Good Game Players?

1804. Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene

1805. $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

1806. A Large-scale Training Paradigm for Graph Generative Models

1807. ReMatching Dynamic Reconstruction Flow

1808. Neural networks on Symmetric Spaces of Noncompact Type

1809. Repulsive Latent Score Distillation for Solving Inverse Problems

1810. Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids

1811. Test-time Adaptation for Image Compression with Distribution Regularization

1812. GeoLoRA: Geometric integration for parameter efficient fine-tuning

1813. ImDy: Human Inverse Dynamics from Imitated Observations

1814. MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation

1815. LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning

1816. Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap

1817. SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization

1818. Selective Induction Heads: How Transformers Select Causal Structures in Context

1819. PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

1820. Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

1821. CycleResearcher: Improving Automated Research via Automated Review

1822. Diffusion Transformers for Tabular Data Time Series Generation

1823. No Preference Left Behind: Group Distributional Preference Optimization

1824. Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

1825. Perturbation-Restrained Sequential Model Editing

1826. Making Transformer Decoders Better Differentiable Indexers

1827. Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

1828. Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

1829. Human-Aligned Chess With a Bit of Search

1830. Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs

1831. On the Transfer of Object-Centric Representation Learning

1832. Prototype antithesis for biological few-shot class-incremental learning

1833. CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution

1834. Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

1835. Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space

1836. Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations

1837. Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

1838. Gradient descent with generalized Newton’s method

1839. MeshMask: Physics-Based Simulations with Masked Graph Neural Networks

1840. Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer

1841. Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

1842. NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

1843. $\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps

1844. A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning

1845. Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

1846. The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG

1847. X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing

1848. No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

1849. Rethinking Shapley Value for Negative Interactions in Non-convex Games

1850. Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards

1851. BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

1852. TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

1853. DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

1854. Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples

1855. AgentStudio: A Toolkit for Building General Virtual Agents

1856. Inner Information Analysis Algorithm for Deep Neural Network based on Community

1857. Efficient Evolutionary Search Over Chemical Space with Large Language Models

1858. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

1859. RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

1860. KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks

1861. Understanding and Enhancing the Transferability of Jailbreaking Attacks

1862. Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness

1863. Robust Representation Consistency Model via Contrastive Denoising

1864. Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

1865. Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling

1866. Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

1867. Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement

1868. Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection

1869. HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS

1870. Denoising Autoregressive Transformers for Scalable Text-to-Image Generation

1871. Learning Geometric Reasoning Networks For Robot Task And Motion Planning

1872. DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References

1873. MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation

1874. VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models

1875. IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

1876. MotionClone: Training-Free Motion Cloning for Controllable Video Generation

1877. InCoDe: Interpretable Compressed Descriptions For Image Generation

1878. Standardizing Structural Causal Models

1879. Training Neural Networks as Recognizers of Formal Languages

1880. Searching for Optimal Solutions with LLMs via Bayesian Optimization

1881. QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing

1882. Confidence Elicitation: A New Attack Vector for Large Language Models

1883. Injecting Universal Jailbreak Backdoors into LLMs in Minutes

1884. High-Quality Joint Image and Video Tokenization with Causal VAE

1885. Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

1886. Mitigate the Gap: Improving Cross-Modal Alignment in CLIP

1887. FairDen: Fair Density-Based Clustering

1888. Stabilized Neural Prediction of Potential Outcomes in Continuous Time

1889. KBLaM: Knowledge Base augmented Language Model

1890. Robust Feature Learning for Multi-Index Models in High Dimensions

1891. Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders

1892. ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

1893. Toward Understanding In-context vs. In-weight Learning

1894. Does Refusal Training in LLMs Generalize to the Past Tense?

1895. Wasserstein-Regularized Conformal Prediction under General Distribution Shift

1896. Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

1897. Self-Updatable Large Language Models by Integrating Context into Model Parameters

1898. SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models

1899. Investigating Pattern Neurons in Urban Time Series Forecasting

1900. Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization

1901. CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

1902. Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

1903. Self-Play Preference Optimization for Language Model Alignment

1904. One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning

1905. Rethinking Spiking Neural Networks from an Ensemble Learning Perspective

1906. DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models

1907. TLDR: Token-Level Detective Reward Model for Large Vision Language Models

1908. PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition

1909. Enhancing Language Model Agents using Diversity of Thoughts

1910. SELF-EVOLVED REWARD LEARNING FOR LLMS

1911. Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

1912. LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

1913. InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation

1914. What Makes Large Language Models Reason in (Multi-Turn) Code Generation?

1915. Generalized Consistency Trajectory Models for Image Manipulation

1916. Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

1917. Federated Few-Shot Class-Incremental Learning

1918. Theory, Analysis, and Best Practices for Sigmoid Self-Attention

1919. KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

1920. Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

1921. Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

1922. ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

1923. SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

1924. Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes

1925. Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models

1926. Truncated Consistency Models

1927. From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

1928. A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence

1929. ARB-LLM: Alternating Refined Binarizations for Large Language Models

1930. Radar: Fast Long-Context Decoding for Any Transformer

1931. Self-Improving Robust Preference Optimization

1932. Oracle efficient truncated statistics

1933. Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate

1934. Robust System Identification: Finite-sample Guarantees and Connection to Regularization

1935. TopoDiffusionNet: A Topology-aware Diffusion Model

1936. Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

1937. Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks

1938. Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference

1939. InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

1940. Glad: A Streaming Scene Generator for Autonomous Driving

1941. Improving Equivariant Networks with Probabilistic Symmetry Breaking

1942. InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling

1943. Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits

1944. PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

1945. NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance

1946. CameraCtrl: Enabling Camera Control for Video Diffusion Models

1947. FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

1948. Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens

1949. Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

1950. Elliptic Loss Regularization

1951. Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization

1952. Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

1953. Concept Bottleneck Language Models For Protein Design

1954. CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

1955. MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

1956. Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback

1957. Learning 3D Perception from Others' Predictions

1958. W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models

1959. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

1960. Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint

1961. Multilevel Generative Samplers for Investigating Critical Phenomena

1962. Calibrating LLMs with Information-Theoretic Evidential Deep Learning

1963. GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

1964. Dissecting Adversarial Robustness of Multimodal LM Agents

1965. BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

1966. A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

1967. COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

1968. On the Crucial Role of Initialization for Matrix Factorization

1969. Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities

1970. Handling Delay in Real-Time Reinforcement Learning

1971. Progressive Parameter Efficient Transfer Learning for Semantic Segmentation

1972. BoneMet: An Open Large-Scale Multi-Modal Murine Dataset for Breast Cancer Bone Metastasis Diagnosis and Prognosis

1973. PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

1974. Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State Consistency

1975. SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings

1976. Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs

1977. Infinite-Resolution Integral Noise Warping for Diffusion Models

1978. Efficient stagewise pretraining via progressive subnetworks

1979. Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

1980. EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

1981. GraphArena: Evaluating and Exploring Large Language Models on Graph Computation

1982. OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code

1983. Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided Queries

1984. Improved Sampling Algorithms for Lévy-Itô Diffusion Models

1985. Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning

1986. MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation

1987. New Algorithms for the Learning-Augmented k-means Problem

1988. Geometry of Lightning Self-Attention: Identifiability and Dimension

1989. Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

1990. Attributing Culture-Conditioned Generations to Pretraining Corpora

1991. UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

1992. IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

1993. Deep Linear Probe Generators for Weight Space Learning

1994. Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

1995. Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning

1996. TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification

1997. Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization

1998. COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

1999. Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining

2000. See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

2001. 3D-SPATIAL MULTIMODAL MEMORY

2002. Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence

2003. Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

2004. Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance

2005. AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors

2006. Contrastive Learning from Synthetic Audio Doppelgängers

2007. Going Beyond Static: Understanding Shifts with Time-Series Attribution

2008. StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces

2009. Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning

2010. ContraDiff: Planning Towards High Return States via Contrastive Learning

2011. ToolGen: Unified Tool Retrieval and Calling via Generation

2012. Query-based Knowledge Transfer for Heterogeneous Learning Environments

2013. ProtoSnap: Prototype Alignment For Cuneiform Signs

2014. DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models

2015. SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

2016. Residual Stream Analysis with Multi-Layer SAEs

2017. A Statistical Approach for Controlled Training Data Detection

2018. MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

2019. Fine-tuning can Help Detect Pretraining Data from Large Language Models

2020. Centrality-guided Pre-training for Graph

2021. Long-time asymptotics of noisy SVGD outside the population limit

2022. MANTRA: The Manifold Triangulations Assemblage

2023. Zero-Shot Natural Language Explanations

2024. Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models

2025. Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling

2026. Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

2027. Decoupling Angles and Strength in Low-rank Adaptation

2028. F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI

2029. Reassessing How to Compare and Improve the Calibration of Machine Learning Models

2030. Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator

2031. Semantic Aware Representation Learning for Lifelong Learning

2032. Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA

2033. GANDALF: Generative AttentioN based Data Augmentation and predictive modeLing Framework for personalized cancer treatment

2034. Controllable Blur Data Augmentation Using 3D-Aware Motion Estimation

2035. Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes

2036. A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops

2037. MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

2038. Contextual Document Embeddings

2039. Anyprefer: An Agentic Framework for Preference Data Synthesis

2040. Small Models are LLM Knowledge Triggers for Medical Tabular Prediction

2041. GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data

2042. GMValuator: Similarity-based Data Valuation for Generative Models

2043. Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios

2044. Building Math Agents with Multi-Turn Iterative Preference Learning

2045. DyCAST: Learning Dynamic Causal Structure from Time Series

2046. Three Mechanisms of Feature Learning in a Linear Network

2047. Graph Neural Networks Gone Hogwild

2048. Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies

2049. I-Con: A Unifying Framework for Representation Learning

2050. On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

2051. A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

2052. Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

2053. Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

2054. Scaling Optimal LR Across Token Horizons

2055. MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

2056. Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation

2057. Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

2058. Discovering Influential Neuron Path in Vision Transformers

2059. Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model

2060. Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

2061. Scaling up Masked Diffusion Models on Text

2062. REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

2063. Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

2064. Training Robust Ensembles Requires Rethinking Lipschitz Continuity

2065. Does Spatial Cognition Emerge in Frontier Models?

2066. Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

2067. Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

2068. Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation

2069. Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

2070. Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image Classification

2071. PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance

2072. Adaptive Pruning of Pretrained Transformer via Differential Inclusions

2073. Variational Best-of-N Alignment

2074. Data Center Cooling System Optimization Using Offline Reinforcement Learning

2075. Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers

2076. Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

2077. FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

2078. Decision Information Meets Large Language Models: The Future of Explainable Operations Research

2079. Forget the Data and Fine-Tuning! Just Fold the Network to Compress

2080. Differentially Private Federated Learning with Time-Adaptive Privacy Spending

2081. TimeInf: Time Series Data Contribution via Influence Functions

2082. Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

2083. HaDeMiF: Hallucination Detection and Mitigation in Large Language Models

2084. Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

2085. Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving

2086. OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning

2087. GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models

2088. Fengbo: a Clifford Neural Operator pipeline for 3D PDEs in Computational Fluid Dynamics

2089. Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data

2090. NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

2091. An Effective Theory of Bias Amplification

2092. K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models

2093. Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

2094. Correlation and Navigation in the Vocabulary Key Representation Space of Language Models

2095. CREAM: Consistency Regularized Self-Rewarding Language Models

2096. Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos

2097. ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

2098. MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

2099. Latent Action Pretraining from Videos

2100. Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

2101. Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning

2102. CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search

2103. Bayesian Regularization of Latent Representation

2104. DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

2105. Convergence of Distributed Adaptive Optimization with Local Updates

2106. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving

2107. Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

2108. Designing Mechanical Meta-Materials by Learning Equivariant Flows

2109. MCNC: Manifold-Constrained Reparameterization for Neural Compression

2110. TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking

2111. SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

2112. Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport

2113. Neural Dueling Bandits: Preference-Based Optimization with Human Feedback

2114. Divergence of Neural Tangent Kernel in Classification Problems

2115. Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator

2116. How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings

2117. Advancing Prompt-Based Methods for Replay-Independent General Continual Learning

2118. Robustness Auditing for Linear Regression: To Singularity and Beyond

2119. Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

2120. RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

2121. Decision Tree Induction Through LLMs via Semantically-Aware Evolution

2122. Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

2123. Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation

2124. Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective

2125. Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA

2126. How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

2127. Protein Language Model Fitness is a Matter of Preference

2128. Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

2129. McEval: Massively Multilingual Code Evaluation

2130. Privacy-Aware Lifelong Learning

2131. MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

2132. Learning Graph Invariance by Harnessing Spuriosity

2133. Mitigating Spurious Correlations in Zero-Shot Multimodal Models

2134. The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures

2135. Accurate and Scalable Graph Neural Networks via Message Invariance

2136. Strong Preferences Affect the Robustness of Preference Models and Value Alignment

2137. VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation

2138. LeanAgent: Lifelong Learning for Formal Theorem Proving

2139. BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL

2140. Combining Induction and Transduction for Abstract Reasoning

2141. Adversarial Training for Defense Against Label Poisoning Attacks

2142. SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation

2143. Matryoshka Multimodal Models

2144. On Rollouts in Model-Based Reinforcement Learning

2145. Information Theoretic Text-to-Image Alignment

2146. Uncertainty Herding: One Active Learning Method for All Label Budgets

2147. FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

2148. A Transfer Attack to Image Watermarks

2149. Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

2150. Learning Hierarchical Polynomials of Multiple Nonlinear Features

2151. Generalizable Motion Planning via Operator Learning

2152. Efficient Causal Decision Making with One-sided Feedback

2153. Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

2154. Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment

2155. Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation

2156. LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

2157. Self-Supervised Diffusion Models for Electron-Aware Molecular Representation Learning

2158. Exploring the Design Space of Visual Context Representation in Video MLLMs

2159. Fair Submodular Cover

2160. L3Ms — Lagrange Large Language Models

2161. The 3D-PC: a benchmark for visual perspective taking in humans and machines

2162. On the Optimal Memorization Capacity of Transformers

2163. InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences

2164. Efficient Cross-Episode Meta-RL

2165. MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

2166. Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

2167. A Formal Framework for Understanding Length Generalization in Transformers

2168. Mask in the Mirror: Implicit Sparsification

2169. Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

2170. Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

2171. Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains

2172. GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching

2173. Multi-Task Dense Predictions via Unleashing the Power of Diffusion

2174. Discovering Group Structures via Unitary Representation Learning

2175. Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

2176. Grokking at the Edge of Numerical Stability

2177. MELODI: Exploring Memory Compression for Long Contexts

2178. MIND: Math Informed syNthetic Dialogues for Pretraining LLMs

2179. T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning

2180. FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling

2181. AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation

2182. MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

2183. A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts

2184. Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization

2185. Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal Disentanglement

2186. Zero-shot forecasting of chaotic systems

2187. Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer

2188. Real-time design of architectural structures with differentiable mechanics and neural networks

2189. Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice

2190. Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach

2191. Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

2192. Measuring And Improving Engagement of Text-to-Image Generation Models

2193. Law of the Weakest Link: Cross Capabilities of Large Language Models

2194. Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems

2195. UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning

2196. Discriminator-Guided Embodied Planning for LLM Agent

2197. State Space Model Meets Transformer: A New Paradigm for 3D Object Detection

2198. MGCFNN: A Neural MultiGrid Solver with Novel Fourier Neural Network for High Wave Number Helmholtz Equations

2199. The Belief State Transformer

2200. Measuring memorization in RLHF for code completion

2201. On the Relation between Trainability and Dequantization of Variational Quantum Learning Models

2202. Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems

2203. Epistemic Monte Carlo Tree Search

2204. HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing

2205. HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction

2206. Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery

2207. Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

2208. DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation

2209. Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry

2210. Metalic: Meta-Learning In-Context with Protein Language Models

2211. Gumbel Counterfactual Generation From Language Models

2212. Solving Video Inverse Problems Using Image Diffusion Models

2213. CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

2214. Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features

2215. ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

2216. Physics-informed Temporal Difference Metric Learning for Robot Motion Planning

2217. Noise Separation guided Candidate Label Reconstruction for Noisy Partial Label Learning

2218. PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization

2219. FIRING-Net: A filtered feature recycling network for speech enhancement

2220. Improving Neural Network Accuracy by Concurrently Training with a Twin Network

2221. Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

2222. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

2223. Efficient Model Editing with Task-Localized Sparse Fine-tuning

2224. Provence: efficient and robust context pruning for retrieval-augmented generation

2225. Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation

2226. MUSE: Machine Unlearning Six-Way Evaluation for Language Models

2227. Learning Harmonized Representations for Speculative Sampling

2228. You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs

2229. PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks

2230. CryoFM: A Flow-based Foundation Model for Cryo-EM Densities

2231. ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs

2232. Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

2233. Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

2234. Text-to-Image Rectified Flow as Plug-and-Play Priors

2235. SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels

2236. LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content

2237. Data Unlearning in Diffusion Models

2238. Adaptive backtracking line search

2239. Fast Training of Sinusoidal Neural Fields via Scaling Initialization

2240. When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction

2241. ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors

2242. Bridging the Gap between Database Search and \emph{De Novo} Peptide Sequencing with SearchNovo

2243. Logical Consistency of Large Language Models in Fact-Checking

2244. Vision-LSTM: xLSTM as Generic Vision Backbone

2245. CTSyn: A Foundation Model for Cross Tabular Data Generation

2246. P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS

2247. GameArena: Evaluating LLM Reasoning through Live Computer Games

2248. Herald: A Natural Language Annotated Lean 4 Dataset

2249. TabM: Advancing tabular deep learning with parameter-efficient ensembling

2250. UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

2251. Spurious Forgetting in Continual Learning of Language Models

2252. Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer

2253. Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models

2254. Test-time Adaptation for Regression by Subspace Alignment

2255. Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization

2256. Locality Sensitive Avatars From Video

2257. KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks

2258. Conservative Contextual Bandits: Beyond Linear Representations

2259. Is In-Context Learning Sufficient for Instruction Following in LLMs?

2260. VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing

2261. 3D Vision-Language Gaussian Splatting

2262. Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies

2263. Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test

2264. Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

2265. Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion

2266. Language Models Are Implicitly Continuous

2267. Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias

2268. High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational Autoencoders

2269. Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training

2270. NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments

2271. TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

2272. Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

2273. HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

2274. GROOT-2: Weakly Supervised Multimodal Instruction Following Agents

2275. Redefining the task of Bioactivity Prediction

2276. Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

2277. Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems

2278. Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

2279. Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

2280. Mixture of Attentions For Speculative Decoding

2281. Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs

2282. Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors

2283. A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics

2284. CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

2285. Sensor-Invariant Tactile Representation

2286. Diffusion Models as Cartoonists: The Curious Case of High Density Regions

2287. 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery

2288. Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

2289. Shape as Line Segments: Accurate and Flexible Implicit Surface Representation

2290. HOPE for a Robust Parameterization of Long-memory State Space Models

2291. Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning

2292. Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

2293. Large Language Models Often Say One Thing and Do Another

2294. A Theory of Initialisation's Impact on Specialisation

2295. Can a Large Language Model be a Gaslighter?

2296. Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

2297. Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold

2298. GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting

2299. DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement

2300. A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

2301. Progress or Regress? Self-Improvement Reversal in Post-training

2302. Halton Scheduler for Masked Generative Image Transformer

2303. Error-quantified Conformal Inference for Time Series

2304. Concept Bottleneck Large Language Models

2305. Separation Power of Equivariant Neural Networks

2306. MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

2307. Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation

2308. Neural Interactive Proofs

2309. PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection

2310. SGD with memory: fundamental properties and stochastic acceleration

2311. A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

2312. Model-Free Offline Reinforcement Learning with Enhanced Robustness

2313. Is Your Multimodal Language Model Oversensitive to Safe Queries?

2314. Near, far: Patch-ordering enhances vision foundation models' scene understanding

2315. Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

2316. ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

2317. Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs

2318. Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts

2319. Do Deep Neural Network Solutions Form a Star Domain?

2320. Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

2321. Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

2322. Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models

2323. InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems

2324. Transformers Handle Endogeneity in In-Context Linear Regression

2325. GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

2326. Size-Generalizable RNA Structure Evaluation by Exploring Hierarchical Geometries

2327. Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

2328. Unsupervised Model Tree Heritage Recovery

2329. A3D: Does Diffusion Dream about 3D Alignment?

2330. Continuous Diffusion for Mixed-Type Tabular Data

2331. Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning

2332. PEARL: Parallel Speculative Decoding with Adaptive Draft Length

2333. Aligning Human Motion Generation with Human Perceptions

2334. Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks

2335. Scale-aware Recognition in Satellite Images under Resource Constraints

2336. MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

2337. Model-agnostic meta-learners for estimating heterogeneous treatment effects over time

2338. Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment

2339. State Space Models are Provably Comparable to Transformers in Dynamic Token Selection

2340. ImageFolder: Autoregressive Image Generation with Folded Tokens

2341. Model Equality Testing: Which Model is this API Serving?

2342. Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing

2343. From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle

2344. Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

2345. Generalized Behavior Learning from Diverse Demonstrations

2346. SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches

2347. Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement

2348. Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark

2349. Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

2350. Underdamped Diffusion Bridges with Applications to Sampling

2351. A Closer Look at Machine Unlearning for Large Language Models

2352. A Robust Method to Discover Causal or Anticausal Relation

2353. Debiasing Mini-Batch Quadratics for Applications in Deep Learning

2354. Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

2355. SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

2356. EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

2357. Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

2358. Beyond Random Masking: When Dropout meets Graph Convolutional Networks

2359. Tight Clusters Make Specialized Experts

2360. Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model

2361. RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

2362. Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

2363. Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher

2364. SegLLM: Multi-round Reasoning Segmentation with Large Language Models

2365. Should VLMs be Pre-trained with Image Data?

2366. InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

2367. Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning

2368. CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems

2369. LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

2370. Deep MMD Gradient Flow without adversarial training

2371. A transfer learning framework for weak to strong generalization

2372. What to align in multimodal contrastive learning?

2373. GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

2374. Towards Continuous Reuse of Graph Models via Holistic Memory Diversification

2375. Lightweight Predictive 3D Gaussian Splats

2376. Universal Image Restoration Pre-training via Degradation Classification

2377. Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information

2378. LLaMA-Omni: Seamless Speech Interaction with Large Language Models

2379. SONICS: Synthetic Or Not - Identifying Counterfeit Songs

2380. Execution-guided within-prompt search for programming-by-example

2381. Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios

2382. A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention

2383. ReSi: A Comprehensive Benchmark for Representational Similarity Measures

2384. Autoregressive Pretraining with Mamba in Vision

2385. Improved Training Technique for Latent Consistency Models

2386. Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

2387. Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box Systems

2388. MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

2389. Generalization and Distributed Learning of GFlowNets

2390. Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

2391. Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

2392. RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs

2393. Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement Learning

2394. Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment

2395. Select before Act: Spatially Decoupled Action Repetition for Continuous Control

2396. Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models

2397. Diffusion Models Are Real-Time Game Engines

2398. Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

2399. QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation

2400. Expected Sliced Transport Plans

2401. B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

2402. Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling

2403. Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

2404. ACES: Automatic Cohort Extraction System for Event-Stream Datasets

2405. GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation

2406. InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

2407. Structure Language Models for Protein Conformation Generation

2408. $q$-exponential family for policy optimization

2409. GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

2410. Understanding Long Videos with Multimodal Language Models

2411. Matérn Kernels for Tunable Implicit Surface Reconstruction

2412. No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

2413. An Online Learning Theory of Trading-Volume Maximization

2414. ADAM: An Embodied Causal Agent in Open-World Environments

2415. Learning High-Degree Parities: The Crucial Role of the Initialization

2416. Endowing Visual Reprogramming with Adversarial Robustness

2417. Unlocking the Potential of Model Calibration in Federated Learning

2418. Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective

2419. Non-myopic Generation of Language Models for Reasoning and Planning

2420. Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

2421. Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

2422. Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models

2423. A Theoretical Framework for Partially-Observed Reward States in RLHF

2424. Distance-Based Tree-Sliced Wasserstein Distance

2425. ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY

2426. Wavelet-based Positional Representation for Long Context

2427. Robotouille: An Asynchronous Planning Benchmark for LLM Agents

2428. Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization

2429. Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits

2430. Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

2431. Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation

2432. SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects

2433. Scalable Mechanistic Neural Networks

2434. Inverse Attention Agents for Multi-Agent Systems

2435. Vertical Federated Learning with Missing Features During Training and Inference

2436. Progressive Mixed-Precision Decoding for Efficient LLM Inference

2437. Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

2438. DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning

2439. KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

2440. DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models

2441. Self-supervised contrastive learning performs non-linear system identification

2442. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

2443. SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments

2444. OpenHands: An Open Platform for AI Software Developers as Generalist Agents

2445. Procedural Synthesis of Synthesizable Molecules

2446. Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks

2447. Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

2448. A Sanity Check for AI-generated Image Detection

2449. Deep Random Features for Scalable Interpolation of Spatiotemporal Data

2450. Meta-Continual Learning of Neural Fields

2451. SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback

2452. Erasing Concept Combination from Text-to-Image Diffusion Model

2453. SparsyFed: Sparse Adaptive Federated Learning

2454. Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning

2455. Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

2456. Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics

2457. Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural Networks

2458. Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization

2459. TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

2460. Direct Distributional Optimization for Provable Alignment of Diffusion Models

2461. TRENDy: Temporal Regression of Effective Nonlinear Dynamics

2462. Equivariant Masked Position Prediction for Efficient Molecular Representation

2463. Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

2464. Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction

2465. From Search to Sampling: Generative Models for Robust Algorithmic Recourse

2466. Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction

2467. Aligned LLMs Are Not Aligned Browser Agents

2468. ProtPainter: Draw or Drag Protein via Topology-guided Diffusion

2469. Learning Mask Invariant Mutual Information for Masked Image Modeling

2470. Understanding Virtual Nodes: Oversquashing and Node Heterogeneity

2471. A Watermark for Order-Agnostic Language Models

2472. Hyperbolic Genome Embeddings

2473. RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

2474. Probabilistic Conformal Prediction with Approximate Conditional Validity

2475. Measuring And Improving Persuasiveness Of Large Language Models

2476. Many-Objective Multi-Solution Transport

2477. Text2PDE: Latent Diffusion Models for Accessible Physics Simulation

2478. On the Expressive Power of Sparse Geometric MPNNs

2479. Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

2480. ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints

2481. EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition

2482. Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

2483. Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

2484. Preserving Diversity in Supervised Fine-Tuning of Large Language Models

2485. Zero-shot Imputation with Foundation Inference Models for Dynamical Systems

2486. CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

2487. Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping

2488. Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts

2489. [Plastic Learning with Deep Fourier Features](iclr_src/ICLR_2025_Main_Papers