mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 23 May 2025

602 papers

  1. LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  2. A Minimalist Method for Fine-tuning Text-to-Image Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  3. Safety-Prioritized, Reinforcement Learning-Enabled Traffic Flow Optimization in a 3D City-Wide Simulation EnvironmentDeep reinforcement learning methods → RL for autonomous driving and traffic
  4. Predictive posterior sampling from non-stationnary Gaussian process priors via Diffusion models with application to climate dataDiffusion models → Flow matching, time series and science
  5. MRI Image Generation Based on Text PromptsDiffusion models → Medical imaging and segmentation
  6. EvidenceMoE: A Physics-Guided Mixture-of-Experts with Evidential Critics for Advancing Fluorescence Light Detection and Ranging in Scattering MediaMixture-of-experts → Vision mixture-of-experts
  7. More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning ModelsLLM reasoning → Hallucination detection and mitigation +1
  8. Cultural Awareness in Vision-Language Models: A Cross-Country ExplorationMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  9. Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic ConfidenceLLM reasoning → Test-time compute and efficient thinking +1
  10. BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge BasesLLM reasoning → Clinical and biomedical applications
  11. Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLPRetrieval-augmented generation → Medical and biomedical RAG
  12. Reinforcement Speculative Decoding for Fast RankingEfficient LLM inference and serving → Speculative decoding
  13. Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge GapsRetrieval-augmented generation → Legal and financial RAG
  14. McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  15. Reinforcement Learning for Ballbot Navigation in Uneven TerrainDeep reinforcement learning methods → RL for robot locomotion and manipulation
  16. LatentLLM: Attention-Aware Joint Tensor CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  17. DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  18. KL-regularization Itself is Differentially Private in Bandits and RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  19. RaDeR: Reasoning-aware Dense Retrieval ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  20. Thought calibration: Efficient and confident test-time scalingLLM reasoning → Test-time compute and efficient thinking
  21. An Outlook on the Opportunities and Challenges of Multi-Agent AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  22. Dynamic Risk Assessments for Offensive Cybersecurity AgentsLLM agents and tool use → Agent threats, guardrails and governance
  23. Convergence of Proximal Policy Gradient Method for Problems with Control Dependent Diffusion CoefficientsDeep reinforcement learning methods → RL theory and sample complexity
  24. Weakly-supervised Mamba-Based Mastoidectomy Shape Prediction for Cochlear Implant Surgery Using 3D T-Distribution LossState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  25. The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  26. Persona Alchemy: Designing, Evaluating, and Implementing Psychologically-Grounded LLM Agents for Diverse Stakeholder RepresentationLLM agents and tool use → Social simulation and multi-agent debate
  27. The Cell Must Go On: Agar.io for Continual Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  28. Diffusion Self-Weighted Guidance for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  29. Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer AccessDiffusion models → Diffusion foundations and sampling
  30. CrashAgent: Crash Scenario Generation via Multi-modal ReasoningLLM reasoning → Chain-of-thought reasoning for driving
  31. CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent LearningEnd-to-end autonomous driving → Cooperative and V2X driving +1
  32. A Critical Evaluation of Defenses against Prompt Injection AttacksLLM safety and security → Prompt injection and agent security
  33. Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision BoundaryLLM safety and security → Safety alignment, refusal and guardrails
  34. Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive RewardsLLM reasoning → Test-time compute and efficient thinking
  35. InstructPart: Task-Oriented Part Segmentation with Instruction ReasoningLLM reasoning → Spatial and embodied reasoning
  36. Single-agent or Multi-agent Systems? Why Not Both?LLM agents and tool use → General LLM agent frameworks and benchmarks
  37. TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and VerificationLLM reasoning → Clinical and biomedical applications +1
  38. Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access ControlLLM agents and tool use → Agent memory systems
  39. Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse ProblemsDiffusion models → Diffusion foundations and sampling
  40. MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-AnsweringRetrieval-augmented generation → Medical and biomedical RAG
  41. Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic LensLLM reasoning → Test-time compute and efficient thinking
  42. The Origins of Representation Manifolds in Large Language ModelsMechanistic interpretability → Sparse autoencoder training and evaluation
  43. NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV CacheEfficient LLM inference and serving → KV cache quantization
  44. BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVsLLM agents and tool use → Multimodal and embodied agents
  45. Implementing Agents in JavaScriptLLM agents and tool use → General LLM agent frameworks and benchmarks
  46. Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to MultimodalityEfficient LLM inference and serving → Visual token pruning in multimodal models
  47. CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language GamesLLM agents and tool use → Reinforcement learning for LLM agents
  48. LA-RCS: LLM-Agent-Based Robot Control SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
  49. The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral DilemmasLLM reasoning → Reasoning benchmarks and evaluation
  50. First Finish Search: Efficient Test-Time Scaling in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  51. Tool Preferences in Agentic LLMs are UnreliableLLM agents and tool use → Tool learning and function calling
  52. VideoGameBench: Can Vision-Language Models complete popular video games?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  53. One RL to See Them All: Visual Triple Unified Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  54. Reward Model Overoptimisation in Iterated RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  55. ProgRM: Build Better GUI Agents with Progress RewardsLLM agents and tool use → GUI and mobile agents +1
  56. Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language ModelsKnowledge distillation → Distillation for recommender systems
  57. NFT: Bridging Supervised Learning and Reinforcement Learning in Math ReasoningLLM reasoning → Reinforcement learning for reasoning
  58. Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLMMultimodal LLMs / vision-language models → Video understanding with MLLMs
  59. ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent FrameworkLLM agents and tool use → Web, search, and research agents
  60. Towards more transferable adversarial attack in black-box mannerDiffusion models → Robustness, privacy and adversarial aspects
  61. QwenLong-CPRS: Towards ∞-LLMs with Dynamic Context OptimizationEfficient LLM inference and serving → Prompt and context compression
  62. CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-raysLLM reasoning → Clinical and biomedical applications +1
  63. Stable Reinforcement Learning for Efficient ReasoningLLM reasoning → Reinforcement learning for reasoning
  64. What Do You Need for Compositional Generalization in Diffusion Planning?Offline RL and imitation learning from data → Diffusion and flow policies for offline RL
  65. Deep Video Discovery: Agentic Search with Tool Use for Long-form Video UnderstandingLLM agents and tool use → Multimodal and embodied agents
  66. Extended Inductive Reasoning for Personalized Preference Inference from Behavioral SignalsLLM reasoning → Reinforcement learning for reasoning +1
  67. Reward Model Generalization for Compute-Aware Test-Time ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  68. FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  69. RestoreVAR: Visual Autoregressive Generation for All-in-One Image RestorationDiffusion models → Image generation, text-to-image and editing
  70. Structured Thinking Matters: Improving LLMs Generalization in Causal Inference TasksLLM reasoning → Causal reasoning in LLMs
  71. Knot So Simple: A Minimalistic Environment for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  72. Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical PerspectiveLLM reasoning → Reinforcement learning for reasoning
  73. Outcome-based Reinforcement Learning to Predict the FutureLLM reasoning → Reinforcement learning for reasoning +1
  74. Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  75. Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and ModelingMultimodal LLMs / vision-language models → Medical vision-language models
  76. Diffusion Classifiers Understand Compositionality, but Conditions ApplyDiffusion models → Image generation, text-to-image and editing
  77. Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RLLLM reasoning → Clinical and biomedical applications
  78. VeriThinker: Learning to Verify Makes Reasoning Model EfficientLLM reasoning → Test-time compute and efficient thinking
  79. Geometric SSM: LTI State Space Models for Selective TasksState-space sequence models (S4, Mamba) → Core SSM architectures for language
  80. Enhancing CTR Prediction with De-correlated Expert NetworksMixture-of-experts → MoE for recommender systems
  81. Language models can learn implicit multi-hop reasoning, but only if they have lots of training dataLLM reasoning → Reasoning benchmarks and evaluation
  82. DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback LearningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  83. T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image EvaluationLLM reasoning → Multimodal reasoning +1
  84. Formalizing Embeddedness Failures in Universal Artificial IntelligenceDeep reinforcement learning methods → Deep RL algorithms and representations
  85. Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across ModalitiesLLM reasoning → Audio-language model reasoning +1
  86. Superplatforms Have to Attack AI AgentsLLM agents and tool use → Social simulation and multi-agent debate
  87. Multi-Person Interaction Generation from Two-Person Motion PriorsDiffusion models → Video generation
  88. Scalable Valuation of Human Feedback through Provably Robust Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  89. Hybrid Mamba-Transformer Decoder for Error-Correcting CodesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  90. Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  91. Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' ReasoningLLM reasoning → Test-time compute and efficient thinking
  92. Not All Tokens Are What You Need In ThinkingLLM reasoning → Test-time compute and efficient thinking
  93. Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI SystemsLLM reasoning → Prompting and chain-of-thought reasoning
  94. Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  95. Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object HallucinationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  96. Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent BehaviourLLM agents and tool use → General LLM agent frameworks and benchmarks
  97. RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph CompletionLLM reasoning → Knowledge- and tool-augmented reasoning
  98. Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM AccelerationEfficient LLM inference and serving → KV cache quantization
  99. Generative Data Augmentation for Object Point Cloud SegmentationDiffusion models → 3D, point cloud and scene generation
  100. U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
All 602
  1. Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language ModelsMechanistic interpretability → SAE features and their applications
  2. R-Genie: Reasoning-Guided Generative Image EditingLLM reasoning → Multimodal reasoning +1
  3. Position: The Real Barrier to LLM Agent Usability is Agentic ROILLM agents and tool use → General LLM agent frameworks and benchmarks
  4. Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  5. But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectorsMechanistic interpretability → Probing deception, bias and beliefs
  6. Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  7. Fast Quiet-STaR: Thinking Without Thought TokensLLM reasoning → Test-time compute and efficient thinking
  8. SafeAgent: Safeguarding LLM Agents via an Automated Risk SimulatorLLM agents and tool use → Agent threats, guardrails and governance
  9. URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  10. Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted dataLLM safety and security → Machine unlearning
  11. SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World DomainEnd-to-end autonomous driving → Generative simulation for driving
  12. Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLMMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  13. SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D GenerationDiffusion models → 3D, point cloud and scene generation
  14. Get Experience from Practice: LLM Agents with Record & ReplayLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. The Third Pillar of Causal Analysis? A Measurement Perspective on Causal RepresentationsLLM reasoning → Causal reasoning in LLMs
  16. Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekLLM reasoning → Spatial and embodied reasoning
  17. Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  18. FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
  19. Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill EvolutionLLM reasoning → Reasoning for agents, planning and code +1
  20. MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction SynthesisSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  21. Towards General Continuous Memory for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  22. QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  23. Plan-R1: Safe and Feasible Trajectory Planning as Language ModelingLLM reasoning → Chain-of-thought reasoning for driving
  24. EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  25. GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMsLLM reasoning → Spatial and embodied reasoning
  26. Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment PerspectiveLLM reasoning → Reinforcement learning for reasoning
  27. Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?LLM safety and security → Jailbreaking
  28. Simulating Macroeconomic Expectations in Survey Experiments with LLM-based Economic AgentsLLM agents and tool use → Social simulation and multi-agent debate
  29. HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and ReasoningLLM reasoning → Multimodal reasoning +1
  30. PreMoE: Proactive Inference for Efficient Mixture-of-ExpertsMixture-of-experts → MoE theory and gating functions
  31. Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in TrainingDiffusion models → Diffusion foundations and sampling
  32. TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital EnvironmentsLLM agents and tool use → GUI and mobile agents
  33. Enhancing Large Vision-Language Models with Layout Modality for Table Question Answering on Japanese Annual Securities ReportsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  34. Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided ExplorationLLM reasoning → Reinforcement learning for reasoning
  35. Scaling Image and Video Generation via Test-Time Evolutionary SearchLLM reasoning → Diffusion reasoning and test-time scaling
  36. Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied EnvironmentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  37. Distilling LLM Agent into Small Models with Retrieval and Code ToolsLLM reasoning → Reasoning for agents, planning and code +2
  38. Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  39. Integrating Visual Interpretation and Linguistic Reasoning for Math Problem SolvingLLM reasoning → Multimodal reasoning +1
  40. Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric ReasoningLLM reasoning → Spatial and embodied reasoning
  41. Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless InputsLLM safety and security → Backdoor and data poisoning attacks
  42. One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  43. AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning ModelLLM reasoning → Knowledge- and tool-augmented reasoning
  44. CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingDiffusion models → Audio, speech and music
  45. InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPOLLM reasoning → Multimodal reasoning
  46. USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban AgentsLLM reasoning → Spatial and embodied reasoning +1
  47. Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized GenerationLLM reasoning → Reinforcement learning for reasoning
  48. JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language ModelsLLM safety and security → Audio jailbreaks and speech backdoors
  49. Enhancing Fourier-based Doppler Resolution with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  50. Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion ModelDiffusion models → Video generation
  51. Deeper Diffusion Models Amplify BiasDiffusion models → Diffusion foundations and sampling
  52. Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination DetectionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  53. CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuningMixture-of-experts → Expert routing strategies
  54. T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  55. RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement LearningLLM reasoning → Multimodal reasoning
  56. Multimodal Conversation Structure UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  57. Co-Reinforcement Learning for Unified Multimodal Understanding and GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  58. Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  59. Optimizing Retrieval-Augmented Generation for Electrical Engineering: A Case Study on ABB Circuit BreakersRetrieval-augmented generation → RAG pipeline design and evaluation
  60. Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic NarrativesLLM safety and security → Jailbreaking
  61. The Spacetime of Diffusion Models: An Information Geometry PerspectiveDiffusion models → Diffusion foundations and sampling
  62. Is Your LLM Really Mastering the Concept? A Multi-Agent BenchmarkLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source IdentificationLLM agents and tool use → Web, search, and research agents
  64. MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  65. On the Design of KL-Regularized Policy Gradient Algorithms for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  66. CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured DocumentsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  67. PD3: A Project Duplication Detection Framework via Adapted Multi-Agent DebateLLM agents and tool use → Software engineering coding agents
  68. From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC BenchmarkLLM reasoning → Multimodal reasoning
  69. MARCO: Meta-Reflection with Cross-Referencing for Code ReasoningLLM reasoning → Reasoning for agents, planning and code
  70. FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial DomainRetrieval-augmented generation → Legal and financial RAG
  71. HydraRAG: Structured Cross-Source Enhanced Large Language Model ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  72. Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision DeficienciesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  73. Hypergraph Mamba for Efficient Whole Slide Image UnderstandingState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  74. Towards Evaluating Proactive Risk Awareness of Multimodal Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  75. Self-Training Large Language Models with Confident ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  76. LeTS: Learning to Think-and-Search via Process-and-Outcome Reward HybridizationLLM reasoning → Knowledge- and tool-augmented reasoning
  77. Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point CloudsKnowledge distillation → Detection and dense prediction distillation
  78. VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  79. Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal LearningMultimodal LLMs / vision-language models → Medical vision-language models
  80. Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning StrategyDiffusion models → Diffusion and flow policies for robotics
  81. MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  82. T2: An Adaptive Test-Time Scaling Strategy for Contextual Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
  83. DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision PoliciesEfficient LLM inference and serving → Early exit and edge inference
  84. LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic ContextSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  85. Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?LLM reasoning → Reasoning benchmarks and evaluation
  86. Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  87. Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  88. Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona PromptingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  89. Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection SpaceOffline RL and imitation learning from data → Robot manipulation imitation learning
  90. Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations ModelingDiffusion models → Diffusion foundations and sampling
  91. Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of ChartsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  92. Value-Guided Search for Efficient Chain-of-Thought ReasoningLLM reasoning → Test-time compute and efficient thinking
  93. EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic FusionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  94. Towards VM Rescheduling Optimization Through Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  95. Dual Ascent Diffusion for Inverse ProblemsDiffusion models → Inverse problems and image restoration
  96. Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A SurveyDiffusion models → Diffusion and flow policies for robotics +1
  97. FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical SystemsDiffusion models → Flow matching, time series and science
  98. BRAVE: Brain-Controlled Prosthetic Arm with Voice Integration and Embodied Learning for Enhanced Mobility
  99. Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes
  100. The Maximal Overlap Discrete Wavelet Scattering Transform and Its Application in Classification Tasks
  101. Exploiting Block Coordinate Descent for Cost-Effective LLM Model Training
  102. AI-Driven SEEG Channel Ranking for Epileptogenic Zone Localization
  103. Benchmarking Early Agitation Prediction in Community-Dwelling People with Dementia Using Multimodal Sensors and Machine Learning
  104. CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imaging
  105. AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design
  106. FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection
  107. Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale
  108. ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging
  109. Uncovering Bottlenecks and Optimizing Scientific Lab Workflows with Cycle Time Reduction Agents
  110. Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
  111. How Much Do Large Language Models Know about Human Motion? A Case Study in 3D Avatar Control
  112. High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework
  113. A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control
  114. VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
  115. Temporal Restoration and Spatial Rewiring for Source-Free Multivariate Time Series Domain Adaptation
  116. Learning Shared Representations from Unpaired Data
  117. CIM-NET: A Video Denoising Deep Neural Network Model Optimized for Computing-in-Memory Architectures
  118. Data-driven multi-agent modelling of calcium interactions in cell culture: PINN vs Regularized Least-squares
  119. Evaluating the Energy-Efficiency of the Code Generated by LLMs
  120. PMOA-TTS: Introducing the PubMed Open Access Textual Times Series Corpus
  121. Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
  122. Beyond Demonstrations: Dynamic Vector Construction from Latent Representations
  123. Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm
  124. Advertising in AI systems: Society must be vigilant
  125. How We Won the ISLES'24 Challenge by Preprocessing
  126. CENet: Context Enhancement Network for Medical Image Segmentation
  127. Development of Interactive Nomograms for Predicting Short-Term Survival in ICU Patients with Aplastic Anemia
  128. LocalKMeans: Convergence of Lloyd's Algorithm with Distributed Local Iterations
  129. Dynamics of Affective States During Takeover Requests in Conditionally Automated Driving Among Older Adults with and without Cognitive Impairment
  130. A Dual Basis Approach for Structured Robust Euclidean Distance Geometry
  131. Rehabilitation Exercise Quality Assessment and Feedback Generation Using Large Language Models with Prompt Engineering
  132. On Theoretical Identifiability of Discrete Latent Causal Graphical Models
  133. Recent Deep Learning in Crowd Behaviour Analysis: A Brief Review
  134. Taming Diffusion for Dataset Distillation with High Representativeness
  135. Towards Anonymous Neural Network Inference
  136. Applications of Modular Co-Design for De Novo 3D Molecule Generation
  137. Human-Centered AI Communication in Co-Creativity: An Initial Framework and Insights
  138. NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities
  139. Monocular Marker-free Patient-to-Image Intraoperative Registration for Cochlear Implant Surgery
  140. RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification
  141. SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training
  142. ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling
  143. Next-token pretraining implies in-context learning
  144. Optimal community detection in dense bipartite graphs
  145. Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications
  146. Small Models, Smarter Learning: The Power of Joint Task Training
  147. Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems
  148. Brightness-Invariant Tracking Estimation in Tagged MRI
  149. SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases
  150. Maximum Principle of Optimal Probability Density Control
  151. Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
  152. CONCORD: Concept-Informed Diffusion for Dataset Distillation
  153. X-MethaneWet: A Cross-scale Global Wetland Methane Emission Benchmark Dataset for Advancing Science Discovery with AI
  154. How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve
  155. On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
  156. Model Editing with Graph-Based External Memory
  157. Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance
  158. DART3: Leveraging Distance for Test Time Adaptation in Person Re-Identification
  159. An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs
  160. PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language
  161. Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling
  162. Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
  163. Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4
  164. COLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification
  165. PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training
  166. CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
  167. Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms
  168. Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
  169. A deep solver for backward stochastic Volterra integral equations
  170. Convexified Message-Passing Graph Neural Networks
  171. Operator Learning for Schr"odinger Equation: Unitarity, Error Bounds, and Time Generalization
  172. Efficient Algorithms for Electing Successive Committees
  173. Tube Loss based Deep Networks For Improving the Probabilistic Forecasting of Wind Speed
  174. Towards a Quantum-classical Augmented Network
  175. Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior
  176. The end of radical concept nativism
  177. Representative Action Selection for Large Action Space Bandit Families
  178. Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
  179. Will Large Language Models Transform Clinical Prediction?
  180. Decomposition of Water Demand Patterns Using Skewed Gaussian Distributions for Behavioral Insights and Operational Planning
  181. Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation
  182. ZeroML: A Next Generation AutoML Language
  183. Intent Classification on Low-Resource Languages with Query Similarity Search
  184. Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback
  185. From Bias to Accountability: How the EU AI Act Confronts Challenges in European GeoAI Auditing
  186. A Robust PPO-optimized Tabular Transformer Framework for Intrusion Detection in Industrial IoT Systems
  187. POSTER: A Multi-Signal Model for Detecting Evasive Smishing
  188. Two-Stage Regularization-Based Structured Pruning for LLMs
  189. Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
  190. IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
  191. A Domain Ontology for Modeling the Book of Purification in Islam
  192. Evidence-Grounded Multimodal Misinformation Detection with Attention-Based GNNs
  193. Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education
  194. ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge
  195. Data Mining-Based Techniques for Software Fault Localization
  196. Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?
  197. REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
  198. Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs
  199. WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
  200. Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learning
  201. Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find
  202. TokBench: Evaluating Your Visual Tokenizer before Visual Generation
  203. Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
  204. Boosting Open Set Recognition Performance through Modulated Representation Learning
  205. Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection
  206. BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
  207. Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement
  208. Frankentext: Stitching random text fragments into long-form narratives
  209. TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
  210. UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification
  211. Scalable Policy Maximization Under Network Interference
  212. Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion
  213. Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization
  214. Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking
  215. Accelerating Learned Image Compression Through Modeling Neural Training Dynamics
  216. F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles
  217. CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting
  218. Dynamic Dual Buffer with Divide-and-Conquer Strategy for Online Continual Learning
  219. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
  220. DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations
  221. Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
  222. Early-Exit Graph Neural Networks
  223. An Iterative Framework for Generative Backmapping of Coarse Grained Proteins
  224. Backpropagation-Free Metropolis-Adjusted Langevin Algorithm
  225. AFD-STA: Adaptive Filtering Denoising with Spatiotemporal Attention for Chaotic System Prediction
  226. DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation
  227. Bayesian Deep Learning for Discrete Choice
  228. Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
  229. Towards Uncertainty Aware Task Delegation and Human-AI Collaborative Decision-Making
  230. Asymptotically optimal regret in communicating Markov decision processes
  231. Semantic Correspondence: Unified Benchmarking and a Strong Baseline
  232. A Pre-trained Foundation Model Framework for Multiplanar MRI Classification of Extramural Vascular Invasion and Mesorectal Fascia Invasion in Rectal Cancer
  233. MathEDU: Feedback Generation on Problem-Solving Processes for Mathematical Learning Support
  234. BOTM: Echocardiography Segmentation via Bi-directional Optimal Token Matching
  235. LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
  236. SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework
  237. SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios
  238. Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
  239. Linear Mixture Distributionally Robust Markov Decision Processes
  240. Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach
  241. Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition
  242. Clip4Retrofit: Enabling Real-Time Image Labeling on Edge Devices via Cross-Architecture CLIP Distillation
  243. CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention
  244. Mahalanobis++: Improving OOD Detection via Feature Normalization
  245. Automata Learning of Preferences over Temporal Logic Formulas from Pairwise Comparisons
  246. 3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation
  247. A Wavelet-based Stereo Matching Framework for Solving Frequency Convergence Inconsistency
  248. Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
  249. RemoteSAM: Towards Segment Anything for Earth Observation
  250. Building Floor Number Estimation from Crowdsourced Street-Level Images: Munich Dataset and Baseline Method
  251. LLM assisted web application functional requirements generation: A case study of four popular LLMs over a Mess Management System
  252. ExoGait-MS: Learning Periodic Dynamics with Multi-Scale Graph Network for Exoskeleton Gait Recognition
  253. Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling
  254. SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
  255. Training with Pseudo-Code for Instruction Following
  256. Clinical Validation of Deep Learning for Real-Time Tissue Oxygenation Estimation Using Spectral Imaging
  257. Deep Operator Neural Network Model Predictive Control
  258. AI Literacy for Legal AI Systems: A practical approach
  259. Distances for Markov chains from sample streams
  260. An Example Safety Case for Safeguards Against Misuse
  261. Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective
  262. Anytime-valid, Bayes-assisted, Prediction-Powered Inference
  263. Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction
  264. TRACE for Tracking the Emergence of Semantic Representations in Transformers
  265. Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
  266. Canonical Pose Reconstruction from Single Depth Image for 3D Non-rigid Pose Recovery on Limited Datasets
  267. ADLGen: Synthesizing Symbolic, Event-Triggered Sensor Sequences for Human Activity Modeling
  268. AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web
  269. Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models
  270. To Glue or Not to Glue? Classical vs Learned Image Matching for Mobile Mapping Cameras to Textured Semantic 3D Building Models
  271. MR-EEGWaveNet: Multiresolutional EEGWaveNet for Seizure Detection from Long EEG Recordings
  272. Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment
  273. Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems
  274. FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models
  275. Is Single-View Mesh Reconstruction Ready for Robotics?
  276. Bias-Optimal Bounds for SGD: A Computer-Aided Lyapunov Analysis
  277. Counting Cycles with AI: Counting Cycles with AI: Computationally Efficient Equivalent Forms with Applications
  278. A Principled Bayesian Framework for Training Binary and Spiking Neural Networks
  279. Federated Causal Inference from Multi-Site Observational Data via Propensity Score Aggregation
  280. Mind the Domain Gap: Measuring the Domain Gap Between Real-World and Synthetic Point Clouds for Automated Driving Development
  281. The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  282. SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
  283. Evaluating NLP Embedding Models for Handling Science-Specific Symbolic Expressions in Student Texts
  284. Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding
  285. LMask: Learn to Solve Constrained Routing Problems with Lazy Masking
  286. Understanding Gated Neurons in Transformers from Their Input-Output Functionality
  287. AutoMiSeg: Automatic Medical Image Segmentation via Test-Time Adaptation of Foundation Models
  288. Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV
  289. Towards Practical Defect-Focused Automated Code Review
  290. Evaluation of Few-Shot Learning Methods for Kidney Stone Type Recognition in Ureteroscopy
  291. KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks
  292. LLM Meeting Decision Trees on Tabular Data
  293. M-learner:A Flexible And Powerful Framework To Study Heterogeneous Treatment Effect In Mediation Model
  294. Promptable cancer segmentation using minimal expert-curated data
  295. Flexible MOF Generation with Torsion-Aware Flow Matching
  296. UltraBoneUDF: Self-supervised Bone Surface Reconstruction from Ultrasound Based on Neural Unsigned Distance Functions
  297. Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention
  298. NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
  299. ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback
  300. Approximating Simple ReLU Networks based on Spectral Decomposition of Fisher Information
  301. Semantic segmentation with reward
  302. Evolving Machine Learning in Non-Stationary Environments: A Unified Survey of Drift, Forgetting, and Adaptation
  303. Universal Domain Adaptation Benchmark for Time Series Data Representation
  304. DataRater: Meta-Learned Dataset Curation
  305. Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
  306. Consensus in the Parliament of AI: Harmonized Multi-Region CT-Radiomics and Foundation-Model Signatures for Multicentre NSCLC Risk Stratification
  307. Track Anything Annotate: Video annotation and dataset generation of computer vision models
  308. FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
  309. Hyperspectral Anomaly Detection Fused Unified Nonconvex Tensor Ring Factors Regularization
  310. Toward Optimal ANC: Establishing Mutual Information Lower Bound
  311. Semi-Supervised Multi-Label Feature Selection with Consistent Sparse Graph Learning
  312. MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback
  313. Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
  314. BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
  315. Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods
  316. Best Group Identification in Multi-Objective Bandits
  317. SpectraLDS: Provable Distillation for Linear Dynamical Systems
  318. Multi-task Learning For Joint Action and Gesture Recognition
  319. DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization
  320. The emergence of sparse attention: impact of data distribution and benefits of repetition
  321. Stochastic Weight Sharing for Bayesian Neural Networks
  322. Explaining Sources of Uncertainty in Automated Fact-Checking
  323. Out of the Shadows: Exploring a Latent Space for Neural Network Verification
  324. Scaling Recurrent Neural Networks to a Billion Parameters with Zero-Order Optimization
  325. Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
  326. Locality-Sensitive Hashing for Efficient Hard Negative Sampling in Contrastive Learning
  327. TEDI: Trustworthy and Ethical Dataset Indicators to Analyze and Compare Dataset Documentation
  328. Continuum Transformers Perform In-Context Learning by Operator Gradient Descent
  329. Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
  330. VLM Models and Automated Grading of Atopic Dermatitis
  331. Investigating Affect Mining Techniques for Annotation Sample Selection in the Creation of Finnish Affective Speech Corpus
  332. Emerging categories in scientific explanations
  333. Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models
  334. Source Separation of Small Classical Ensembles: Challenges and Opportunities
  335. ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification
  336. Quantifying uncertainty in spectral clusterings: expectations for perturbed and incomplete data
  337. PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
  338. Low-Resource NMT: A Case Study on the Written and Spoken Languages in Hong Kong
  339. VIBE: Vector Index Benchmark for Embeddings
  340. An Attention Infused Deep Learning System with Grad-CAM Visualization for Early Screening of Glaucoma
  341. Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition
  342. Hyperparameter Optimization via Interacting with Probabilistic Circuits
  343. A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances
  344. Latent Mode Decomposition
  345. DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
  346. DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
  347. Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion
  348. Bruno: Backpropagation Running Undersampled for Novel device Optimization
  349. Optimal Online Change Detection via Random Fourier Features
  350. Supervised Graph Contrastive Learning for Gene Regulatory Networks
  351. EXECUTE: A Multilingual Benchmark for LLM Token Understanding
  352. Thalia: A Global, Multi-Modal Dataset for Volcanic Activity Monitoring
  353. TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
  354. Optimizing Shortfall Risk Metric for Learning Regression Models
  355. C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
  356. TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving
  357. Joker: Joint Optimization Framework for Lightweight Kernel Machines
  358. Unsupervised Clustering for Fault Analysis in High-Voltage Power Systems Using Voltage and Current Signals
  359. Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models
  360. Qiskit Machine Learning: an open-source library for quantum machine learning tasks at scale on quantum hardware and classical simulators
  361. Soft-CAM: Making black box models self-explainable for medical image analysis
  362. Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks
  363. MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
  364. Discrete Neural Flow Samplers with Locally Equivariant Transformer
  365. A tensor network approach for chaotic time series prediction
  366. The Pilot Corpus of the English Semantic Sketches
  367. RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection
  368. PEAR: Equal Area Weather Forecasting on the Sphere
  369. A Distributionally Robust Framework for Nuisance in Causal Effect Estimation
  370. PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization
  371. Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
  372. CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models
  373. SemSketches-2021: experimenting with the machine processing of the pilot semantic sketches corpus
  374. Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
  375. COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection
  376. Enhancing AI System Resiliency: Formulation and Guarantee for LSTM Resilience Based on Control Theory
  377. SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data
  378. CoDec: Prefix-Shared Decoding Kernel for LLMs
  379. ViP2-CLIP: Visual-Perception Prompting with Unified Alignment for Zero-Shot Anomaly Detection
  380. ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction
  381. Semi-Supervised Medical Image Segmentation via Dual Networks
  382. 5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization
  383. Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection
  384. Tuning Language Models for Robust Prediction of Diverse User Behaviors
  385. Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery
  386. SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding
  387. Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification
  388. EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy
  389. What is the role of memorization in Continual Learning?
  390. Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
  391. Automating Versatile Time-Series Analysis with Tiny Transformers on Embedded FPGAs
  392. Automated scientific minimization of regret
  393. DAM-GT: Dual Positional Encoding-Based Attention Masking Graph Transformer for Node Classification
  394. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
  395. Instruct2See: Learning to Remove Any Obstructions Across Distributions
  396. Unveiling the Basin-Like Loss Landscape in Large Language Models
  397. Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
  398. Bridging Electronic Health Records and Clinical Texts: Contrastive Learning for Enhanced Clinical Tasks
  399. A Survey on Stereotype Detection in Natural Language Processing
  400. A Network Science Approach to Granular Time Series Segmentation
  401. Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
  402. Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis
  403. ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation
  404. BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling
  405. Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
  406. Leveraging Stochastic Depth Training for Adaptive Inference
  407. textttRange-Arithmetic: Verifiable Deep Learning Inference on an Untrusted Party
  408. CAS-IQA: Teaching Vision-Language Models for Synthetic Angiography Quality Assessment
  409. Large language model as user daily behavior data generator: balancing population diversity and individual personality
  410. PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings
  411. MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation
  412. Adaptive Semantic Token Communication for Transformer-based Edge Inference
  413. Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
  414. NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
  415. JELAI: Integrating AI and Learning Analytics in Jupyter Notebooks
  416. MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity
  417. CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
  418. Distance Estimation in Outdoor Driving Environments Using Phase-only Correlation Method with Event Cameras
  419. MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery
  420. Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation
  421. Multiphysics Bench: Benchmarking and Investigating Scientific Machine Learning for Multiphysics PDEs
  422. p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Models
  423. Wildfire spread forecasting with Deep Learning
  424. ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization
  425. Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing
  426. Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection
  427. FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation
  428. Graph Inverse Style Transfer for Counterfactual Explainability
  429. Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition
  430. Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity
  431. Learning Representational Disparities
  432. TimeCF: A TimeMixer-Based Model with adaptive Convolution and Sharpness-Aware Minimization Frequency Domain Loss for long-term time seris forecasting
  433. GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
  434. DECT-based Space-Squeeze Method for Multi-Class Classification of Metastatic Lymph Nodes in Breast Cancer
  435. Transparency and Proportionality in Post-Processing Algorithmic Bias Correction
  436. What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
  437. Large Language Models Do Multi-Label Classification Differently
  438. Offline Constrained Reinforcement Learning under Partial Data Coverage
  439. L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
  440. RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognition
  441. The Discovery Engine: A Framework for AI-Driven Synthesis and Navigation of Scientific Knowledge Landscapes
  442. Managing FAIR Knowledge Graphs as Polyglot Data End Points: A Benchmark based on the rdf2pg Framework and Plant Biology Data
  443. Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
  444. ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
  445. Research on Defect Detection Method of Motor Control Board Based on Image Processing
  446. HiLAB: A Hybrid Inverse-Design Framework
  447. DTRT: Enhancing Human Intent Estimation and Role Allocation for Physical Human-Robot Collaboration
  448. ExARNN: An Environment-Driven Adaptive RNN for Learning Non-Stationary Power Dynamics
  449. keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection
  450. Anatomy-Guided Multitask Learning for MRI-Based Classification of Placenta Accreta Spectrum and its Subtypes
  451. Hyperspectral in situ remote sensing of water surface nitrate in the Fitzroy River estuary, Queensland, Australia, using deep learning
  452. Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions
  453. ConfRover: Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
  454. Reverse-Speech-Finder: A Neural Network Backtracking Architecture for Generating Alzheimer's Disease Speech Samples and Improving Diagnosis Performance
  455. The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts
  456. PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
  457. InfoDet: A Dataset for Infographic Element Detection
  458. SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction
  459. SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models
  460. Efficient compression of neural networks and datasets
  461. Efficient Adaptive Experimentation with Noncompliance
  462. A Position Paper on the Automatic Generation of Machine Learning Leaderboards
  463. HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning
  464. CLIMB: Class-imbalanced Learning Benchmark on Tabular Data
  465. Real-time Traffic Accident Anticipation with Feature Reuse
  466. Baitradar: A Multi-Model Clickbait Detection Algorithm Using Deep Learning
  467. Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
  468. PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints
  469. Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems
  470. Discovering Forbidden Topics in Language Models
  471. Designing an efficient and equitable humanitarian supply chain dynamically via reinforcement learning
  472. Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision
  473. Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
  474. HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
  475. SEvoBench : A C++ Framework For Evolutionary Single-Objective Optimization Benchmarking
  476. UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information
  477. Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
  478. VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
  479. Speechless: Speech Instruction Training Without Speech for Low Resource Languages
  480. Conversations: Love Them, Hate Them, Steer Them
  481. Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
  482. Wasserstein Transfer Learning
  483. From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation
  484. Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits
  485. FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
  486. Wildfire Detection Using Vision Transformer with the Wildfire Dataset
  487. CatBOX: A Categorical-Continuous Bayesian Optimization with Spectral Mixture Kernels for Accelerated Catalysis Experiments
  488. Dual-sensing driving detection model
  489. WiNGPT-3.0 Technical Report
  490. Programmable Photonic Unitary Processor Enables Parametrized Differentiable Long-Haul Spatial Division Multiplexed Transmission
  491. AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing
  492. Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
  493. An End-to-End Approach for Child Reading Assessment in the Xhosa Language
  494. Ellipsoidal Time Series Forecasting
  495. Improved and Oracle-Efficient Online ℓ1-Multicalibration
  496. Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture
  497. Are GNNs Worth the Effort for IoT Botnet Detection? A Comparative Study of VAE-GNN vs. ViT-MLP and VAE-MLP Approaches
  498. A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit
  499. Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
  500. Graph Attention Neural Network for Botnet Detection: Evaluating Autoencoder, VAE and PCA-Based Dimension Reduction
  501. Adversarial Robustness of Nonparametric Regression
  502. CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots