mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 29 May 2025

608 papers

  1. A Survey of Generative Categories and Techniques in Multimodal Generative ModelsMixture-of-experts → Multimodal MoE models
  2. Composite Reward Design in PPO-Driven Adaptive FilteringDeep reinforcement learning methods → RL theory and sample complexity
  3. Contextual Integrity in LLMs via Reasoning and Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  4. Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  5. Vid-SME: Membership Inference Attacks against Large Video Understanding ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  6. FOLIAGE: Towards Physical Intelligence World Models Via Unbounded Surface EvolutionWorld models → Latent predictive world models
  7. Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job SchedulingLLM reasoning → Test-time compute and efficient thinking
  8. The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer MarketsLLM agents and tool use → Social simulation and multi-agent debate
  9. Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in RoboticsLLM reasoning → Spatial and embodied reasoning +1
  10. Literature Review Of Multi-Agent Debate For Problem-SolvingLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  12. mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  13. Can LLMs Reason Structurally? Benchmarking via the Lens of Data StructuresLLM reasoning → Reasoning benchmarks and evaluation
  14. Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learningDeep reinforcement learning methods → Deep RL algorithms and representations
  15. DINO-R1: Incentivizing Reasoning Capability in Vision Foundation ModelsLLM reasoning → Multimodal reasoning
  16. LLM Agents Should Employ Security PrinciplesLLM agents and tool use → Agent threats, guardrails and governance +1
  17. Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language ModelMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  18. Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video UnderstandingRetrieval-augmented generation → Multimodal RAG
  19. MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and KnowledgeLLM reasoning → Clinical and biomedical applications
  20. VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RLLLM reasoning → Multimodal reasoning +1
  21. Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model ServingEfficient LLM inference and serving → KV cache optimization
  22. FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model CompressionEfficient LLM inference and serving → Early exit and edge inference
  23. InterMT: Multi-Turn Interleaved Preference Alignment with Human FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  24. Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and ImproveLLM agents and tool use → Software engineering coding agents
  25. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language ModelsLLM reasoning → Multimodal reasoning
  26. Retrieval Augmented Generation based Large Language Models for Causality MiningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  27. Vision Language Models are BiasedMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  28. Scaling up the think-aloud methodLLM reasoning → Reasoning benchmarks and evaluation
  29. Thompson Sampling in Online RLHF with General Function ApproximationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  30. Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic SegmentationMixture-of-experts → Vision mixture-of-experts
  31. Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective AmbiguityLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  32. Generating Fit Check Videos with a Handheld CameraDiffusion models → Video generation
  33. OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task AutomationLLM reasoning → Reasoning for agents, planning and code +1
  34. Test-Time Training Done RightDiffusion models → Video generation
  35. Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design ProblemsLLM reasoning → Mathematical reasoning
  36. KGMark: A Diffusion Watermark for Knowledge GraphsLLM safety and security → Watermarking generated content and models
  37. ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  38. Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoEMixture-of-experts → Mixture of LoRA experts
  39. InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and ReasoningLLM reasoning → Clinical and biomedical applications +1
  40. A Convolution and Attention Based Encoder for Reinforcement Learning under Partial ObservabilityDeep reinforcement learning methods → Deep RL algorithms and representations
  41. OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and ModalitiesLLM safety and security → Safety alignment, refusal and guardrails
  42. Revisiting Uncertainty Estimation and Calibration of Large Language ModelsMixture-of-experts → MoE large language models
  43. Large Language Model-Based Agents for Automated Research Reproducibility: An Exploratory Study in Alzheimer's DiseaseLLM agents and tool use → Medical and scientific domain agents
  44. Argus: Vision-Centric Reasoning with Grounded Chain-of-ThoughtLLM reasoning → Multimodal reasoning +1
  45. MMSI-Bench: A Benchmark for Multi-Image Spatial IntelligenceLLM reasoning → Spatial and embodied reasoning +1
  46. ZeroGUI: Automating Online GUI Learning at Zero Human CostMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  47. Differential Information Distribution: A Bayesian Perspective on Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  48. Puzzled by Puzzles: When Vision-Language Models Can't Take a HintMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  49. LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow TransformersDiffusion models → Image generation, text-to-image and editing
  50. Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action ModelsVision-language-action models → VLA for autonomous driving +1
  51. DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement LearningLLM reasoning → Mathematical reasoning
  52. ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing TasksLLM reasoning → Spatial and embodied reasoning +1
  53. Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  54. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  55. To Trust Or Not To Trust Your Vision-Language Model's PredictionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  56. DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISPDiffusion models → Inverse problems and image restoration
  57. Bounded Rationality for LLMs: Satisficing Alignment at Inference-TimeLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  58. PixelThink: Towards Efficient Chain-of-Pixel ReasoningLLM reasoning → Multimodal reasoning +1
  59. ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringLLM agents and tool use → Reinforcement learning for LLM agents
  60. LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity RecognitionLLM reasoning → Multimodal reasoning
  61. DiffER: Categorical Diffusion for Chemical RetrosynthesisDiffusion models → Flow matching, time series and science
  62. Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  63. SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social EnvironmentsLLM reasoning → Reasoning benchmarks and evaluation
  64. AMOR: Adaptive Character Control through Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  65. Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize BetterMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  66. Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math CapabilityLLM reasoning → Mathematical reasoning
  67. Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic ComputationLLM reasoning → Mathematical reasoning
  68. Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise AnalyticsLLM agents and tool use → Web, search, and research agents
  69. VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  70. Grounded Reinforcement Learning for Visual ReasoningLLM reasoning → Multimodal reasoning
  71. ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung CancerDiffusion models → Medical imaging and segmentation
  72. Bayesian Optimization from Human Feedback: Near-Optimal Regret BoundsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  73. GSO: Challenging Software Optimization Tasks for Evaluating SWE-AgentsLLM agents and tool use → Software engineering coding agents
  74. Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  75. ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term InteractionsLLM agents and tool use → Tool learning and function calling
  76. Bayesian Perspective on Memorization and ReconstructionLLM safety and security → Membership inference attacks
  77. VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation ModelsDiffusion models → Video generation
  78. How do Transformers Learn Implicit Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
  79. Optimization-Free Diffusion Model -- A Perturbation Theory ApproachDiffusion models → Diffusion foundations and sampling
  80. Continuous Chain of Thought Enables Parallel Exploration and ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  81. Are Reasoning Models More Prone to Hallucination?LLM reasoning → Hallucination detection and mitigation
  82. MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference AlignmentLLM agents and tool use → Agent threats, guardrails and governance +2
  83. ZeroSep: Separate Anything in Audio with Zero TrainingDiffusion models → Audio, speech and music
  84. Table-R1: Inference-Time Scaling for Table ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  85. Inference-time Scaling of Diffusion Models through Classical SearchLLM reasoning → Diffusion reasoning and test-time scaling +1
  86. Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  87. Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software EngineeringLLM reasoning → Reasoning for agents, planning and code
  88. EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  89. Agent-SAMA: State-Aware Mobile AssistantLLM agents and tool use → GUI and mobile agents
  90. Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw PuzzlesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  91. On-Policy RL with Optimal Reward BaselineLLM reasoning → Reinforcement learning for reasoning +1
  92. BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM ModelLLM reasoning → Clinical and biomedical applications
  93. Cognitive Guardrails for Open-World Decision Making in Autonomous Drone SwarmsLLM safety and security → Prompt injection and agent security
  94. CoT Red-Handed: Stress Testing Chain-of-Thought MonitoringLLM reasoning → Prompting and chain-of-thought reasoning
  95. Evaluating AI capabilities in detecting conspiracy theories on YouTubeLLM safety and security → Safety alignment, refusal and guardrails
  96. Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression RecognitionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  97. Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  98. Merge Hijacking: Backdoor Attacks to Model Merging of Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  99. SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  100. Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual InformationLLM reasoning → Multimodal reasoning +1
All 608
  1. Learning Parametric Distributions from Samples and PreferencesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  2. Understanding Refusal in Language Models with Sparse AutoencodersLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  3. Probability-Consistent Preference Optimization for Enhanced LLM ReasoningLLM reasoning → Mathematical reasoning +1
  4. Normalizing Flows are Capable Models for Continuous ControlDeep reinforcement learning methods → RL with diffusion and flow models
  5. TRAP: Targeted Redirecting of Agentic PreferencesLLM reasoning → Multimodal reasoning +2
  6. Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable BenchmarkingLLM reasoning → Knowledge- and tool-augmented reasoning
  7. Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-DoubtLLM reasoning → Test-time compute and efficient thinking
  8. Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning PatternsLLM reasoning → Reinforcement learning for reasoning +2
  9. EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious InstructionsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  10. LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment AdapterDiffusion models → Inverse problems and image restoration
  11. On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
  12. Diffusion Guidance Is a Controllable Policy Improvement OperatorOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  13. Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied AgentsVision-language-action models → Reasoning and chain-of-thought in VLA +1
  14. CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation DetectionLLM reasoning → Multimodal reasoning +1
  15. CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM SynthesisDiffusion models → Flow matching, time series and science
  16. Emergent Risk Awareness in Rational Agents under Resource ConstraintsLLM reasoning → Reasoning for agents, planning and code +1
  17. Diversity-Aware Policy Optimization for Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  18. Enhanced DACER Algorithm with High Diffusion EfficiencyDiffusion models → Diffusion and flow policies for robotics +1
  19. From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  20. KVzip: Query-Agnostic KV Cache Compression with Context ReconstructionEfficient LLM inference and serving → KV cache optimization
  21. AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language ModelsLLM safety and security → Jailbreaking
  22. GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual ReasoningLLM reasoning → Multimodal reasoning +1
  23. Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +2
  24. AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive ReasoningLLM reasoning → Spatial and embodied reasoning
  25. UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  26. Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label VariationLLM reasoning → Prompting and chain-of-thought reasoning
  27. Discriminative Policy Optimization for Token-Level Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  28. VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?LLM reasoning → Multimodal reasoning
  29. Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  30. Grower-in-the-Loop Interactive Reinforcement Learning for Greenhouse Climate ControlDeep reinforcement learning methods → RL for energy, networks and operations
  31. Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. Towards Reward Fairness in RLHF: From a Resource Allocation PerspectiveLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  33. Beyond Optimal Transport: Model-Aligned Coupling for Flow MatchingDiffusion models → Flow matching, time series and science
  34. Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample FilteringDiffusion models → Diffusion foundations and sampling
  35. Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data PriorsLLM reasoning → Test-time compute and efficient thinking
  36. Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  37. TRACE: Trajectory-Constrained Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  38. Score-based Generative Modeling for Conditional Independence TestingDiffusion models → Diffusion foundations and sampling
  39. MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source ExtractionDiffusion models → Audio, speech and music
  40. Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMsRetrieval-augmented generation → Hallucination detection in RAG
  41. RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing ForgeriesDiffusion models → Inverse problems and image restoration
  42. MathArena: Evaluating LLMs on Uncontaminated Math CompetitionsLLM reasoning → Mathematical reasoning
  43. Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context CompressionRetrieval-augmented generation → Generation and context integration +1
  44. Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic PerceptionRetrieval-augmented generation → Agentic RAG, agents and memory
  45. LADA: Scalable Label-Specific CLIP Adapter for Continual LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  46. Does Machine Unlearning Truly Remove Knowledge?LLM safety and security → Machine unlearning
  47. VLM-RRT: Vision Language Model Guided RRT Search for Autonomous UAV NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  48. Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object FusionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  49. SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  50. Efficiently Access Diffusion Fisher: Within the Outer Product Span SpaceDiffusion models → Diffusion foundations and sampling
  51. Accelerating RLHF Training with Reward Variance IncreaseLLM reasoning → Reinforcement learning for reasoning +1
  52. Equivalence of stochastic and deterministic policy gradientsDeep reinforcement learning methods → RL theory and sample complexity
  53. ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question AnsweringLLM reasoning → Multimodal reasoning +1
  54. OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source SoftwareLLM agents and tool use → Software engineering coding agents
  55. MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence CalibrationLLM reasoning → Multimodal reasoning +1
  56. Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core ParallelismEfficient LLM inference and serving → Speculative decoding
  57. SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  58. Cross-Task Experiential Learning on LLM-based Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  59. HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment ImageDiffusion models → 3D, point cloud and scene generation
  60. Two Is Better Than One: Rotations Scale LoRAsMixture-of-experts → Mixture of LoRA experts
  61. Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static VerificationSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  62. RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy TransferDiffusion models → Diffusion and flow policies for robotics
  63. FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image EditingDiffusion models → Image generation, text-to-image and editing
  64. PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist AgentsLLM agents and tool use → Multimodal and embodied agents
  65. HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target ScoringEnd-to-end autonomous driving → End-to-end system architecture
  66. PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical LinguisticsLLM reasoning → Reasoning benchmarks and evaluation
  67. ContextQFormer: A New Context Modeling Method for Multi-Turn Multi-Modal ConversationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  68. TextSR: Diffusion Super-Resolution with Multilingual OCR GuidanceDiffusion models → Inverse problems and image restoration
  69. Elicit and Enhance: Advancing Multimodal Reasoning in Medical ScenariosLLM reasoning → Clinical and biomedical applications
  70. Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics
  71. Alignment Data Map for Efficient Preference Data Selection and DiagnosisLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  72. Learning to Search for Vehicle Routing with Multiple Time WindowsDeep reinforcement learning methods → RL for games and combinatorial optimization
  73. Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language ModelsLLM reasoning → Multimodal reasoning
  74. GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video DiffusionDiffusion models → 3D, point cloud and scene generation
  75. SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking ServicesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  76. Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics DataDiffusion models → Diffusion and flow policies for robotics +1
  77. From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  78. CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model AgentsLLM agents and tool use → Medical and scientific domain agents
  79. RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  80. ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory ImputationDiffusion models → Diffusion and flow policies for robotics
  81. Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled StudyMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  82. Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug InteractionLLM reasoning → Clinical and biomedical applications
  83. An Empirical Study of Federated Prompt Learning for Vision Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  84. Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  85. AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance +2
  86. Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  87. Scalable Complexity Control Facilitates Reasoning Ability of LLMsLLM reasoning → Test-time compute and efficient thinking
  88. A Practical Approach for Building Production-Grade Conversational Agents with Workflow GraphsLLM agents and tool use → General LLM agent frameworks and benchmarks
  89. QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without RetrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  90. Hybrid Cross-domain Robust Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  91. DyePack: Provably Flagging Test Set Contamination in LLMs Using BackdoorsLLM safety and security → Backdoor and data poisoning attacks
  92. LLM Agents for Bargaining with Utility-based FeedbackLLM agents and tool use → Social simulation and multi-agent debate +1
  93. Knowledge Distillation for Reservoir-based Classifier: Human Activity RecognitionKnowledge distillation → Distillation for medical imaging
  94. Free Lunch for User Experience: Crowdsourcing Agents for Scalable User StudiesLLM agents and tool use → Social simulation and multi-agent debate
  95. MOVi: Training-free Text-conditioned Multi-Object Video GenerationDiffusion models → Video generation
  96. Learning Recommender Mechanisms for Bayesian Stochastic GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  97. HyperMotionX: The Dataset and Benchmark with DiT-Based Pose-Guided Human Image Animation of Complex MotionsDiffusion models → Video generation
  98. LoopNav: Benchmarking Spatial Consistency in World ModelsWorld models → Video-generation world models and simulators
  99. Learning coordinated badminton skills for legged manipulatorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  100. EquiReg: Equivariance Regularized Diffusion for Inverse ProblemsDiffusion models → Inverse problems and image restoration
  101. MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary ProgrammingLLM agents and tool use → Software engineering coding agents
  102. Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional EffectivenessLLM reasoning → Reasoning for agents, planning and code +1
  103. LLM-based HSE Compliance Assessment: Benchmark, Performance, and AdvancementsLLM reasoning → Reasoning for agents, planning and code
  104. Darwin Godel Machine: Open-Ended Evolution of Self-Improving AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  105. StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMsLLM reasoning → Reasoning benchmarks and evaluation
  106. RISEE: A Highly Interactive Naturalistic Driving Trajectories Dataset with Human Subjective Risk Perception and Eye-tracking Information
  107. Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans
  108. Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis
  109. Neural networks with image recognition by pairs
  110. DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarios
  111. TerraIncognita: A Dynamic Benchmark for Species Discovery Using Frontier Models
  112. Dc-EEMF: Pushing depth-of-field limit of photoacoustic microscopy via decision-level constrained learning
  113. Knowledge Graphs for Digitized Manuscripts in Jagiellonian Digital Library Application
  114. LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning
  115. Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population
  116. Non-collective Calibrating Strategy for Time Series Forecasting
  117. Super-temporal-resolution Photoacoustic Imaging with Dynamic Reconstruction through Implicit Neural Representation in Sparse-view
  118. Multimodal Foundation Model for Cross-Modal Retrieval and Activity Recognition Tasks
  119. The End Of Universal Lifelong Identifiers: Identity Systems For The AI Era
  120. Gaussian mixture models as a proxy for interacting language models
  121. Optimizing Storytelling, Improving Audience Retention, and Reducing Waste in the Entertainment Industry
  122. Reducing Latency in LLM-Based Natural Language Commands Processing for Robot Navigation
  123. Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations
  124. Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs
  125. Human sensory-musculoskeletal modeling and control of whole-body movements
  126. Evaluating the Sensitivity of LLMs to Prior Context
  127. Framing Political Bias in Multilingual LLMs Across Pakistani Languages
  128. Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models
  129. Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling
  130. Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs
  131. Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports
  132. Prompt Engineer: Analyzing Hard and Soft Skill Requirements in the AI Job Market
  133. Hierarchical Bayesian Knowledge Tracing in Undergraduate Engineering Education
  134. Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy
  135. SIM: A mapping framework for built environment auditing based on street view imagery
  136. Primal-Dual Neural Algorithmic Reasoning
  137. Adaptive Resolution for Finite-Rank Gaussian Processes
  138. Cross-Modal Characterization of Thin Film MoS2 Using Generative Models
  139. TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
  140. Exploring Domain Wall Pinning in Ferroelectrics via Automated High Throughput AFM
  141. Characterising the Inductive Biases of Neural Networks on Boolean Data
  142. Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition
  143. Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs
  144. Differential Gated Self-Attention
  145. 3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
  146. NeuronTune: Towards Self-Guided Spurious Bias Mitigation
  147. MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering
  148. Conformal Object Detection by Sequential Risk Control
  149. Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
  150. GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs
  151. LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training
  152. Studying the Soupability of Documents in State Space Models
  153. Leveraging machine learning features for linear optical interferometer control
  154. From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?
  155. Hidden Persuasion: Detecting Manipulative Narratives on Social Media During the 2022 Russian Invasion of Ukraine
  156. MaskAdapt: Unsupervised Geometry-Aware Domain Adaptation Using Multimodal Contextual Learning and RGB-Depth Masking
  157. Multi-Group Proportional Representation for Text-to-Image Models
  158. The Rich and the Simple: On the Implicit Bias of Adam and SGD
  159. BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
  160. Large Language Model Meets Constraint Propagation
  161. Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
  162. A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study
  163. How far away are truly hyperparameter-free learning algorithms?
  164. Redefining Research Crowdsourcing: Incorporating Human Feedback with LLM-Powered Digital Twins
  165. Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
  166. DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessment
  167. Multi-output Classification using a Cross-talk Architecture for Compound Fault Diagnosis of Motors in Partially Labeled Condition
  168. Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
  169. Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization
  170. DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets
  171. Adaptive Deadline and Batch Layered Synchronized Federated Learning
  172. Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
  173. Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
  174. Improved Approximations for Hard Graph Problems using Predictions
  175. Acoustic Classification of Maritime Vessels using Learnable Filterbanks
  176. Can Emotion Fool Anti-spoofing?
  177. MangoLeafViT: Leveraging Lightweight Vision Transformer with Runtime Augmentation for Efficient Mango Leaf Disease Classification
  178. Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation
  179. Estimating Misreporting in the Presence of Genuine Modification: A Causal Perspective
  180. Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
  181. Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review
  182. TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
  183. Position: The Future of Bayesian Prediction Is Prior-Fitted
  184. SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations
  185. Searching Neural Architectures for Sensor Nodes on IoT Gateways
  186. BIRD: Behavior Induction via Representation-structure Distillation
  187. SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving
  188. Exploring Societal Concerns and Perceptions of AI: A Thematic Analysis through the Lens of Problem-Seeking
  189. ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
  190. Representational Difference Explanations
  191. Estimation of Head Motion in Structural MRI and its Impact on Cortical Thickness Measurements in Retrospective Data
  192. Probing Association Biases in LLM Moderation Over-Sensitivity
  193. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling
  194. LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
  195. One Task Vector is not Enough: A Large-Scale Study for In-Context Learning
  196. Cora: Correspondence-aware image editing using few step diffusion
  197. BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
  198. CNN-LSTM Hybrid Model for AI-Driven Prediction of COVID-19 Severity from Spike Sequences and Clinical Data
  199. AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining
  200. A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
  201. A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
  202. Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
  203. MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection
  204. Gibbs randomness-compression proposition
  205. Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
  206. Combining Deep Architectures for Information Gain estimation and Reinforcement Learning for multiagent field exploration
  207. Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
  208. PhyxMamba: Chaotic System Reconstruction from Short Context Observations with Generative State-Space Models
  209. mRNA Design and Optimization with Deep Knowledge-Infused Approach
  210. BiBLDR: Bidirectional Behavior Learning for Drug Repositioning
  211. Quantum computing and artificial intelligence: status and perspectives
  212. Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
  213. A Start To End Machine Learning Approach To Maximize Scientific Throughput From The LCLS-II-HE
  214. TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
  215. From Chat Logs to Collective Insights: Aggregative Question Answering
  216. Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
  217. Model Immunization from a Condition Number Perspective
  218. Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping
  219. REOrdering Patches Improves Vision Models
  220. Comparative of Genetic Fuzzy regression techniques for aeroacoustic phenomenons
  221. Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
  222. MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
  223. LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization
  224. How Animals Dance (When You're Not Looking)
  225. On the Convergence Analysis of Muon
  226. ATLAS: Learning to Optimally Memorize the Context at Test Time
  227. ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
  228. Unintentional Consequences: Generative AI Use for Cybercrime
  229. EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast
  230. FMG-Det: Foundation Model Guided Robust Object Detection
  231. MuLoCo: Muon is a practical inner optimizer for DiLoCo
  232. SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
  233. COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents
  234. TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
  235. AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
  236. SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods
  237. From Connectivity to Autonomy: The Dawn of Self-Evolving Communication Systems
  238. Skin Lesion Phenotyping via Nested Multi-modal Contrastive Learning
  239. Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
  240. CLDTracker: A Comprehensive Language Description for Visual Tracking
  241. (U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
  242. DiCoFlex: Model-agnostic diverse counterfactuals with flexible control
  243. Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
  244. DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  245. Mobi-π: Mobilizing Your Robot Learning Policy
  246. Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models
  247. Automatic classification of stop realisation with wav2vec2.0
  248. ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
  249. Learning Compositional Functions with Transformers from Easy-to-Hard Data
  250. Understanding Mode Connectivity via Parameter Space Symmetry
  251. LoLA: Low-Rank Linear Attention With Sparse Caching
  252. AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
  253. OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
  254. D-AR: Diffusion via Autoregressive Models
  255. Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
  256. Keyed Chaotic Dynamics for Privacy-Preserving Neural Inference
  257. ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs
  258. Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
  259. Securing AI Agents with Information-Flow Control
  260. Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis
  261. Global optimization of graph acquisition functions for neural architecture search
  262. Comparing the Effects of Persistence Barcodes Aggregation and Feature Concatenation on Medical Imaging
  263. Human Empathy as Encoder: AI-Assisted Depression Assessment in Special Education
  264. GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns
  265. Color Image Set Recognition Based on Quaternionic Grassmannians
  266. AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
  267. Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection
  268. Towards Explainable Sequential Learning
  269. Characterizing the Expressivity of Fixed-Precision Transformer Language Models
  270. Instance-Optimality for Private KL Distribution Estimation
  271. Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
  272. One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
  273. Learning Interpretable Differentiable Logic Networks for Tabular Regression
  274. Autoregressive Meta-Actions for Unified Controllable Trajectory Generation
  275. The Generalized Skew Spectrum of Graphs
  276. Data Model Design for Explainable Machine Learning-based Electricity Applications
  277. On Transferring Transferability: Towards a Theory for Size Generalization
  278. LLM Performance for Code Generation on Noisy Tasks
  279. Bridging Classical and Modern Computer Vision: PerceptiveNet for Tree Crown Semantic Segmentation
  280. DeepChest: Dynamic Gradient-Free Task Weighting for Effective Multi-Task Learning in Chest X-ray Classification
  281. Multilook Coherent Imaging: Theoretical Guarantees and Algorithms
  282. Federated Foundation Language Model Post-Training Should Focus on Open-Source Models
  283. Accelerated Training of Federated Learning via Second-Order Methods
  284. PCA for Enhanced Cross-Dataset Generalizability in Breast Ultrasound Tumor Segmentation
  285. Weakly-supervised Localization of Manipulated Image Regions Using Multi-resolution Learned Features
  286. Collaborative Last-Mile Delivery: A Multi-Platform Vehicle Routing Problem With En-route Charging
  287. Improving Time Series Forecasting via Instance-aware Post-hoc Revision
  288. Engineering Serendipity through Recommendations of Items with Atypical Aspects
  289. Maximum Likelihood Learning of Latent Dynamics Without Reconstruction
  290. DRO: A Python Library for Distributionally Robust Optimization in Machine Learning
  291. Adaptive Federated LoRA in Heterogeneous Wireless Networks with Independent Sampling
  292. Sustainable Carbon-Aware and Water-Efficient LLM Scheduling in Geo-Distributed Cloud Datacenters
  293. Comparing the Moore-Penrose Pseudoinverse and Gradient Descent for Solving Linear Regression Problems: A Performance Analysis
  294. Translation in the Wild
  295. Going from a Representative Agent to Counterfactuals in Combinatorial Choice
  296. Position Paper: Metadata Enrichment Model: Integrating Neural Networks and Semantic Knowledge Graphs for Cultural Heritage Applications
  297. Large SVARs
  298. CLaC at SemEval-2025 Task 6: A Multi-Architecture Approach for Corporate Environmental Promise Verification
  299. Domain-Aware Tensor Network Structure Search
  300. Synchronizing Process Model and Event Abstraction for Grounded Process Intelligence (Extended Version)
  301. Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
  302. Comparative assessment of fairness definitions and bias mitigation strategies in machine learning-based diagnosis of Alzheimer's disease from MR images
  303. Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization
  304. CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization
  305. Efficient AllReduce with Stragglers
  306. OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data
  307. AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity
  308. Individual differences in the cognitive mechanisms of planning strategy discovery
  309. DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
  310. Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds
  311. A Robot-Assisted Approach to Small Talk Training for Adults with ASD
  312. Position: Epistemic uncertainty estimation methods are fundamentally incomplete
  313. VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
  314. Can Large Language Models Challenge CNNs in Medical Image Analysis?
  315. Identity resolution of software metadata using Large Language Models
  316. Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
  317. Spoken Language Modeling with Duration-Penalized Self-Supervised Units
  318. R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
  319. SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training
  320. Autoformalization in the Era of Large Language Models: A Survey
  321. VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation
  322. PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views
  323. Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons
  324. TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
  325. Refining Labeling Functions with Limited Labeled Data
  326. A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimization
  327. Semantics-Aware Human Motion Generation from Audio Instructions
  328. Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss
  329. UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions
  330. LCB-CV-UNet: Enhanced Detector for High Dynamic Range Radar Signals
  331. A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation
  332. Network Inversion for Uncertainty-Aware Out-of-Distribution Detection
  333. The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation
  334. Strategic Classification with Non-Linear Classifiers
  335. Rethinking Regularization Methods for Knowledge Graph Completion
  336. VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration
  337. Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
  338. Bounded-Abstention Pairwise Learning to Rank
  339. UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors
  340. A Mathematical Framework for AI-Human Integration in Work
  341. Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
  342. On the Validity of Head Motion Patterns as Generalisable Depression Biomarkers
  343. OTPTO: Joint Product Selection and Inventory Optimization in Fresh E-commerce Front-End Warehouses
  344. The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence
  345. SWE-bench Goes Live!
  346. Toward Effective AI Governance: A Review of Principles
  347. Bidirectional predictive coding
  348. Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
  349. From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
  350. Video Editing for Audio-Visual Dubbing
  351. Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation
  352. A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy
  353. Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
  354. Robust and Annotation-Free Wound Segmentation on Noisy Real-World Pressure Ulcer Images: Towards Automated DESIGN-Rtextsuperscripttextregistered Assessment
  355. Dynamic Estimation Loss Control in Variational Quantum Sensing via Online Conformal Inference
  356. VModA: An Effective Framework for Adaptive NSFW Image Moderation
  357. Automated Modeling Method for Pathloss Model Discovery
  358. Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models
  359. Dynamic Spectral Backpropagation for Efficient Neural Network Training
  360. PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening
  361. MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification
  362. Representing local protein environments with machine learning force fields
  363. Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis
  364. Sentinel: Scheduling Live Streams with Proactive Anomaly Detection in Crowdsourced Cloud-Edge Platforms
  365. Graph Positional Autoencoders as Self-supervised Learners
  366. A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
  367. Dual-stream attention-guided learning for weakly supervised whole slide image classification
  368. Nosey: Open-source hardware for acoustic nasalance
  369. Matryoshka Model Learning for Improved Elastic Student Models
  370. X2Graph for Cancer Subtyping Prediction on Biological Tabular Data
  371. Fine-Tuning Next-Scale Visual Autoregressive Models with Group Relative Policy Optimization
  372. Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
  373. Efficient Parameter Estimation for Bayesian Network Classifiers using Hierarchical Linear Smoothing
  374. CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection
  375. Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments
  376. Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition
  377. Spoken question answering for visual queries
  378. Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
  379. Quality assessment of 3D human animation: Subjective and objective evaluation
  380. EmoBench-UA: A Benchmark Dataset for Emotion Detection in Ukrainian
  381. How Does Response Length Affect Long-Form Factuality
  382. Federated Unsupervised Semantic Segmentation
  383. ScEdit: Script-based Assessment of Knowledge Editing
  384. Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation
  385. GenCAD-Self-Repairing: Feasibility Enhancement for 3D CAD Generation
  386. Comparative Analysis of the Land Use and Land Cover Changes in Different Governorates of Oman using Spatiotemporal Multi-spectral Satellite Data
  387. Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
  388. The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text
  389. Are MLMs Trapped in the Visual Room?
  390. Unsupervised Transcript-assisted Video Summarization and Highlight Detection
  391. Stable Thompson Sampling: Valid Inference via Variance Inflation
  392. UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes
  393. Automatic Construction of Multiple Classification Dimensions for Managing Approaches in Scientific Papers
  394. Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
  395. Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
  396. How to Evaluate Participant Contributions in Decentralized Federated Learning
  397. Joint estimation of smooth graph signals from partial linear measurements
  398. MCTSr-Zero: Self-Reflective Psychological Counseling Dialogues Generation via Principles and Adaptive Exploration
  399. Graph Random Walk with Feature-Label Space Alignment: A Multi-Label Feature Selection Method
  400. Generalizability vs. Counterfactual Explainability Trade-Off
  401. Daunce: Data Attribution through Uncertainty Estimation
  402. A Jump-Diffusion Framework for Irregular Time Series Generation
  403. Navigating the Accuracy-Size Trade-Off with Flexible Model Merging
  404. Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
  405. HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers
  406. WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems
  407. Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric
  408. JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows
  409. Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
  410. Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
  411. Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images
  412. Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks
  413. ExpeTrans: LLMs Are Experiential Transfer Learners
  414. DeepRTE: Pre-trained Attention-based Neural Network for Radiative Transfer
  415. TrackVLA: Embodied Visual Tracking in the Wild
  416. Improving the Effective Receptive Field of Message-Passing Neural Networks
  417. Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement
  418. FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
  419. FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
  420. Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging
  421. DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
  422. The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
  423. Map&Make: Schema Guided Text to Table Generation
  424. Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
  425. ZIPA: A family of efficient models for multilingual phone recognition
  426. Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes
  427. Best Arm Identification with Possibly Biased Offline Data
  428. Implicit Inversion turns CLIP into a Decoder
  429. Topological Adaptive Least Mean Squares Algorithms over Simplicial Complexes
  430. LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
  431. PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
  432. Conceptual Framework Toward Embodied Collective Adaptive Intelligence
  433. Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
  434. Cross-Domain Bilingual Lexicon Induction via Pretrained Language Models
  435. Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning
  436. Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring
  437. VERINA: Benchmarking Verifiable Code Generation
  438. Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
  439. Patient Domain Supervised Contrastive Learning for Lung Sound Classification Using Mobile Phone
  440. DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
  441. Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
  442. MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
  443. Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking
  444. CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables
  445. Identification of Patterns of Cognitive Impairment for Early Detection of Dementia
  446. Generating Diverse Training Samples for Relation Extraction with Large Language Models
  447. EAD: An EEG Adapter for Automated Classification
  448. Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery
  449. LUMION: Fast Fault Recovery for ML Jobs Using Programmable Optical Fabrics
  450. CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing
  451. Weight Spectra Induced Efficient Model Adaptation
  452. MAP: Revisiting Weight Decomposition for Low-Rank Adaptation
  453. LeMoRe: Learn More Details for Lightweight Semantic Segmentation
  454. Equivariant Spherical Transformer for Efficient Molecular Modeling
  455. Gradient Boosting Decision Tree with LSTM for Investment Prediction
  456. Gradient Methods with Online Scaling Part I. Theoretical Foundations
  457. Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
  458. Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
  459. Second Opinion Matters: Towards Adaptive Clinical AI via the Consensus of Expert Model Ensemble
  460. Rethinking Multi-Modal Learning from Gradient Uncertainty
  461. URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration
  462. Efficient Quantum Approximate kNN Algorithm via Granular-Ball Computing
  463. Machine Learning Framework for Characterizing Processing-Structure Relationship in Block Copolymer Thin Films
  464. Loss-Guided Model Sharing and Local Learning Correction in Decentralized Federated Learning for Crop Disease Classification
  465. DINGO: Constrained Inference for Diffusion LLMs
  466. Self-Correcting Code Generation Using Small Language Models
  467. Be.FM: Open Foundation Models for Human Behavior
  468. Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
  469. Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object
  470. Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders
  471. DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration
  472. Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
  473. Multi-Sourced Compositional Generalization in Visual Question Answering
  474. SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images
  475. From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data
  476. Deep Modeling and Optimization of Medical Image Classification
  477. TailorSQL: An NL2SQL System Tailored to Your Query Workload
  478. EL4NER: Ensemble Learning for Named Entity Recognition via Multiple Small-Parameter Large Language Models
  479. Improving Multilingual Social Media Insights: Aspect-based Comment Analysis
  480. Machine-Facing English: Defining a Hybrid Register Shaped by Human-AI Discourse
  481. Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
  482. Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions
  483. Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset
  484. Uncovering Visual-Semantic Psycholinguistic Properties from the Distributional Structure of Text Embedding Space
  485. Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
  486. Context-Robust Knowledge Editing for Language Models
  487. K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
  488. Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
  489. Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
  490. SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language Model
  491. EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge
  492. Synthetic Document Question Answering in Hungarian
  493. Deep Copula Classifier: Theory, Consistency, and Empirical Evaluation
  494. Walking the Weight Manifold: a Topological Approach to Conditioning Inspired by Neuromodulation
  495. Verify-in-the-Graph: Entity Disambiguation Enhancement for Complex Claim Verification with Interactive Graph Representation
  496. Number of Clusters in a Dataset: A Regularized K-means Approach
  497. MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design
  498. Model-Preserving Adaptive Rounding
  499. Strategic Reflectivism In Intelligent Systems
  500. A Computational Approach to Improving Fairness in K-means Clustering
  501. Pose-free 3D Gaussian splatting via shape-ray estimation
  502. iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures
  503. Exploring Scaling Laws for EHR Foundation Models
  504. Agile Orchestration at Will: An Entire Smart Service-Based Security Architecture Towards 6G
  505. ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
  506. LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments
  507. Directed Graph Grammars for Sequence-based Learning
  508. Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages