mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 14 Oct 2025

415 papers

  1. Refine Thought: A Test-Time Inference Method for Embedding Model ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  2. DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving ScenesEnd-to-end autonomous driving → Generative simulation for driving
  3. MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  4. Aligning Language Models with Investor and Market Behavior for Financial RecommendationsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  5. Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud EnvironmentsKnowledge distillation → Knowledge distillation for LLMs
  6. Can GRPO Help LLMs Transcend Their Pretraining Origin?LLM reasoning → Reinforcement learning for reasoning
  7. Interpreting the Latent Structure of Operator Precedence in Language ModelsLLM reasoning → Mathematical reasoning
  8. Schema for In-Context LearningLLM reasoning → Reasoning benchmarks and evaluation
  9. Benefits and Limitations of Communication in Multi-Agent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  10. RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMsLLM safety and security → Jailbreaking
  11. Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak DetectionLLM safety and security → Jailbreaking
  12. K-frames: Scene-Driven Any-k Keyframe Selection for long video understandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  13. Reliable Fine-Grained Evaluation of Natural Language Math ProofsLLM reasoning → Mathematical reasoning
  14. ECG-Mamba-V2: Architectural Refinements to a Bidirectional State Space Model for Multi-Label 12-Lead ECG ClassificationState-space sequence models (S4, Mamba) → Physiological signal modeling
  15. Repairing Reward Functions with Feedback to Mitigate Reward HackingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  16. Toward Reasoning-Centric Time-Series AnalysisLLM reasoning → Time series reasoning
  17. On the Role of Preference Variance in Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. Escaping Local Optima in the Waddington Landscape: A Two-Stage TRPO-PPO Approach for Single-Cell Perturbation AnalysisDeep reinforcement learning methods → RL for energy, networks and operations
  19. From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language ModelLLM reasoning → Chain-of-thought reasoning for driving
  20. Max It or Miss It: Benchmarking LLM On Solving Extremal ProblemsLLM reasoning → Mathematical reasoning
  21. Tailored untruths: How personalisation challenges LLM safeguardsLLM safety and security → Safety alignment, refusal and guardrails
  22. UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  23. SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied AgentsLLM agents and tool use → Agent threats, guardrails and governance
  24. Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality CheckLLM safety and security → Vision-language and text-to-image safety
  25. DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage ShapingLLM reasoning → Reinforcement learning for reasoning +1
  26. A Connection Between Score Matching and Local Intrinsic DimensionDiffusion models → Diffusion foundations and sampling
  27. Scope: Selective Cross-modal Orchestration of Visual Perception ExpertsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  28. 3-Model Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  29. CADE 2.5 - ZeResFDG: Frequency-Decoupled, Rescaled and Zero-Projected Guidance for SD/SDXL Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  30. Epistemic-aware Vision-Language Foundation Model for Fetal Ultrasound InterpretationMultimodal LLMs / vision-language models → Medical vision-language models
  31. SpareCodeSearch: Searching for Code Context When You Have No Spare GPURetrieval-augmented generation → RAG for code
  32. Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  33. Unifying Vision-Language Latents for Zero-label Image Caption EnhancementMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  34. Toward LLM-Supported Automated Assessment of Critical Thinking SubskillsLLM reasoning → Reasoning benchmarks and evaluation
  35. EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue CorpusKnowledge distillation → Knowledge distillation for LLMs
  36. KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent SystemsLLM agents and tool use → Software engineering coding agents +1
  37. From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. Efficient Adaptive Transformer: An Empirical Study and Reproducible FrameworkEfficient LLM inference and serving → Early exit and edge inference
  39. VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource LanguagesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  40. DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web SearchMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  41. DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous DrivingWorld models → World models for autonomous driving +2
  42. ViCO: A Training Strategy towards Semantic Aware Dynamic High-ResolutionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  43. UniFusion: Vision-Language Model as Unified Encoder in Image GenerationMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  44. Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum PhysicsLLM reasoning → Mathematical reasoning +1
  45. MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D AvatarsDiffusion models → 3D, point cloud and scene generation
  46. SRUM: Fine-Grained Self-Rewarding for Unified Multimodal ModelsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  47. VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural HeritageMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  48. FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  49. Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model SweepsMixture-of-experts → MoE theory and gating functions
  50. Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  51. Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and ReasoningLLM reasoning → Multimodal reasoning +1
  52. Reflection-Based Task Adaptation for Self-Improving VLAVision-language-action models → Reinforcement learning and post-training
  53. Multi-Agent Debate for LLM Judges with Adaptive Stability DetectionLLM reasoning → Reasoning for agents, planning and code +1
  54. ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  55. DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation MaximizationDiffusion models → Inverse problems and image restoration
  56. Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?LLM reasoning → Test-time compute and efficient thinking
  57. Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer AnswersLLM safety and security → Safety alignment, refusal and guardrails
  58. Understanding Parametric Knowledge Injection in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  59. Reasoning Pattern Matters: Learning to Reason without Human RationalesLLM reasoning → Reinforcement learning for reasoning
  60. Expert or not? assessing data quality in offline reinforcement learningOffline RL and imitation learning from data → Offline RL algorithms
  61. Memory as Action: Autonomous Context Curation for Long-Horizon Agentic TasksLLM agents and tool use → Agent memory systems
  62. A Functional Perspective on Knowledge Distillation in Neural NetworksKnowledge distillation → General knowledge distillation methods
  63. WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask GenerationDiffusion models → Inverse problems and image restoration
  64. Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent SpaceLLM reasoning → Multimodal reasoning
  65. There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingDiffusion models → Diffusion foundations and sampling
  66. LayerSync: Self-aligning Intermediate LayersDiffusion models → Diffusion foundations and sampling
  67. Learning Human Motion with Temporally Conditional MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  68. HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle GamesLLM reasoning → Reasoning benchmarks and evaluation
  69. CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous DrivingWorld models → World models for autonomous driving +3
  70. VISaGE: Understanding Visual Generics and ExceptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  71. Unconditional Human Motion and Shape Generation via Balanced Score-Based DiffusionDiffusion models → Video generation
  72. BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)LLM reasoning → Test-time compute and efficient thinking
  73. Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness GuidanceDiffusion models → Diffusion foundations and sampling
  74. A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot CooperationDeep reinforcement learning methods → Safe and constrained RL
  75. Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  76. Time-Correlated Video Bridge MatchingDiffusion models → Video generation
  77. PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  78. Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized IntersectionsDeep reinforcement learning methods → RL for autonomous driving and traffic
  79. PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing TasksLLM reasoning → Reasoning for agents, planning and code
  80. Low-Field Magnetic Resonance Image Quality Enhancement using a Conditional Flow Matching ModelDiffusion models → Medical imaging and segmentation
  81. Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research AgendaMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  82. A Survey of Vibe Coding with Large Language ModelsLLM agents and tool use → Software engineering coding agents
  83. Improving Generative Behavior Cloning via Self-Guidance and Adaptive ChunkingDiffusion models → Diffusion and flow policies for robotics
  84. Controlling Intent Expressiveness in Robot Motion with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  85. Pretraining in Actor-Critic Reinforcement Learning for LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  86. MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little ExpertsMixture-of-experts → Efficient MoE training and inference systems
  87. Fine-grained Analysis of Brain-LLM Alignment through Input AttributionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  88. Physics-Informed Reinforcement Learning for Large-Scale EV Smart Charging Considering Distribution Network Voltage ConstraintsDeep reinforcement learning methods → RL for energy, networks and operations
  89. Finite-time Convergence Analysis of Actor-Critic with Evolving RewardDeep reinforcement learning methods → RL theory and sample complexity
  90. RAG-Anything: All-in-One RAG FrameworkRetrieval-augmented generation → Multimodal RAG
  91. Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech GenerationLLM safety and security → Safety alignment, refusal and guardrails
  92. Deep SPI: Safe Policy Improvement via World ModelsWorld models → Latent dynamics models and model-based RL +1
  93. Hybrid Gaussian Splatting for Novel Urban View SynthesisDiffusion models → 3D, point cloud and scene generation
  94. An Empirical Study for Representations of Videos in Video Question Answering via MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  95. Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual ProjectorLLM reasoning → Hallucination detection and mitigation +1
  96. Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video RetrievalKnowledge distillation → Multimodal distillation
  97. Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action ModelVision-language-action models → 3D and spatial-aware VLA
  98. SpineBench: Benchmarking Multimodal LLMs for Spinal Pathology AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  99. Reducing Belief Deviation in Reinforcement Learning for Active ReasoningLLM reasoning → Reinforcement learning for reasoning
  100. Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and DevelopmentDiffusion models → Diffusion and flow policies for robotics +1
All 415
  1. PromptLocate: Localizing Prompt Injection AttacksLLM safety and security → Prompt injection and agent security
  2. A Gradient Guided Diffusion Framework for Chance Constrained ProgrammingDiffusion models → Diffusion foundations and sampling
  3. Analysing Moral Bias in Finetuned LLMs through Mechanistic InterpretabilityMechanistic interpretability → Probing deception, bias and beliefs
  4. HoneyBee: Data Recipes for Vision-Language ReasonersLLM reasoning → Multimodal reasoning +1
  5. Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion TrajectoryDiffusion models → Diffusion foundations and sampling
  6. GOAT: A Training Framework for Goal-Oriented Agent with ToolsLLM reasoning → Reasoning for agents, planning and code +1
  7. HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance
  8. DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research AgentsLLM agents and tool use → Web, search, and research agents
  10. Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam VideosLLM reasoning → Chain-of-thought reasoning for driving +1
  11. Not in Sync: Unveiling Temporal Bias in Audio Chat ModelsLLM reasoning → Audio-language model reasoning
  12. CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMsLLM reasoning → Multimodal reasoning +2
  13. Learning Mean-Field Games through Mean-Field Actor-Critic FlowDeep reinforcement learning methods → RL for games and combinatorial optimization
  14. Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley SynthesisDiffusion models → Audio, speech and music
  15. MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials ScienceLLM reasoning → Clinical and biomedical applications
  16. Towards Inference-time Scaling for Continuous Space ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  17. A Survey on Parallel ReasoningLLM reasoning → Test-time compute and efficient thinking
  18. Self-Verifying Reflection Helps Transformers with CoT ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  19. Probabilistic Super-Resolution for Urban Micrometeorology via a Schr"odinger BridgeDiffusion models → Diffusion foundations and sampling
  20. SafeMT: Multi-turn Safety for Multimodal Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  21. Towards Engineering Multi-Agent LLMs: A Protocol-Driven ApproachLLM agents and tool use → Software engineering coding agents
  22. ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image GenerationLLM safety and security → Watermarking generated content and models
  23. Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face RestorationDiffusion models → Inverse problems and image restoration
  24. G4Splat: Geometry-Guided Gaussian Splatting with Generative PriorDiffusion models → 3D, point cloud and scene generation
  25. Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  26. Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward FeedbackDiffusion models → Audio, speech and music
  27. One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided ExplorationWorld models → World models for language agents
  28. HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from TrajectoryLLM reasoning → Spatial and embodied reasoning
  29. ThinkPilot: Steering Reasoning Models via Automated Think-prefixes OptimizationLLM reasoning → Test-time compute and efficient thinking
  30. Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire ResponseLLM reasoning → Spatial and embodied reasoning +1
  31. APCE: Adaptive Progressive Context Expansion for Long Context ProcessingEfficient LLM inference and serving → KV cache optimization
  32. Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  33. Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature LearningState-space sequence models (S4, Mamba) → Core SSM architectures for language
  34. Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation
  35. Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant
  36. MOTION: ML-Assisted On-Device Low-Latency Motion Recognition
  37. StrikeWatch: Wrist-worn Gait Recognition with Compact Time-series Models on Low-power FPGAs
  38. Cardi-GPT: An Expert ECG-Record Processing Chatbot
  39. RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics
  40. Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis
  41. Data for Inclusion: The Redistributive Power of Data Economics
  42. Convolutional Attention in Betting Exchange Markets
  43. Layer-Aware Influence for Online Data Valuation Estimation
  44. Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers
  45. PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction
  46. An Order-Sensitive Conflict Measure for Random Permutation Sets
  47. AMStraMGRAM: Adaptive Multi-cutoff Strategy Modification for ANaGRAM
  48. Using Kolmogorov-Smirnov Distance for Measuring Distribution Shift in Machine Learning
  49. The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents
  50. CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection
  51. LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
  52. Switchboard-Affect: Emotion Perception Labels from Conversational Speech
  53. Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory
  54. Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
  55. Post-surgical Endometriosis Segmentation in Laparoscopic Videos
  56. Attribution Quality in AI-Generated Content:Benchmarking Style Embeddings and LLM Judges
  57. Dual-attention ResNet outperforms transformers in HER2 prediction on DCE-MRI
  58. GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents
  59. Bayes or Heisenberg: Who(se) Rules?
  60. The Harder The Better: Maintaining Supervised Fine-tuning Generalization with Less but Harder Data
  61. A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness
  62. MultiFoodhat: A potential new paradigm for intelligent food quality inspection
  63. Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion
  64. Physics-Informed autoencoder for DSC-MRI Perfusion post-processing: application to glioma grading
  65. Order from Chaos: Comparative Study of Ten Leading LLMs on Unstructured Data Categorization
  66. Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation
  67. SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion
  68. SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models
  69. Randomness and Interpolation Improve Gradient Descent
  70. Conformal Inference for Open-Set and Imbalanced Classification
  71. Bridging Idealized and Operational Models: An Explainable AI Framework for Earth System Emulators
  72. Information Shapes Koopman Representation
  73. Machine Learning-Based Ultrasonic Weld Characterization Using Hierarchical Wave Modeling and Diffusion-Driven Distribution Alignment
  74. SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding
  75. Deliberate Lab: A Platform for Real-Time Human-AI Social Experiments
  76. Developing and Validating the Arabic Version of the Attitudes Toward Large Language Models Scale
  77. CurLL: A Developmental Framework to Evaluate Continual Learning in Language Models
  78. What is Implementation Science; and Why It Matters for Bridging the Artificial Intelligence Innovation-to-Application Gap in Medical Imaging
  79. OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning
  80. CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing
  81. Deep Learning-Based Visual Fatigue Detection Using Eye Gaze Patterns in VR
  82. Behavioral Biometrics for Automatic Detection of User Familiarity in VR
  83. Simplicial Gaussian Models: Representation and Inference
  84. Balancing Performance and Reject Inclusion: A Novel Confident Inlier Extrapolation Framework for Credit Scoring
  85. Simulation-Based Pretraining and Domain Adaptation for Astronomical Time Series with Minimal Labeled Data
  86. Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
  87. An Investigation of Memorization Risk in Healthcare Foundation Models
  88. HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants
  89. The Curious Case of Curiosity across Human Cultures and LLMs
  90. Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
  91. FedGTEA: Federated Class-Incremental Learning with Gaussian Task Embedding and Alignment
  92. Who's Asking? Evaluating LLM Robustness to Inquiry Personas in Factual Question Answering
  93. InferA: A Smart Assistant for Cosmological Ensemble Data
  94. Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
  95. Robust Plant Disease Diagnosis with Few Target-Domain Samples
  96. State-Change Learning for Prediction of Future Events in Endoscopic Videos
  97. SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
  98. Learning to Grasp Anything by Playing with Random Toys
  99. Three Lenses on the AI Revolution: Risk, Transformation, Continuity
  100. A Critical Review of the Need for Knowledge-Centric Evaluation of Quranic Recitation
  101. Adaptive Generation of Bias-Eliciting Questions for LLMs
  102. Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering
  103. Ethic-BERT: An Enhanced Deep Learning Model for Ethical and Non-Ethical Content Classification
  104. Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS
  105. Detect Anything via Next Point Prediction
  106. CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
  107. Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
  108. Cost Analysis of Human-corrected Transcription for Predominately Oral Languages
  109. Content Anonymization for Privacy in Long-form Audio
  110. Wavefront Coding for Accommodation-Invariant Near-Eye Displays
  111. What If : Understanding Motion Through Sparse Interactions
  112. Dr.LLM: Dynamic Layer Routing in LLMs
  113. Sample-Efficient Omniprediction for Proper Losses
  114. Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction
  115. Language Models Model Language
  116. Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
  117. AnyUp: Universal Feature Upsampling
  118. Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective
  119. PET Head Motion Estimation Using Supervised Deep Learning with Attention
  120. E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
  121. KoALA: KL-L0 Adversarial Detector via Label Agreement
  122. SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
  123. CTRL-Rec: Controlling Recommender Systems With Natural Language
  124. Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
  125. Hey, wait a minute: on at-issue sensitivity in Language Models
  126. Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect
  127. HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictions
  128. Clutch Control: An Attention-based Combinatorial Bandit for Efficient Mutation in JavaScript Engine Fuzzing
  129. Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior
  130. Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems
  131. Improving Decision Trees through the Lens of Parameterized Local Search
  132. Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages
  133. CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression
  134. Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
  135. Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
  136. Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies
  137. Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
  138. SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
  139. Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
  140. CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
  141. Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?
  142. Topological Signatures of ReLU Neural Network Activation Patterns
  143. Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
  144. Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition
  145. From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
  146. EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
  147. Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
  148. CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
  149. MCOP: Multi-UAV Collaborative Occupancy Prediction
  150. TerraCodec: Compressing Optical Earth Observation Data
  151. Structure-Aware Spectral Sparsification via Uniform Edge Sampling
  152. Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
  153. On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
  154. SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
  155. Towards Foundation Inference Models that Learn ODEs In-Context
  156. Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency
  157. Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis
  158. On Foundation Models for Temporal Point Processes to Accelerate Scientific Discovery
  159. Thermodynamic structure of the Sinkhorn flow
  160. COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
  161. Adapting Noise to Data: Generative Flows from 1D Processes
  162. Laminar: A Scalable Asynchronous RL Post-Training Framework
  163. Designing Tools with Control Confidence
  164. Learning-To-Measure: In-Context Active Feature Acquisition
  165. ACADATA: Parallel Dataset of Academic Data for Machine Translation
  166. Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Models
  167. Same model, better performance: the impact of shuffling on DNA Language Models benchmarking
  168. StyleDecipher: Robust and Explainable Detection of LLM-Generated Texts with Stylistic Analysis
  169. COINS: SemantiC Ids Enhanced COLd Item RepresentatioN for Click-through Rate Prediction in E-commerce Search
  170. Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
  171. Teaching Language Models to Faithfully Express their Uncertainty
  172. Unlocking Zero-Shot Plant Segmentation with Pl@ntNet Intelligence
  173. MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking
  174. Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings
  175. Universal Adaptive Environment Discovery
  176. Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
  177. ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
  178. Voronoi-Assisted Optimization for Diffusing Unsigned Distance Fields from Unoriented Points
  179. Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
  180. Why the noise model matters: A performance gap in learned regularization
  181. The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
  182. Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation
  183. PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
  184. BSGS: Bi-stage 3D Gaussian Splatting for Camera Motion Deblurring
  185. Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews
  186. CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling
  187. Diff-XYZ: A Benchmark for Evaluating Diff Understanding
  188. Fast Visuomotor Policy for Robotic Manipulation
  189. A Text-Image Fusion Method with Data Augmentation Capabilities for Referring Medical Image Segmentation
  190. When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
  191. SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
  192. MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
  193. Community size rather than grammatical complexity better predicts Large Language Model accuracy in a novel Wug Test
  194. Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
  195. A Function-Centric Perspective on Flat and Sharp Minima
  196. Bayesian Optimization for Dynamic Pricing and Learning
  197. A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation
  198. Formal Models and Convergence Analysis for Context-Aware Security Verification
  199. Neural Guided Sampling for Quantum Circuit Optimization
  200. Tensor Completion via Monotone Inclusion: Generalized Low-Rank Priors Meet Deep Denoisers
  201. MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamics
  202. VideoLucy: Deep Memory Backtracking for Long Video Understanding
  203. Geopolitics, Geoeconomics, and Sovereign Risk: Different Shocks, Different Channels
  204. Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystals
  205. Robot Learning: A Tutorial
  206. Cautious Weight Decay
  207. Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs
  208. Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
  209. Scene Coordinate Reconstruction Priors
  210. Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling
  211. Phenome-Wide Multi-Omics Integration Uncovers Distinct Archetypes of Human Aging
  212. Towards Cross-Modal Error Detection with Tables and Images
  213. LiteVPNet: A Lightweight Network for Video Encoding Control in Quality-Critical Applications
  214. Deep Attention-guided Adaptive Subsampling
  215. Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation
  216. Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
  217. LLM-REVal: Can We Trust LLM Reviewers Yet?
  218. (R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm
  219. CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
  220. O-Forge: An LLM + Computer Algebra Framework for Asymptotic Analysis
  221. Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models
  222. Sliding-Window Signatures for Time Series: Application to Electricity Demand Forecasting
  223. Leveraging Teleconnections with Physics-Informed Graph Attention Networks for Long-Range Extreme Rainfall Forecasting in Thailand
  224. Simple Projection Variants Improve ColBERT Performance
  225. Causal Inspired Multi Modal Recommendation
  226. Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
  227. DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
  228. A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction
  229. General Fourier Feature Physics-Informed Extreme Learning Machine (GFF-PIELM) for High-Frequency PDEs
  230. Chinese ModernBERT with Whole-Word Masking
  231. PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
  232. Quantum Annealing for Staff Scheduling in Educational Environments
  233. TFGA-Net: Temporal-Frequency Graph Attention Network for Brain-Controlled Speaker Extraction
  234. Multi-Action Self-Improvement for Neural Combinatorial Optimization
  235. Heterogeneous RBCs via Deep Multi-Agent Reinforcement Learning
  236. The Living Forecast: Evolving Day-Ahead Predictions into Intraday Reality
  237. Tensor Logic: The Language of AI
  238. HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
  239. Human-in-the-Loop Bandwidth Estimation for Quality of Experience Optimization in Real-Time Video Communication
  240. AngularFuse: A Closer Look at Angle-based Perception for Spatial-Sensitive Multi-Modality Image Fusion
  241. Local Background Features Matter in Out-of-Distribution Detection
  242. Multiplicative Loss for Enhancing Semantic Segmentation in Medical and Cellular Images
  243. Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding
  244. Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
  245. FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning
  246. DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
  247. Optimal Regularization for Performative Learning
  248. PromptFlow: Training Prompts Like Neural Networks
  249. MoRA: On-the-fly Molecule-aware Low-Rank Adaptation Framework for LLM-based Multi-Modal Molecular Assistant
  250. Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection
  251. Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
  252. BIGFix: Bidirectional Image Generation with Token Fixing
  253. MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
  254. DIANet: A Phase-Aware Dual-Stream Network for Micro-Expression Recognition via Dynamic Images
  255. HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment
  256. DE3S: Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classification
  257. DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
  258. Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
  259. The Impact of Synthetic Data on Object Detection Model Performance: A Comparative Analysis with Real-World Data
  260. Controllable Collision Scenario Generation via Collision Pattern Prediction
  261. On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy
  262. BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
  263. From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
  264. Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
  265. UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
  266. State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
  267. DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation
  268. Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
  269. Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
  270. Budget-constrained Active Learning to Effectively De-censor Survival Data
  271. Fairness-Constrained Optimization Attack in Federated Learning
  272. MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations
  273. Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
  274. Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
  275. FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
  276. nuGPR: GPU-Accelerated Gaussian Process Regression with Iterative Algorithms and Low-Rank Approximations
  277. MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites
  278. Hardware-aware Coding Function Design for Compressive Single-Photon 3D Cameras
  279. Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
  280. Locket: Robust Feature-Locking Technique for Language Models
  281. Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
  282. Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
  283. Chimera: State Space Models Beyond Sequences
  284. Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models
  285. DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
  286. Gaussian Semantic Field for One-shot LiDAR Global Localization
  287. An Adaptive Edge-Guided Dual-Network Framework for Fast QR Code Motion Deblurring
  288. IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation
  289. H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space
  290. ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations
  291. GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs
  292. An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations
  293. Enhancing Neural Code Representation with Additional Context
  294. Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models
  295. FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
  296. Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
  297. BeSTAD: Behavior-Aware Spatio-Temporal Anomaly Detection for Human Mobility Data
  298. A Review on Domain Adaption and Generative Adversarial Networks(GANs)
  299. EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
  300. Influence Dynamics and Stagewise Data Attribution
  301. MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging
  302. VIDMP3: Video Editing by Representing Motion with Pose and Position Priors
  303. AI Agents as Universal Task Solvers
  304. Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
  305. APGNet: Adaptive Prior-Guided for Underwater Camouflaged Object Detection
  306. MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation
  307. Generative AI and Sales Productivity: Field Experiments in Online Retail
  308. ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
  309. POET: Preference Optimization for Enhanced Text-to-Image Generation
  310. Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
  311. On the Interplay between Human Label Variation and Model Fairness
  312. CausalTrace: A Neurosymbolic Causal Analysis Agent for Smart Manufacturing
  313. Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models
  314. CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
  315. Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM