mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 27 May 2025

637 papers

  1. MLE-STAR: Machine Learning Engineering Agent via Search and Targeted RefinementLLM agents and tool use → Web, search, and research agents
  2. Topology-Aware and Highly Generalizable Deep Reinforcement Learning for Efficient Retrieval in Multi-Deep Storage SystemsDeep reinforcement learning methods → RL for robot navigation and UAV control
  3. Code Researcher: Deep Research Agent for Large Systems Code and Commit HistoryLLM agents and tool use → Software engineering coding agents
  4. MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS GyroscopesMixture-of-experts → MoE theory and gating functions
  5. Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency RewardsDiffusion models → Image generation, text-to-image and editing
  6. Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding ModelsRetrieval-augmented generation → Generation and context integration
  7. GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  8. A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  9. Aligning LLMs by Predicting Preferences from User Writing SamplesLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  10. Watermarking Without Standards Is Not AI GovernanceLLM safety and security → Watermarking generated content and models
  11. TuneComp: Joint Fine-tuning and Compression for Large Foundation ModelsKnowledge distillation → Knowledge distillation for LLMs
  12. Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short OnesLLM reasoning → Test-time compute and efficient thinking
  13. ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion GenerationDiffusion models → Diffusion foundations and sampling +1
  14. TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data PredictionLLM reasoning → Knowledge- and tool-augmented reasoning
  15. Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data CreationLLM reasoning → Reasoning for agents, planning and code +2
  16. Memorization to Generalization: Emergence of Diffusion Models from Associative MemoryDiffusion models → Diffusion foundations and sampling
  17. Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  18. BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity SpectrumLLM agents and tool use → Medical and scientific domain agents
  19. Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional SubgoalsDiffusion models → Diffusion and flow policies for robotics +1
  20. What is Adversarial Training for Diffusion Models?Diffusion models → Robustness, privacy and adversarial aspects
  21. Deep Reinforcement Learning Agents are not even close to Human IntelligenceDeep reinforcement learning methods → RL training of language and agent models
  22. Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  23. Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset AnalysisRetrieval-augmented generation → Multimodal RAG
  24. Adapting Foundation Vision-Language Models to Medical Diagnosis via Query-Driven Expert BridgingMultimodal LLMs / vision-language models → Medical vision-language models
  25. Rethinking the Outlier Distribution in Large Language Models: An In-depth StudyLLM reasoning → Test-time compute and efficient thinking
  26. R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  27. Efficient Controllable Diffusion via Optimal Classifier GuidanceDiffusion models → Diffusion foundations and sampling
  28. PreGenie: An Agentic Framework for High-quality Visual Presentation GenerationLLM agents and tool use → Multimodal and embodied agents
  29. Think Before You Diffuse: Infusing Physical Rules into Video DiffusionLLM reasoning → Spatial and embodied reasoning +1
  30. QuARI: Query Adaptive Retrieval ImprovementMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  31. Efficient Diffusion Models for Symmetric ManifoldsDiffusion models → Diffusion foundations and sampling
  32. Apprenticeship learning with prior beliefs using inverse optimizationOffline RL and imitation learning from data → Inverse reinforcement learning +1
  33. SoSBench: Benchmarking Safety Alignment on Six Scientific DomainsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  34. R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token RoutingLLM reasoning → Test-time compute and efficient thinking
  35. Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New PerspectivesLLM reasoning → Reasoning benchmarks and evaluation
  36. Fast and Cost-effective Speculative Edge-Cloud Decoding with Early ExitsEfficient LLM inference and serving → Early exit and edge inference
  37. Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  38. Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-TuningDiffusion models → Diffusion foundations and sampling
  39. Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  40. AITEE -- Agentic Tutor for Electrical EngineeringLLM agents and tool use → Educational agents and math problem solving
  41. CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  42. Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  43. ChemAmp: Amplified Chemistry Tools via Composable AgentsLLM agents and tool use → Medical and scientific domain agents
  44. EaqVLA: Encoding-aligned Quantization for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  45. Diffusion Model-based Activity Completion for AI Motion Capture from VideosDiffusion models → Video generation
  46. Knowledge Distillation Approach for SOS Fusion Staging: Towards Fully Automated Skeletal Maturity AssessmentKnowledge distillation → Distillation for medical imaging
  47. Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision MakingLLM agents and tool use → Medical and scientific domain agents
  48. ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  49. AdInject: Real-World Black-Box Attacks on Web Agents via Advertising DeliveryLLM agents and tool use → Agent threats, guardrails and governance
  50. UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents +1
  51. Reinforcing General Reasoning without VerifiersLLM reasoning → Reinforcement learning for reasoning
  52. Be Decisive: Noise-Induced Layouts for Multi-Subject GenerationDiffusion models → Image generation, text-to-image and editing
  53. Hardware-Efficient Attention for Fast DecodingEfficient LLM inference and serving → KV cache optimization
  54. Are Language Models Consequentialist or Deontological Moral Reasoners?LLM reasoning → Reasoning benchmarks and evaluation
  55. Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention CalibrationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  56. Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided DiffusionDiffusion models → Discrete and text diffusion
  58. ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  59. Do LLMs Need to Think in One Language? Correlation between Latent Language and Task PerformanceLLM reasoning → Reasoning benchmarks and evaluation
  60. OmniSync: Towards Universal Lip Synchronization via Diffusion TransformersDiffusion models → Audio, speech and music
  61. Can Large Reasoning Models Self-Train?LLM reasoning → Reinforcement learning for reasoning
  62. Hume: Introducing System-2 Thinking in Visual-Language-Action ModelLLM reasoning → Spatial and embodied reasoning +1
  63. Learning Individual Behavior in Agent-Based Models with Graph Diffusion NetworksDiffusion models → Diffusion and flow policies for robotics
  64. GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code GenerationLLM reasoning → Reasoning for agents, planning and code +2
  65. A Framework for Adversarial Analysis of Decision Support Systems Prior to DeploymentDeep reinforcement learning methods → Adversarial robustness and RL in finance
  66. RefTool: Reference-Guided Tool Creation for Knowledge-Intensive ReasoningLLM reasoning → Reasoning for agents, planning and code
  67. Pangu Pro MoE: Mixture of Grouped Experts for Efficient SparsityMixture-of-experts → MoE large language models
  68. MRS: Multi-Resolution Skills for HRL AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
  69. Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  70. SquarechiPO: Differentially Private and Robust chi2-Preference Optimization in Offline Direct AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  71. Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary FeaturesDeep reinforcement learning methods → RL theory and sample complexity
  72. AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  73. DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  74. ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud UnderstandingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  75. GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K ResolutionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  76. Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?LLM reasoning → Multimodal reasoning
  77. Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought ReasoningLLM reasoning → Mathematical reasoning
  78. OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
  79. HoliTom: Holistic Token Merging for Fast Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  80. MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video ScenariosMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  81. MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMsLLM reasoning → Multimodal reasoning +1
  82. MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-onDiffusion models → 3D, point cloud and scene generation
  83. Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical OperationsLLM reasoning → Clinical and biomedical applications
  84. A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological FeaturesKnowledge distillation → Distillation for medical imaging
  85. Large Language Models Miss the Multi-Agent MarkLLM agents and tool use → General LLM agent frameworks and benchmarks
  86. rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified DatasetLLM reasoning → Reasoning for agents, planning and code
  87. Complex System Diagnostics Using a Knowledge Graph-Informed and Large Language Model-Enhanced FrameworkLLM agents and tool use → Financial trading and forecasting agents
  88. XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State LevelLLM agents and tool use → GUI and mobile agents
  89. Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy SpaceLLM safety and security → Jailbreaking
  90. Breaking the Performance Ceiling in Reinforcement Learning requires Inference StrategiesDeep reinforcement learning methods → RL training of language and agent models
  91. CROP: Contextual Region-Oriented Visual Token PruningEfficient LLM inference and serving → Visual token pruning in multimodal models
  92. Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  93. Universal Speech Enhancement with Regression and Generative MambaState-space sequence models (S4, Mamba) → Speech and audio SSMs
  94. Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following CapabilitiesMixture-of-experts → MoE large language models
  95. Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM CrowdsourcingLLM safety and security → Jailbreaking
  96. Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  97. Normalized Attention Guidance: Universal Negative Guidance for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  98. Walk Before You Run! Concise LLM Reasoning via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  99. TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word AlignmentLLM reasoning → Reasoning benchmarks and evaluation
  100. IKMo: Image-Keyframed Motion Generation with Trajectory-Pose Conditioned Motion Diffusion ModelDiffusion models → Video generation
All 637
  1. FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and AttentionDiffusion models → Image generation, text-to-image and editing
  2. Learning Single Index Models with Diffusion PriorsDiffusion models → Inverse problems and image restoration
  3. Universal Value-Function UncertaintiesOffline RL and imitation learning from data → Offline RL algorithms +1
  4. Creativity in LLM-based Multi-Agent Systems: A SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Differentiable Solver Search for Fast Diffusion SamplingDiffusion models → Diffusion foundations and sampling
  6. Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue EvaluationMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  7. Conditional Diffusion Models with Classifier-Free Gibbs-like GuidanceDiffusion models → Diffusion foundations and sampling
  8. Thinker: Learning to Think Fast and SlowLLM reasoning → Test-time compute and efficient thinking
  9. DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and ResponseMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  10. RPM: Reasoning-Level Personalization for Black-Box Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  11. Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of ExpertsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  12. Efficient Large Language Model Inference with Neural Block LinearizationEfficient LLM inference and serving → Early exit and edge inference
  13. DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. Red-Teaming Text-to-Image Systems by Rule-based Preference ModelingLLM safety and security → Vision-language and text-to-image safety
  15. Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  16. Minute-Long Videos with Dual ParallelismsDiffusion models → Diffusion foundations and sampling
  17. CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software BuildingLLM agents and tool use → Software engineering coding agents
  18. Why Distillation can Outperform Zero-RL: The Role of Flexible ReasoningLLM reasoning → Reinforcement learning for reasoning
  19. LPOI: Listwise Preference Optimization for Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  20. Agent-Environment Alignment via Automated Interface GenerationLLM reasoning → Reasoning for agents, planning and code +1
  21. RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual RedundancyDiffusion models → Video generation
  22. Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic SegmentationLLM reasoning → Reasoning benchmarks and evaluation
  23. FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion modelsDiffusion models → Diffusion foundations and sampling
  24. Multi-Mode Process Control Using Multi-Task Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  25. Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  26. Who Reasons in the Large Language Models?LLM reasoning → Reasoning benchmarks and evaluation
  27. Generative Image Compression by Estimating Gradients of the Rate-variable Feature DistributionDiffusion models → Diffusion for compression and wireless
  28. Evaluating and Steering Modality Preferences in Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. DreamBoothDPO: Improving Personalized Generation using Direct Preference OptimizationDiffusion models → Image generation, text-to-image and editing +1
  30. Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements RefinementLLM agents and tool use → Software engineering coding agents
  31. Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQALLM reasoning → Knowledge- and tool-augmented reasoning
  32. OrienText: Surface Oriented Textual Image GenerationDiffusion models → Image generation, text-to-image and editing
  33. Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain PerspectiveDiffusion models → Robustness, privacy and adversarial aspects +1
  34. Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge GraphsLLM reasoning → Reasoning benchmarks and evaluation
  35. PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba AdapterState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  36. On VLMs for Diverse Tasks in Multimodal Meme ClassificationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  37. ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance GenerationDiffusion models → Image generation, text-to-image and editing
  38. Multi-objective Large Language Model Alignment with Hierarchical ExpertsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  39. Revisiting Multi-Agent World Modeling from a Diffusion-Inspired PerspectiveWorld models → Latent dynamics models and model-based RL +1
  40. Geometry-Editable and Appearance-Preserving Object CompositonDiffusion models → 3D, point cloud and scene generation
  41. Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple SubjectsDiffusion models → Image generation, text-to-image and editing
  42. HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth CompletionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  43. A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  44. Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic AssignmentDeep reinforcement learning methods → RL for autonomous driving and traffic
  45. EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  46. Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  47. Step-Wise Formal Verification for LLM-Based Mathematical Problem SolvingLLM reasoning → Mathematical reasoning
  48. Leveraging Diffusion Models for Parameterized Quantum Circuit GenerationDiffusion models → Diffusion foundations and sampling
  49. AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  50. Multi-Embodiment Robotic Retargeting via Guided Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
  51. Concealment of Intent: A Game-Theoretic AnalysisLLM safety and security → Prompt injection and agent security
  52. FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference AccelerationEfficient LLM inference and serving → KV cache quantization
  53. HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence ModelingKnowledge distillation → Knowledge distillation for LLMs
  54. Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
  55. MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  56. MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular OptimizationLLM reasoning → Clinical and biomedical applications +1
  57. Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent PerspectiveLLM reasoning → Multimodal reasoning +2
  58. Improved Representation Steering for Language ModelsMechanistic interpretability → Activation steering methods
  59. Score Replacement with Bounded Deviation for Rare Prompt GenerationDiffusion models → Image generation, text-to-image and editing
  60. Learning Generalizable Robot Policy with Human Demonstration Video as a PromptOffline RL and imitation learning from data → Robot manipulation imitation learning
  61. Rendering-Aware Reinforcement Learning for Vector Graphics GenerationDeep reinforcement learning methods → RL with diffusion and flow models
  62. Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  63. STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy EvaluationDiffusion models → Diffusion and flow policies for robotics
  64. TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMsLLM reasoning → Multimodal reasoning
  65. SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long SequencesEfficient LLM inference and serving → Speculative decoding
  66. PARTONOMY: Large Multimodal Models with Part-Level Visual UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  67. Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence InstructionDiffusion models → Diffusion foundations and sampling
  68. Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
  69. Interactive OT Gym: A Reinforcement Learning-Based Interactive Optical tweezer (OT)-Driven Microrobotics Simulation PlatformDeep reinforcement learning methods → RL for robot locomotion and manipulation
  70. Can Agents Fix Agent Issues?LLM agents and tool use → Software engineering coding agents
  71. MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMsLLM reasoning → Spatial and embodied reasoning +1
  72. RRO: LLM Agent Optimization Through Rising Reward TrajectoriesLLM reasoning → Reinforcement learning for reasoning +2
  73. SPA-RL: Reinforcing LLM Agents via Stepwise Progress AttributionLLM agents and tool use → Reinforcement learning for LLM agents
  74. Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  75. ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-MakingLLM agents and tool use → Multimodal and embodied agents
  76. A reinforcement learning agent for maintenance of deteriorating systems with increasingly imperfect repairsDeep reinforcement learning methods → RL for energy, networks and operations
  77. LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image GenerationDiffusion models → Flow matching, time series and science
  78. VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +2
  79. MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  80. Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational PerspectiveLLM reasoning → Spatial and embodied reasoning
  81. Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware ExplorationLLM reasoning → Test-time compute and efficient thinking
  82. Sparsified State-Space Models are Efficient Highway NetworksEfficient LLM inference and serving → Token pruning and merging for ViTs
  83. Accelerating RL for LLM Reasoning with Optimal Advantage RegressionLLM reasoning → Reinforcement learning for reasoning
  84. GIFARC: Synthetic Dataset for Leveraging Human-Intuitive Analogies to Elevate AI ReasoningLLM reasoning → Multimodal reasoning +1
  85. MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool LearningLLM reasoning → Reasoning for agents, planning and code +1
  86. DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +1
  87. Self-Route: Automatic Mode Switching via Capability Estimation for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
  88. BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking MechanismLLM agents and tool use → GUI and mobile agents
  89. An Optimisation Framework for Unsupervised Environment DesignDeep reinforcement learning methods → Deep RL algorithms and representations
  90. Can Past Experience Accelerate LLM Reasoning?LLM reasoning → Test-time compute and efficient thinking
  91. IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial ScenariosLLM reasoning → Spatial and embodied reasoning
  92. Music Audio-Visual Question Answering Requires Specialized Multimodal DesignsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  93. SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability AnalysisLLM reasoning → Reasoning for agents, planning and code
  94. Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference MatchingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  95. Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  96. SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  97. Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  98. Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  99. REAL-Prover: Retrieval Augmented Lean Prover for Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
  100. Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  101. Mamba-Driven Topology Fusion for Monocular 3D Human Pose EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  102. InstGenIE: Generative Image Editing Made Efficient with Mask-aware Caching and SchedulingDiffusion models → Image generation, text-to-image and editing
  103. Forecasting Nigerian Equity Stock Returns Using Long Short-Term Memory Technique
  104. PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation
  105. Development of a Multiprocessing Interface Genetic Algorithm for Optimising a Multilayer Perceptron for Disease Prediction
  106. Verifiable Safety Q-Filters via Hamilton-Jacobi Reachability and Multiplicative Q-Networks
  107. What Do Latent Action Models Actually Learn?
  108. AZT1D: A Real-World Dataset for Type 1 Diabetes
  109. PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series
  110. CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs
  111. WDMIR: Wavelet-Driven Multimodal Intent Recognition
  112. Aligning Proteins and Language: A Foundation Model for Protein Retrieval
  113. A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing
  114. Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing
  115. OASIS: Online Sample Selection for Continual Visual Instruction Tuning
  116. CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge
  117. AbsoluteNet: A Deep Learning Neural Network to Classify Cerebral Hemodynamic Responses of Auditory Processing
  118. The Folly of AI for Age Verification
  119. Ratas framework: A comprehensive genai-based approach to rubric-based marking of real-world textual exams
  120. DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries
  121. Emotion-aware Dual Cross-Attentive Neural Network with Label Fusion for Stance Detection in Misinformative Social Media Content
  122. LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
  123. MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
  124. LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion
  125. DenseLoRA: Dense Low-Rank Adaptation of Large Language Models
  126. DLP: Dynamic Layerwise Pruning in Large Language Models
  127. MedOrchestra: A Hybrid Cloud-Local LLM Approach for Clinical Data Interpretation
  128. ADA: Automated Moving Target Defense for AI Workloads via Ephemeral Infrastructure-Native Rotation in Kubernetes
  129. Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies
  130. Localized Weather Prediction Using Kolmogorov-Arnold Network-Based Models and Deep RNNs
  131. DeepMultiConnectome: Deep Multi-Task Prediction of Structural Connectomes Directly from Diffusion MRI Tractography
  132. Recovering Fairness Directly from Modularity: a New Way for Fair Community Partitioning
  133. HDRSDR-VQA: A Subjective Video Quality Dataset for HDR and SDR Comparative Evaluation
  134. In Search of Adam's Secret Sauce
  135. SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
  136. Music Source Restoration
  137. Unsupervised Latent Pattern Analysis for Estimating Type 2 Diabetes Risk in Undiagnosed Populations
  138. Representative Language Generation
  139. Revisiting Common Assumptions about Arabic Dialects in NLP
  140. Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
  141. Optimizing Data Augmentation through Bayesian Model Selection
  142. Revisiting Self-attention for Cross-domain Sequential Recommendation
  143. Voice Quality Dimensions as Interpretable Primitives for Speaking Style for Atypical Speech and Affect
  144. Towards Operational Automated Greenhouse Gas Plume Detection and Delineation
  145. From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs
  146. PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective
  147. A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging
  148. SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
  149. Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms
  150. Global Minimizers of ℓp-Regularized Objectives Yield the Sparsest ReLU Neural Networks
  151. Faster Rates for Private Adversarial Bandits
  152. VeriTrail: Closed-Domain Hallucination Detection with Traceability
  153. Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
  154. P-DROP: Poisson-Based Dropout for Graph Neural Networks
  155. GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task
  156. Compositional Scene Understanding through Inverse Generative Modeling
  157. DualSchool: How Reliable are LLMs for Optimization Education?
  158. Calibrating LLM Confidence by Probing Perturbed Representation Stability
  159. MMTABREAL: Real-World Benchmark for Multimodal Table Understanding
  160. Gradient-flow SDEs have unique transient population dynamics
  161. Beyond Single-Channel: Multichannel Signal Imaging for PPG-to-ECG Reconstruction with Vision Transformers
  162. FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
  163. Visual Loop Closure Detection Through Deep Graph Consensus
  164. From prosthetic memory to prosthetic denial: Auditing whether large language models are prone to mass atrocity denialism
  165. Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
  166. Broad Spectrum Structure Discovery in Large-Scale Higher-Order Networks
  167. Learning to See More: UAS-Guided Super-Resolution of Satellite Imagery for Precision Agriculture
  168. Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen
  169. Counterfactual Simulatability of LLM Explanations for Generation Tasks
  170. Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks
  171. MIND-Stack: Modular, Interpretable, End-to-End Differentiability for Autonomous Navigation
  172. LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing
  173. pared: Model selection using multi-objective optimization
  174. OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
  175. Are Statistical Methods Obsolete in the Era of Deep Learning? A Study of ODE Inverse Problems
  176. Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
  177. Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
  178. Responsible Data Stewardship: Generative AI and the Digital Waste Problem
  179. Privacy-Preserving Chest X-ray Report Generation via Multimodal Federated Learning with ViT and GPT-2
  180. Assessing and Refining ChatGPT's Performance in Identifying Targeting and Inappropriate Language: A Comparative Study
  181. Network classification through random walks
  182. A Joint Reconstruction-Triplet Loss Autoencoder Approach Towards Unseen Attack Detection in IoV Networks
  183. Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
  184. STA-Risk: A Deep Dive of Spatio-Temporal Asymmetries for Breast Cancer Risk Prediction
  185. Learning to Upscale 3D Segmentations in Neuroimaging
  186. AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling
  187. MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs
  188. What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
  189. LLMPR: A Novel LLM-Driven Transfer Learning based Petition Ranking Model
  190. tenSVD algorithm for compression
  191. Incentivizing Permissionless Distributed Learning of LLMs
  192. multivariateGPT: a decoder-only transformer for multivariate categorical and numeric data
  193. What happens when generative AI models train recursively on each others' outputs?
  194. Make Planning Research Rigorous Again!
  195. Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
  196. Expert Survey: AI Reliability & Security Research Priorities
  197. STACI: Spatio-Temporal Aleatoric Conformal Inference
  198. Explaining Large Language Models with gSMILE
  199. PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
  200. AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
  201. Seeing Isn't Orienting: A Cognitively Informed Hierarchical Benchmark for Object Orientation in MLLMs
  202. Iterative Corpus Refinement for Materials Property Prediction Based on Scientific Texts
  203. Geometric Feature Prompting of Image Segmentation Models
  204. PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects
  205. BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration
  206. The Feasibility of Topic-Based Watermarking on Academic Peer Reviews
  207. Object Concepts Emerge from Motion
  208. Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter
  209. Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
  210. Learning where to learn: Training data distribution optimization for scientific machine learning
  211. VideoMarkBench: Benchmarking Robustness of Video Watermarking
  212. Preventing Adversarial AI Attacks Against Autonomous Situational Awareness: A Maritime Case Study
  213. How does Misinformation Affect Large Language Model Behaviors and Preferences?
  214. Public Discourse Sandbox: Facilitating Human and AI Digital Communication Research
  215. Leveraging XP and CRISP-DM for Agile Data Science Projects
  216. Optimizing Deep Learning for Skin Cancer Classification: A Computationally Efficient CNN with Minimal Accuracy Trade-Off
  217. Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learning
  218. Relevance-driven Input Dropout: an Explanation-guided Regularization Technique
  219. Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment
  220. Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI
  221. CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning
  222. Fairness in Federated Learning: Fairness for Whom?
  223. A Pure Hypothesis Test for Inhomogeneous Random Graph Models Based on a Kernelised Stein Discrepancy
  224. Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
  225. RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
  226. Concentration Distribution Learning from Label Distributions
  227. StreamLink: Large-Language-Model Driven Distributed Data Engineering System
  228. Spectral-inspired Operator Learning with Limited Data and Unknown Physics
  229. Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
  230. FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition
  231. Beyond Explainability: The Case for AI Validation
  232. VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents
  233. Towards Human-Like Trajectory Prediction for Autonomous Driving: A Behavior-Centric Approach
  234. Multi-instance Learning as Downstream Task of Self-Supervised Learning-based Pre-trained Model
  235. Fog Intelligence for Network Anomaly Detection
  236. Enhancing Selection of Climate Tech Startups with AI -- A Case Study on Integrating Human and AI Evaluations in the ClimaTech Great Global Innovation Challenge
  237. How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
  238. Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis
  239. Vision Transformers with Self-Distilled Registers
  240. Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
  241. Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
  242. Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
  243. Hypothesis Generation via LLM-Automated Language Bias for ILP
  244. MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
  245. Policy Optimized Text-to-Image Pipeline Design
  246. Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-index Models
  247. DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction
  248. Causal Posterior Estimation
  249. High-Dimensional Calibration from Swap Regret
  250. LazyVLM: Neuro-Symbolic Approach to Video Analytics
  251. ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
  252. Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendations
  253. Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling
  254. Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
  255. VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin
  256. Autoencoding Random Forests
  257. Towards Better Instruction Following Retrieval Models
  258. Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution
  259. CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects
  260. Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
  261. Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning
  262. Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
  263. When Shift Happens - Confounding Is to Blame
  264. A Physics-Augmented GraphGPS Framework for the Reconstruction of 3D Riemann Problems from Sparse Data
  265. Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learning
  266. Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs
  267. RelationalFactQA: A Benchmark for Evaluating Tabular Fact Retrieval from Large Language Models
  268. Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks
  269. Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
  270. A Structured Unplugged Approach for Foundational AI Literacy in Primary Education
  271. DecisionFlow: Advancing Large Language Model as Principled Decision Maker
  272. Augmenting Research Ideation with Data: An Empirical Investigation in Social Science
  273. Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits
  274. From Aggregation to Selection: User-Validated Distributed Social Recommendation
  275. Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
  276. PHISH in MESH: Korean Adversarial Phonetic Substitution and Phonetic-Semantic Feature Integration Defense
  277. Analyzing values about gendered language reform in LLMs' revisions
  278. Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility
  279. Improving LLM-based Global Optimization with Search Space Partitioning
  280. YOLO-SPCI: Enhancing Remote Sensing Object Detection via Selective-Perspective-Class Integration
  281. PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
  282. Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
  283. Subgroups Matter for Robust Bias Mitigation
  284. Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
  285. CRISP-NAM: Competing Risks Interpretable Survival Prediction with Neural Additive Models
  286. AgriFM: A Multi-source Temporal Remote Sensing Foundation Model for Agriculture Mapping
  287. Towards Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations
  288. Prostate Cancer Screening with Artificial Intelligence-Enhanced Micro-Ultrasound: A Comparative Study with Traditional Methods
  289. The Multilingual Divide and Its Impact on Global AI Safety
  290. PEDANTIC: A Dataset for the Automatic Examination of Definiteness in Patent Claims
  291. An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction
  292. Inspecting Training Dynamics of Similarity Development in Supervised Vision Networks
  293. Joint Learning in the Gaussian Single Index Model
  294. Structure from Collision
  295. Scheduling in Queueing Systems with Uncertain and Evolving Holding Costs
  296. UGCE: User-Guided Incremental Counterfactual Exploration
  297. Something's Fishy In The Data Lake: A Critical Re-evaluation of Table Union Search Benchmarks
  298. Leveraging large language models and traditional machine learning ensembles for ADHD detection from narrative transcripts
  299. Assured Autonomy with Neuro-Symbolic Perception
  300. Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization
  301. efunc: An Efficient Function Representation without Neural Networks
  302. Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism
  303. Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead
  304. Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation
  305. Optimizing fMRI Data Acquisition for Decoding Natural Speech with Limited Participants
  306. How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian
  307. LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
  308. Are Graph Attention Networks Able to Model Structural Information?
  309. Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detection
  310. RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models
  311. Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands
  312. Multilingual Pretraining for Pixel Language Models
  313. DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution
  314. Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation
  315. Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
  316. ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
  317. Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings
  318. BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Design
  319. A Unified LLM-Adaptable Framework for Cold-Start Cognitive Diagnosis
  320. 3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
  321. Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning
  322. PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems
  323. Is Hyperbolic Space All You Need for Medical Anomaly Detection?
  324. Why Do More Experts Fail? A Theoretical Analysis of Model Merging
  325. A Representation Level Analysis of NMT Model Robustness to Grammatical Errors
  326. Wavelet Flow For Extragalactic Foreground Simulations
  327. Addressing Data Quality Decompensation in Federated Learning via Dynamic Client Selection
  328. Pretrained LLMs Learn Multiple Types of Uncertainty
  329. Transfer learning for multifidelity simulation-based inference in cosmology
  330. Interpretable DNFs
  331. Input Convex Kolmogorov Arnold Networks
  332. EF-VI: Enhancing End-Frame Injection for Video Inbetweening
  333. Developing hybrid mechanistic and data-driven personalized prediction models for platelet dynamics
  334. Crop recommendation with machine learning: leveraging environmental and economic factors for optimal crop selection
  335. Learning Annotation Consensus for Continuous Emotion Recognition
  336. Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation
  337. Exploring the Hidden Capacity of LLMs for One-Step Text Generation
  338. Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling
  339. Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion
  340. Latent label distribution grid representation for modeling uncertainty
  341. Topological Deep Learning for Speech Data
  342. M-Wanda: Improving One-Shot Pruning for Multilingual LLMs
  343. Quantum AIXI: Universal Intelligence via Quantum Information
  344. Leveraging GANs for citation intent classification and its impact on citation network analysis
  345. STEB: In Search of the Best Evaluation Approach for Synthetic Time Series
  346. Model as Loss: A Self-Consistent Training Paradigm
  347. GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation
  348. RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
  349. Assessment of L2 Oral Proficiency using Speech Large Language Models
  350. Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score
  351. A Predicting Phishing Websites Using Support Vector Machine and MultiClass Classification Based on Association Rule Techniques
  352. HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
  353. Identifying Heart Attack Risk in Vulnerable Population: A Machine Learning Approach
  354. Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis
  355. Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction
  356. SageAttention2++: A More Efficient Implementation of SageAttention2
  357. Robust and Computation-Aware Gaussian Processes
  358. ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction
  359. Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
  360. A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction
  361. Instance Data Condensation for Image Super-Resolution
  362. Improved Impossible Tuning and Lipschitz-Adaptive Universal Online Learning with Gradient Variations
  363. BLUCK: A Benchmark Dataset for Bengali Linguistic Understanding and Cultural Knowledge
  364. Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)
  365. Stopping Criteria for Value Iteration on Concurrent Stochastic Reachability and Safety Games
  366. Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity
  367. Predicting Implicit Arguments in Procedural Video Instructions
  368. Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals
  369. Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles
  370. Advancing high-fidelity 3D and Texture Generation with 2.5D latents
  371. Robust Video-Based Pothole Detection and Area Estimation for Intelligent Vehicles with Depth Map and Kalman Smoothing
  372. A domain adaptation neural network for digital twin-supported fault diagnosis
  373. Large Language Model-enhanced Reinforcement Learning for Low-Altitude Economy Networking
  374. Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interaction
  375. CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians
  376. FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis
  377. Scalable and adaptive prediction bands with kernel sum-of-squares
  378. LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms
  379. TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
  380. Text-Queried Audio Source Separation via Hierarchical Modeling
  381. Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
  382. NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation
  383. Cardiac Digital Twins at Scale from MRI: Open Tools and Representative Models from ~55000 UK Biobank Participants
  384. Federated Instrumental Variable Analysis via Federated Generalized Method of Moments
  385. LLMs are Frequency Pattern Learners in Natural Language Inference
  386. Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains
  387. Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?
  388. Facial Attribute Based Text Guided Face Anonymization
  389. BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks
  390. Articulatory strategy in vowel production as a basis for speaker discrimination
  391. Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
  392. Assessing the Use of Face Swapping Methods as Face Anonymizers in Videos
  393. RefAV: Towards Planning-Centric Scenario Mining
  394. Identifying Super Spreaders in Multilayer Networks
  395. MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection
  396. Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing
  397. Deep k-grouping: An Unsupervised Learning Framework for Combinatorial Optimization on Graphs and Hypergraphs
  398. Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
  399. RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
  400. Personalized Query Auto-Completion for Long and Short-Term Interests with Adaptive Detoxification Generation
  401. Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence
  402. Context-Aware Content Moderation for German Newspaper Comments
  403. Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning
  404. Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization
  405. Research Community Perspectives on "Intelligence" and Large Language Models
  406. Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection
  407. DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Prediction
  408. Scattering Networks on Noncommutative Finite Groups
  409. Streamlining Knowledge Graph Creation with PyRML
  410. Unified Deep Learning Approach for Estimating the Metallicities of RR Lyrae Stars Using light curves from Gaia Data Release 3
  411. Efficient Spectral Control of Partially Observed Linear Dynamical Systems
  412. Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning
  413. NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
  414. Information-Theoretic Complementary Prompts for Improved Continual Text Classification
  415. QwT-v2: Practical, Effective and Efficient Post-Training Quantization
  416. MLMC-based Resource Adequacy Assessment with Active Learning Trained Surrogate Models
  417. Good Enough? An Investigation on the Impact of Label Quality in Large-Scale Medical Datasets
  418. Label Leakage in Federated Inertial-based Human Activity Recognition
  419. Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models
  420. HuMoCon: Concept Discovery for Human Motion Understanding
  421. Humble AI in the real-world: the case of algorithmic hiring
  422. Automated Privacy Information Annotation in Large Language Model Interactions
  423. Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?
  424. Multitemporal Latent Dynamical Framework for Hyperspectral Images Unmixing
  425. Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
  426. Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
  427. How Do Transformers Learn Variable Binding in Symbolic Programs?
  428. DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
  429. One-Time Soft Alignment Enables Resilient Learning without Weight Transport
  430. Frequency Composition for Compressed and Domain-Adaptive Neural Networks
  431. Improved Bounds for Swap Multicalibration and Swap Omniprediction
  432. YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation
  433. Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning
  434. Generalizable Heuristic Generation Through LLMs with Meta-Optimization
  435. MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection
  436. Stereo Radargrammetry Using Deep Learning from Airborne SAR Images
  437. Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties
  438. Can LLMs Learn to Map the World from Local Descriptions?
  439. Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models
  440. In Context Learning with Vision Transformers: Case Study
  441. Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
  442. Respond to Change with Constancy: Instruction-tuning with LLM for Non-I.I.D. Network Traffic Classification
  443. Stability Selection via Variable Decorrelation
  444. Exploring Timeline Control for Facial Motion Generation
  445. ProBA: Probabilistic Bundle Adjustment with the Bhattacharyya Coefficient
  446. An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
  447. Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
  448. Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
  449. Fully Spiking Neural Networks for Unified Frame-Event Object Tracking
  450. Causality-Driven Infrared and Visible Image Fusion
  451. Frame-Level Captions for Long Video Generation with Complex Multi Scenes
  452. AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset
  453. Tracing and Reversing Edits in LLMs
  454. High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and (L0,L1)-Smoothness
  455. Interpretable Credit Default Prediction with Ensemble Learning and SHAP
  456. Spatial RoboGrasp: Generalized Robotic Grasping Control Policy
  457. RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph
  458. The Role of AI in Early Detection of Life-Threatening Diseases: A Retinal Imaging Perspective
  459. Simple yet Effective Graph Distillation via Clustering
  460. Quantum Machine Learning in Healthcare: Evaluating QNN and QSVM Models
  461. Leaner Transformers: More Heads, Less Depth
  462. Multi-VQC: A Novel QML Approach for Enhancing Healthcare Classification
  463. VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion
  464. Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset
  465. Debiased Ill-Posed Regression
  466. FM-Planner: Foundation Model Guided Path Planning for Autonomous Drone Navigation
  467. Towards Cross-Domain Multi-Targeted Adversarial Attacks
  468. CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation
  469. Non-invasive maturity assessment of iPSC-CMs based on optical maturity characteristics using interpretable AI
  470. TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
  471. MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning
  472. Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems
  473. CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
  474. Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomalies
  475. ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
  476. Practical estimation of the optimal classification error with soft labels and calibration
  477. Stationary MMD Points
  478. Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing
  479. Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation
  480. MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
  481. 'Hello, World!': Making GNNs Talk with LLMs
  482. Detecting Informative Channels: ActionFormer
  483. Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
  484. Adversarial bandit optimization for approximately linear functions
  485. E2E Process Automation Leveraging Generative AI and IDP-Based Automation Agent: A Case Study on Corporate Expense Processing
  486. Semi-supervised Clustering Through Representation Learning of Large-scale EHR Data
  487. Do LLMs Understand Collaborative Signals? Diagnosis and Repair
  488. Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting
  489. Recurrent Neural Operators: Stable Long-Term PDE Prediction
  490. Are Data Embeddings effective in time series forecasting?
  491. Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting
  492. Hierarchical Instruction-aware Embodied Visual Tracking
  493. Time-Series Learning for Proactive Fault Prediction in Distributed Systems with Deep Neural Structures
  494. Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
  495. Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series
  496. Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets
  497. Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages
  498. Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions
  499. Evidential Deep Active Learning for Semi-Supervised Classification
  500. A False Discovery Rate Control Method Using a Fully Connected Hidden Markov Random Field for Neuroimaging Data
  501. VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images
  502. Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
  503. SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
  504. Supervised Contrastive Learning for Ordinal Engagement Measurement
  505. Contrastive Desensitization Learning for Cross Domain Face Forgery Detection
  506. PonderLM: Pretraining Language Models to Ponder in Continuous Space
  507. LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation
  508. Continuous-Time Attention: PDE-Guided Mechanisms for Long-Sequence Transformers
  509. TeroSeek: An AI-Powered Knowledge Base and Retrieval Generation Platform for Terpenoid Research
  510. AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
  511. Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge
  512. Photography Perspective Composition: Towards Aesthetic Perspective Recommendation
  513. Chinese Cyberbullying Detection: Dataset, Method, and Validation
  514. RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment
  515. FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
  516. Scan-and-Print: Patch-level Data Summarization and Augmentation for Content-aware Layout Generation in Poster Design
  517. Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning
  518. Moment Expansions of the Energy Distance
  519. Binarized Neural Networks Converge Toward Algorithmic Simplicity: Empirical Support for the Learning-as-Compression Hypothesis
  520. STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models
  521. HCQA-1.5 @ Ego4D EgoSchema Challenge 2025
  522. CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models
  523. See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
  524. Open-Det: An Efficient Learning Framework for Open-Ended Detection
  525. TrustSkin: A Fairness Pipeline for Trustworthy Facial Affect Analysis Across Skin Tone
  526. Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction
  527. Explaining Concept Shift with Interpretable Feature Attribution
  528. Test-Time Learning for Large Language Models
  529. Unified Text-Image-to-Video Generation: A Training-Free Approach to Flexible Visual Conditioning
  530. Position: Adopt Constraints Over Fixed Penalties in Deep Learning
  531. ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation
  532. POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization
  533. OccLE: Label-Efficient 3D Semantic Occupancy Prediction
  534. Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea
  535. OmniIndoor3D: Comprehensive Indoor 3D Reconstruction
  536. Comparisons between a Large Language Model-based Real-Time Compound Diagnostic Medical AI Interface and Physicians for Common Internal Medicine Cases using Simulated Patients
  537. Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation