mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 2 Feb 2026

699 papers

  1. Learn2Fold: Structured Origami Generation with World Model PlanningWorld models → Embodied and robot world models
  2. vLLM Hook v0: A Plug-in for Programming Model Internals on vLLMLLM safety and security → Safety alignment, refusal and guardrails +1
  3. CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +2
  4. IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal TraditionsLLM reasoning → Reasoning for agents, planning and code
  5. Make Every Draft Count: Hidden State based Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  6. DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource ContentionLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. "Humans welcome to observe": A First Look at the Agent Social Network MoltbookLLM agents and tool use → Social simulation and multi-agent debate
  8. Neural Sabermetrics with World Model: Play-by-play Predictive Modeling with Large Language ModelWorld models → World models for language agents
  9. Fair Context Learning for Evidence-Balanced Test-Time Adaptation in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  10. Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. The Geometry of Representational Failures in Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market SimulationLLM agents and tool use → Financial trading and forecasting agents
  13. Condition Errors Refinement in Autoregressive Image Generation with Diffusion LossDiffusion models → Diffusion foundations and sampling
  14. DiGAN: Diffusion-Guided Attention Network for Early Alzheimer's Disease DetectionDiffusion models → Medical imaging and segmentation
  15. Training-Free Self-Correction for Multimodal Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
  16. How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?Diffusion models → Diffusion and flow policies for robotics +1
  17. A Multi-scale Linear-time Encoder for Whole-Slide Image AnalysisState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  18. Notes on the Reward Representation of Posterior UpdatesDeep reinforcement learning methods → Deep RL algorithms and representations
  19. Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMsLLM reasoning → Test-time compute and efficient thinking
  20. A Random Matrix Theory Perspective on the Consistency of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  21. FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific InsightsLLM agents and tool use → Web, search, and research agents
  22. Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  23. Aligning Language Model Benchmarks with Pairwise PreferencesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  24. Learning-Infused Formal Reasoning: From Contract Synthesis to Artifact Reuse and Formal SemanticsLLM reasoning → Reasoning benchmarks and evaluation
  25. ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual QueryingLLM reasoning → Multimodal reasoning +1
  26. Accelerating Structured Chain-of-Thought in Autonomous VehiclesLLM reasoning → Chain-of-thought reasoning for driving +1
  27. "I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference TimeLLM reasoning → Test-time compute and efficient thinking
  28. Causal Flow Q-Learning for Robust Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  29. Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem RoutingLLM reasoning → Prompting and chain-of-thought reasoning
  30. Adaptive Linear Path Model-Based DiffusionDiffusion models → Diffusion and flow policies for robotics
  31. A Single Revision Step Improves Token-Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  32. CALIBURN: Self-Calibrated LLM Unlearning AlignmentLLM safety and security → Machine unlearning
  33. R2-Router: A New Paradigm for LLM Routing with ReasoningLLM reasoning → Test-time compute and efficient thinking
  34. Causal Evaluation of Membership Inference AttacksLLM safety and security → Membership inference attacks
  35. Joint Learning of Hierarchical Neural Options and Abstract World ModelWorld models → Latent dynamics models and model-based RL
  36. Super-Resolution and Denoising of Corneal B-Scan OCT Imaging Using Diffusion Model Plug-and-Play PriorsDiffusion models → Medical imaging and segmentation
  37. Causality--Delta: Jacobian-Based Dependency Analysis in Flow Matching ModelsDiffusion models → Flow matching, time series and science
  38. Scaling-Aware Adapter for Structure-Grounded LLM ReasoningLLM reasoning → Spatial and embodied reasoning
  39. On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  40. From Task Solving to Robust Real-World Adaptation in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Scaling Small Agents Through Strategy AuctionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. Search-Augmented Masked Diffusion Models for Constrained GenerationDiffusion models → Discrete and text diffusion
  43. Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept DiscoveryMechanistic interpretability → SAE features and their applications
  44. Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal DiffusionDeep reinforcement learning methods → Deep RL algorithms and representations
  45. Maximum Likelihood Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  46. ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference EvolutionLLM agents and tool use → Reinforcement learning for LLM agents
  47. Sparsely Supervised DiffusionDiffusion models → Diffusion foundations and sampling
  48. Monotonicity as an Architectural Bias for Robust Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  49. Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  50. AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning ProcessLLM reasoning → Multimodal reasoning +1
  51. MARS: Modular Agent with Reflective Search for Automated AI ResearchLLM agents and tool use → Web, search, and research agents
  52. A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model BehaviorLLM reasoning → Prompting and chain-of-thought reasoning
  53. Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease ManagementLLM reasoning → Clinical and biomedical applications
  54. Learning Better Certified Models from Empirically-Robust TeachersKnowledge distillation → Federated, robust and private distillation
  55. daVinci-Agency: Unlocking Long-Horizon Agency Data-EfficientlyLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent CommunityLLM agents and tool use → Social simulation and multi-agent debate
  57. Gender Dynamics and Homophily in a Social Network of LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  58. Reward-free Alignment for Conflicting ObjectivesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  59. PixelGen: Improving Pixel Diffusion with Perceptual SupervisionDiffusion models → Diffusion foundations and sampling
  60. RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL SystemLLM agents and tool use → Reinforcement learning for LLM agents +1
  61. RE-TRAC: REcursive TRAjectory Compression for Deep Search AgentsLLM agents and tool use → Web, search, and research agents
  62. Expanding the Capabilities of Reinforcement Learning via Text FeedbackDeep reinforcement learning methods → RL training of language and agent models
  63. Flow Policy Gradients for Robot ControlDeep reinforcement learning methods → RL with diffusion and flow models
  64. Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time ScalabilityLLM reasoning → Reinforcement learning for reasoning
  65. AgentRx: Diagnosing AI Agent Failures from Execution TrajectoriesLLM agents and tool use → Software engineering coding agents
  66. MemSkill: Learning and Evolving Memory Skills for Self-Evolving AgentsLLM agents and tool use → Agent memory systems +1
  67. SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive LearningMixture-of-experts → Expert routing strategies
  68. Breaking the Reversal Curse in Autoregressive Language Models via Identity BridgeLLM reasoning → Prompting and chain-of-thought reasoning
  69. Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding ExpertsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  70. MentisOculi: Revealing the Limits of Reasoning with Mental ImageryLLM reasoning → Multimodal reasoning +1
  71. Abstract Activation Spaces for Content-Invariant Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  72. TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic EnvironmentsVision-language-action models → Reasoning and chain-of-thought in VLA
  73. Relationship-Aware Hierarchical 3D Scene Graph for Task ReasoningLLM reasoning → Spatial and embodied reasoning
  74. Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn InteractionLLM agents and tool use → Agent threats, guardrails and governance
  75. World-Gymnast: Training Robots with Reinforcement Learning in a World ModelWorld models → Embodied and robot world models +1
  76. Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual StorytellingLLM reasoning → Multimodal reasoning
  77. Active Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  78. Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoELLM reasoning → Test-time compute and efficient thinking +1
  79. UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and EditingLLM reasoning → Multimodal reasoning
  80. Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  81. ReasonEdit: Editing Vision-Language Models using Human ReasoningLLM reasoning → Multimodal reasoning +1
  82. Making Expert Reasoning Learnable with Self-DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  83. PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation LearningDiffusion models → Diffusion and flow policies for robotics +1
  84. David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement LearningLLM agents and tool use → Agent threats, guardrails and governance +2
  85. Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical MemoryWorld models → Video-generation world models and simulators
  86. SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  87. ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  88. Unified Personalized Reward Model for Vision GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  89. Live-Evo: Online Evolution of Agentic Memory from Continuous FeedbackLLM agents and tool use → Agent memory systems
  90. ReasonCACHE: Teaching LLMs To Reason Without Weight UpdatesLLM reasoning → Reasoning benchmarks and evaluation
  91. Context Learning for Multi-Agent DiscussionLLM agents and tool use → General LLM agent frameworks and benchmarks
  92. A Task-Level Evaluation of AI Agents in Open-Source ProjectsLLM agents and tool use → Software engineering coding agents
  93. LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference OptimizationLLM reasoning → Multimodal reasoning +2
  94. Enhancing Indoor Occupancy Prediction via Sparse Query-Based Multi-Level Consistent Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  95. Interpreting and Controlling LLM Reasoning through Integrated Policy GradientLLM reasoning → Reasoning benchmarks and evaluation
  96. Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  97. Advancing General-Purpose Reasoning Models with Modular Gradient SurgeryLLM reasoning → Reinforcement learning for reasoning
  98. EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  99. DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-WildMixture-of-experts → Multimodal MoE models
  100. Choice-Model-Assisted Q-learning for Delayed-Feedback Revenue ManagementDeep reinforcement learning methods → RL theory and sample complexity
All 699
  1. MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from HistologyMixture-of-experts → Medical and biomedical MoE
  2. RACC: Representation-Aware Coverage Criteria for LLM Safety TestingLLM safety and security → Jailbreaking
  3. Kimi K2.5: Visual Agentic IntelligenceLLM agents and tool use → Multimodal and embodied agents
  4. dziribot: rag based intelligent conversational agent for algerian arabic dialectLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. OmniCode: A Benchmark for Evaluating Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  6. Unlocking the Duality between Flow and Field MatchingDiffusion models → Flow matching, time series and science
  7. Learning Markov Decision Processes under Fully Bandit FeedbackDeep reinforcement learning methods → RL theory and sample complexity
  8. Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL DivergencesDeep reinforcement learning methods → RL theory and sample complexity
  9. Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning +1
  10. Geometry- and Relation-Aware Diffusion for EEG Super-ResolutionDiffusion models → Medical imaging and segmentation
  11. Adaptive Control in Autonomous Driving via Real-Time Recurrent RLEnd-to-end autonomous driving → Reinforcement learning for driving +1
  12. Agent-Based Software Artifact EvaluationLLM agents and tool use → Software engineering coding agents
  13. LiFlow: Flow Matching for 3D LiDAR Scene CompletionDiffusion models → 3D, point cloud and scene generation
  14. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video GenerationDiffusion models → Video generation
  15. MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization
  16. Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case StudyRetrieval-augmented generation → Time series and agricultural RAG
  17. Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  18. Sampling-Free Diffusion Transformers for Low-Complexity MIMO Channel EstimationDiffusion models → Diffusion for compression and wireless
  19. More Than a Quick Glance: Overcoming the Greedy Bias in KV-Cache CompressionEfficient LLM inference and serving → KV cache optimization
  20. Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  21. TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. SSI-DM: Singularity Skipping Inversion of Diffusion ModelsDiffusion models → Inverse problems and image restoration
  23. ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  24. Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial OptimizationLLM reasoning → Mathematical reasoning
  25. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  26. Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  27. Reg4Pru: Regularisation Through Random Token Routing for Token PruningEfficient LLM inference and serving → Token pruning and merging for ViTs
  28. D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool UseLLM reasoning → Reasoning for agents, planning and code
  29. LoopViT: Scaling Visual ARC with Looped TransformersLLM reasoning → Multimodal reasoning
  30. ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  31. Learning Generative Selection for Best-of-NLLM reasoning → Reinforcement learning for reasoning
  32. FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA
  33. EvoMU: Evolutionary Machine UnlearningLLM safety and security → Machine unlearning
  34. CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation SystemsLLM agents and tool use → Software engineering coding agents
  35. Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  36. A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal CurseDiffusion models → Discrete and text diffusion
  37. There Is More to Refusal in Large Language Models than a Single DirectionMechanistic interpretability → Steering and probing for LLM safety
  38. Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein DynamicsDiffusion models → Flow matching, time series and science
  39. Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal TrainingDiffusion models → Diffusion foundations and sampling
  40. Unifying Masked Diffusion Models with Various Generation Orders and BeyondDiffusion models → Discrete and text diffusion
  41. An Empirical Study of World Model QuantizationWorld models → Latent predictive world models
  42. Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token ContextsEfficient LLM inference and serving → KV cache optimization
  43. Teacher-Guided Student Self-Knowledge Distillation Using Diffusion ModelDiffusion models → Diffusion foundations and sampling
  44. How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  45. Probabilistic Performance Guarantees for Multi-Task Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  46. FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent SpaceDiffusion models → Video generation
  47. See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action DesignersLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  48. QVCache: A Query-Aware Vector CacheRetrieval-augmented generation → Vector search and ANN indexes
  49. FORLER: Federated Offline Reinforcement Learning with Q-Ensemble and Actor RectificationOffline RL and imitation learning from data → Offline RL algorithms
  50. WildGraphBench: Benchmarking GraphRAG with Wild-Source CorporaRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  51. SIDiffAgent: Self-Improving Diffusion AgentDiffusion models → Image generation, text-to-image and editing +1
  52. Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model AgentsLLM reasoning → Reasoning for agents, planning and code +1
  53. Are Semantic Networks Associated with Idea Originality in Artificial Creativity? A Comparison with Human AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse ProblemsDiffusion models → Inverse problems and image restoration
  55. Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  56. Hunt Instead of Wait: Evaluating Deep Data Research on Large Language ModelsLLM agents and tool use → Web, search, and research agents
  57. Constrained Process Maps for Multi-Agent Generative AI WorkflowsLLM agents and tool use → Agent threats, guardrails and governance
  58. One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  59. Edge-Aligned Initialization of Kernels for Steered Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
  60. Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background StoriesLLM reasoning → Knowledge- and tool-augmented reasoning
  61. Light Alignment Improves LLM Safety via Model Self-Reflection with a Single NeuronLLM safety and security → Safety alignment, refusal and guardrails
  62. NEAT: Neuron-Based Early Exit for Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  63. Logic-Guided Vector Fields for Constrained Generative ModelingDiffusion models → Flow matching, time series and science
  64. Beyond RAG for Agent Memory: Retrieval by Decoupling and AggregationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  65. ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal ReasoningLLM reasoning → Multimodal reasoning
  66. UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous DrivingWorld models → World models for autonomous driving +1
  67. On the Limits of Layer Pruning for Generative Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  68. Emergent Analogical Reasoning in TransformersLLM reasoning → Reasoning benchmarks and evaluation
  69. Localized Control in Diffusion Models via Latent Vector PredictionDiffusion models → Image generation, text-to-image and editing
  70. SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  71. Stochastic Interpolants in Hilbert SpacesDiffusion models → Diffusion foundations and sampling
  72. Enhancing Multi-Image Understanding through Delimiter Token ScalingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  73. Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  74. S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  75. Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  76. Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  77. Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech RecognitionMixture-of-experts → Multimodal MoE models
  78. Self-Consolidation for Self-Evolving AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  79. Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  80. Grounding Generated Videos in Feasible Plans via World ModelsWorld models → Embodied and robot world models
  81. Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  82. Boundary-Constrained Diffusion Models for Floorplan Generation: Balancing Realism and DiversityDiffusion models → 3D, point cloud and scene generation
  83. Human Society-Inspired Approaches to Agentic AI Security: The 4C FrameworkLLM agents and tool use → Agent threats, guardrails and governance
  84. LiteCoOp: Lightweight Multi-LLM Shared-Tree Reasoning for Model-Serving Compiler OptimizationsLLM reasoning → Reasoning for agents, planning and code +1
  85. When Workout Buddies Are Virtual: AI Agents and Human Peers in a Longitudinal Physical Activity StudyLLM agents and tool use → General LLM agent frameworks and benchmarks
  86. ForSim: Stepwise Forward Simulation for Traffic Policy Fine-TuningOffline RL and imitation learning from data → Imitation and offline RL for driving
  87. VLM-Guided Experience ReplayLLM reasoning → Multimodal reasoning +1
  88. Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMsLLM reasoning → Test-time compute and efficient thinking
  89. Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language ModelMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  90. Path Tracking with Dynamic Control Point Blending for Autonomous Vehicles: An Experimental StudyEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  91. ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional SupportLLM agents and tool use → Agent memory systems
  92. Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward ModelsLLM reasoning → Multimodal reasoning +2
  93. Multimodal Large Language Models for Real-Time Situated ReasoningLLM reasoning → Spatial and embodied reasoning +1
  94. Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  95. Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation ModelingDiffusion models → Inverse problems and image restoration
  96. SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating ProceduresMixture-of-experts → MoE large language models
  97. Designing Time Series Experiments in A/B Testing with Transformer Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  98. FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented OptimizationLLM safety and security → Federated unlearning and poisoning
  99. Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +2
  100. ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  101. Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  102. Concept-Based Dictionary Learning for Inference-Time Safety in Vision Language Action ModelsVision-language-action models → Safety and adversarial attacks
  103. Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and AnomaliesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  104. INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular DiscoveryLLM agents and tool use → Web, search, and research agents
  105. GPD: Guided Progressive Distillation for Fast and High-Quality Video GenerationDiffusion models → Video generation
  106. From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA modelsVision-language-action models → Generalist VLA models and benchmarks
  107. Sentence Curve Language ModelsDiffusion models → Discrete and text diffusion
  108. FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image EditingDiffusion models → Image generation, text-to-image and editing
  109. Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse AttentionWorld models → Video-generation world models and simulators +2
  110. ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routingLLM reasoning → Reasoning for agents, planning and code +1
  111. RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache ReuseLLM reasoning → Reasoning for agents, planning and code +2
  112. Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  113. RFS: Reinforcement Learning with Residual Flow Steering for Dexterous ManipulationDiffusion models → Diffusion and flow policies for robotics +2
  114. Seeing is Coding: On the Effectiveness of Vision Language Models in Code UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  115. DDP-WM: Disentangled Dynamics Prediction for Efficient World ModelsWorld models → Embodied and robot world models
  116. LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  117. Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language ModelEfficient LLM inference and serving → Prompt and context compression
  118. Position: Beyond Model-Centric Prediction -- Agentic Time Series ForecastingLLM agents and tool use → Financial trading and forecasting agents
  119. Efficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response PredictionKnowledge distillation → General knowledge distillation methods
  120. IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal HallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  121. Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise ConsistencyDiffusion models → Robustness, privacy and adversarial aspects +1
  122. PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft ModelsEfficient LLM inference and serving → Speculative decoding
  123. Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual EmbeddingsRetrieval-augmented generation → Privacy and security of RAG
  124. Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image GenerationLLM agents and tool use → Multimodal and embodied agents
  125. WorldCup Sampling for Multi-bit LLM WatermarkingLLM safety and security → Watermarking generated content and models
  126. Adversarial Reward Auditing for Active Detection and Mitigation of Reward HackingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  127. SafePred: A Predictive Guardrail for Computer-Using Agents via World ModelsWorld models → World model security and GUI agents +1
  128. DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo EstimationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  129. COMI: Coarse-to-fine Context Compression via Marginal Information GainEfficient LLM inference and serving → Prompt and context compression
  130. ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative SimulationLLM reasoning → Reasoning for agents, planning and code +1
  131. Game of Thought: Robust Information Seeking with Large Language Models Using Game TheoryLLM reasoning → Reasoning for agents, planning and code
  132. LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking +1
  133. textbfAGTAO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive OrthogonalityLLM safety and security → Machine unlearning
  134. Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  135. Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  136. What LLMs Think When You Don't Tell Them What to Think About?LLM reasoning → Reasoning benchmarks and evaluation
  137. Semantic-aware Wasserstein Policy Regularization for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  138. FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  139. SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  140. TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World ScenariosLLM agents and tool use → General LLM agent frameworks and benchmarks
  141. Adaptive Information Control for Search-Augmented LLM ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  142. ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  143. FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas EditingLLM agents and tool use → Software engineering coding agents
  144. PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot ManipulationLLM reasoning → Spatial and embodied reasoning +2
  145. CoDiQ: Test-Time Scaling for Controllable Difficult Question GenerationLLM reasoning → Reasoning benchmarks and evaluation
  146. Efficient Adversarial Attacks on High-dimensional Offline BanditsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  147. ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project DevelopmentLLM agents and tool use → Software engineering coding agents
  148. Steering Vector Fields for Context-Aware Inference-Time Control in Large Language ModelsMechanistic interpretability → Activation steering methods
  149. Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement LearningEfficient LLM inference and serving → Visual token pruning in multimodal models +1
  150. Membership Inference Attack Against Music Diffusion Models via Generative Manifold PerturbationDiffusion models → Robustness, privacy and adversarial aspects
  151. From Perception to Action: Spatial AI Agents and World ModelsWorld models → World models for language agents +1
  152. A2Eval: Agentic and Automated Evaluation for Embodied BrainLLM agents and tool use → Medical and scientific domain agents
  153. ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  154. Research on World Models Is Not Merely Injecting World Knowledge into Specific TasksWorld models → World models for language agents
  155. PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned RewardsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  156. A Practical Tensor-Network Compression Pipeline for Production-Scale Large Language ModelsEfficient LLM inference and serving → KV cache optimization
  157. What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?LLM agents and tool use → General LLM agent frameworks and benchmarks
  158. Token Pruning for In-Context Generation in Diffusion TransformersDiffusion models → Diffusion foundations and sampling +1
  159. Reasoning with Autoregressive-Diffusion Collaborative ThoughtsDiffusion models → Discrete and text diffusion
  160. Boosting Maximum Entropy Reinforcement Learning via One-Step Flow MatchingDiffusion models → Diffusion and flow policies for robotics +1
  161. Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPOLLM reasoning → Reinforcement learning for reasoning +1
  162. Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMsLLM reasoning → Reasoning for agents, planning and code +1
  163. Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based FrameworkState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  164. Faster and Better Alignment for Flow Matching Models via Step-aware AdvantagesDiffusion models → Diffusion and flow policies for robotics +1
  165. Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia ArticlesLLM agents and tool use → Web, search, and research agents
  166. Provable Defense Framework for LLM Jailbreaks via Noise-Augumented AlignmentLLM safety and security → Jailbreaking
  167. HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  168. Nearly Optimal Active Preference Learning and Its Application to LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  169. Generative Visual Code Mobile World ModelsWorld models → World model security and GUI agents +1
  170. SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  171. One-Step Diffusion for Perceptual Image CompressionDiffusion models → Diffusion for compression and wireless
  172. FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based AgentsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  173. AdNanny: One Reasoning LLM for All Offline Ads Recommendation TasksLLM reasoning → LLM reasoning for recommendation
  174. Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to OddLLM reasoning → Multimodal reasoning
  175. InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMsLLM reasoning → Multimodal reasoning +1
  176. S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific ResearchLLM agents and tool use → Web, search, and research agents +1
  177. Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion RecognitionKnowledge distillation → Multimodal distillation
  178. Toward Cognitive Supersensing in Multimodal Large Language ModelLLM reasoning → Multimodal reasoning +1
  179. MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM SafetyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  180. UniDWM: Towards a Unified Driving World Model via Multifaceted Representation LearningWorld models → World models for autonomous driving +1
  181. Logit Lens Supervision for Patch-Level Explanations in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  182. Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  183. A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  184. When Is Rank-1 Enough? Geometry-Guided Initialization for Parameter-Efficient Fine-TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  185. Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-TrainingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  186. Optimal Sample Complexity for Single Time-Scale Actor-Critic with MomentumDeep reinforcement learning methods → RL theory and sample complexity
  187. SIEVE: Sample-Efficient Parametric Learning from Natural Language
  188. Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing
  189. Semantic Containment as a Fundamental Property of Emergent Misalignment
  190. Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal
  191. Measuring Pragmatic Influence in Large Language Model Instructions
  192. Genetic Generalized Additive Models
  193. Should There be a Teacher In-the-Loop? A Study of Generative AI Personalized Tasks Middle School
  194. Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
  195. P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA
  196. Implicit Bias in LLMs for Transgender Populations
  197. A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning
  198. X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles
  199. Guidestar-Free Adaptive Optics with Asymmetric Apertures
  200. A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures
  201. A Distributed Multi-Modal Sensing Approach for Human Activity Recognition in Real-Time Human-Robot Collaboration
  202. AI for Sustainable Data Protection and Fair Algorithmic Management in Environmental Regulation
  203. Financial Bond Similarity Search Using Representation Learning
  204. HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference
  205. Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
  206. TruKAN: Towards More Efficient Kolmogorov-Arnold Networks Using Truncated Power Functions
  207. Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey
  208. Refining Decision Boundaries In Anomaly Detection Using Similarity Search Within the Feature Space
  209. A Reproducible Framework for Bias-Resistant Machine Learning on Small-Sample Neuroimaging Data
  210. DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
  211. Weighted Temporal Decay Loss for Learning Wearable PPG Data with Sparse Clinical Labels
  212. FaceLinkGen: A Re-evaluation of Identity Leakage in Privacy-Preserving Face Recognition and Face Anonymization Systems Using Simple Distillation
  213. Spatiotemporal Decision Transformer for Traffic Coordination
  214. Minimal Computational Preconditions for Subjective Perspective in Artificial Agents
  215. Decentralized SGD with Controlled Disagreement Finds Flatter Minima
  216. Moving On, Even When You're Broken: Fail-Active Trajectory Generation via Diffusion Policies Conditioned on Embodiment and Task
  217. DoubleTake: Contrastive Reasoning for Faithful Decision-Making in Medical Imaging
  218. TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation
  219. Self-Soupervision: Cooking Model Soups without Labels
  220. HALT: Hallucination Assessment via Log-probs as Time series
  221. Mixture of Concept Bottleneck Experts
  222. Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs
  223. A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
  224. STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search
  225. Late-Stage Generalization Collapse in Grokking: Detecting anti-grokking with Weightwatcher
  226. IMAGINE: Intelligent Multi-Agent Godot-based Indoor Networked Exploration
  227. When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models
  228. Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
  229. Self-Supervised Uncalibrated Multi-View Video Anonymization in the Operating Room
  230. AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents
  231. Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression
  232. Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication
  233. Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains
  234. Beyond Content: Behavioral Policies Reveal Actors in Information Operations
  235. What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA
  236. Invertible continuous latent dynamic for long-term data assimilation in complex physical systems
  237. SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs
  238. When Efficient Communication Explains Convexity
  239. From Tokens to Numbers: Continuous Number Modeling for SVG Generation
  240. Downscaling land surface temperature data using edge detection and block-diagonal Gaussian process regression
  241. LmPT: Conditional Point Transformer for Anatomical Landmark Detection on 3D Point Clouds
  242. Real-time topology-aware M-mode OCT segmentation for robotic deep anterior lamellar keratoplasty (DALK) guidance
  243. Plug-In Classification of Drift Functions in Diffusion Processes Using Neural Networks
  244. Simulating Human Audiovisual Search Behavior
  245. Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
  246. LEMON: Local Explanations via Modality-aware OptimizatioN
  247. Cross-Temporal Attention Fusion (CTAF) for Multimodal Physiological Signals in Self-Supervised Learning
  248. Evaluating False Alarm and Missing Attacks in CAN IDS
  249. Verification and Identification in ECG biometric on large-scale
  250. AmharicStoryQA: A Multicultural Story Question Answering Benchmark in Amharic
  251. BiTimeCrossNet: Time-Aware Self-Supervised Learning for Pediatric Sleep
  252. Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
  253. Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
  254. SVD-ViT: Does SVD Make Vision Transformers Attend More to the Foreground?
  255. Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
  256. Near-Universal Multiplicative Updates for Nonnegative Einsum Factorization
  257. Physics-based generation of multilayer corneal OCT data via Gaussian modeling and MCML for AI-driven diagnostic and surgical guidance applications
  258. Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
  259. TopoPrune: Robust Data Pruning via Unified Latent Space Topology
  260. When Noise Lowers The Loss: Rethinking Likelihood-Based Evaluation in Music Large Language Models
  261. Time-Critical Multimodal Medical Transportation: Organs, Patients, and Medical Supplies
  262. TabPFN for Zero-shot Parametric Engineering Design Generation
  263. WAXAL: A Large-Scale Multilingual African Language Speech Corpus
  264. Predicting first-episode homelessness among US Veterans using longitudinal EHR data: time-varying models and social risk factors
  265. CAPS: Unifying Attention, Recurrence, and Alignment in Transformer-based Time Series Forecasting
  266. Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensing
  267. End-to-end reconstruction of OCT optical properties and speckle-reduced structural intensity via physics-based learning
  268. Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels
  269. Perfusion Imaging and Single Material Reconstruction in Polychromatic Photon Counting CT
  270. Towards Understanding Steering Strength
  271. Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
  272. BinaryPPO: Efficient Policy Optimization for Binary Classification
  273. Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers
  274. InfMem: Learning System-2 Memory Control for Long-Context Agent
  275. NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
  276. Eidolon: A Post-Quantum Signature Scheme Based on k-Colorability in the Age of Graph Neural Networks
  277. FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
  278. MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fields
  279. Benchmarking Large Language Models for Zero-shot and Few-shot Phishing URL Detection
  280. hSNMF: Hybrid Spatially Regularized NMF for Image-Derived Spatial Transcriptomics
  281. WideSeek: Advancing Wide Research via Multi-Agent Scaling
  282. A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees
  283. Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation
  284. Performance of Small Language Model Pretraining on FABRIC: An Empirical Study
  285. Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)
  286. Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Securing Participant Identity with Decentralized Identifiers and Verifiable Credentials
  287. Recommender system in X inadvertently profiles ideological positions of users
  288. Learning Consistent Causal Abstraction Networks
  289. CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
  290. A Semi-Supervised Pipeline for Generalized Behavior Discovery from Animal-Borne Motion Time Series
  291. TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints
  292. Testing Storage-System Correctness: Challenges, Fuzzing Limitations, and AI-Augmented Opportunities
  293. Discovering Data Manifold Geometry through Geometric Properties
  294. Fine-Tuning Language Models to Know What They Know
  295. AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice
  296. EchoJEPA: A Latent Predictive Foundation Model for Echocardiography
  297. MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
  298. New explanations and inference for least angle regression
  299. HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
  300. Multi-head automated segmentation by incorporating detection head into the contextual layer neural network
  301. Age-Aware Edge-Blind Federated Learning via Over-the-Air Aggregation
  302. Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
  303. From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
  304. Conflict-Aware Client Selection for Multi-Server Federated Learning
  305. Finite-Sample Wasserstein Error Bounds and Concentration Inequalities for Nonlinear Stochastic Approximation
  306. RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval
  307. Large Language Models for Mental Health: A Multilingual Evaluation
  308. Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization
  309. Maximizing Reliability with Bayesian Optimization
  310. Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
  311. SelvaMask: Segmenting Trees in Tropical Forests and Beyond
  312. Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization
  313. Poly-attention: a general scheme for higher-order self-attention
  314. SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
  315. Trust Region Continual Learning as an Implicit Meta-Learner
  316. Structure Enables Effective Self-Localization of Errors in LLMs
  317. Active Transfer Bagging: A New Approach for Accelerated Active Learning Acquisition of Data by Combined Transfer Learning and Bagging Based Models
  318. Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank
  319. Masked Autoencoders as Universal Speech Enhancer
  320. Catalyst: Out-of-Distribution Detection via Elastic Scaling
  321. Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
  322. SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
  323. Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation
  324. An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
  325. Personalized Image Generation via Human-in-the-loop Bayesian Optimization
  326. Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing
  327. Transformers learn factored representations
  328. Self-Supervised Learning from Structural Invariance
  329. From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making
  330. ProofVerifier: A Scalable, Diversity-Driven Framework for Natural-Language Proof Verification
  331. C-kNN-LSH: A Nearest-Neighbor Algorithm for Sequential Counterfactual Inference
  332. Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes
  333. SWE-Universe: Scale Real-World Verifiable Environments to Millions
  334. Automated Multiple Mini Interview (MMI) Scoring
  335. Transfer Learning Through Conditional Quantile Matching
  336. NAB: Neural Adaptive Binning for Sparse-View CT reconstruction
  337. Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning
  338. Implicit neural representation of textures
  339. Artificial Intelligence and Symmetries: Learning, Encoding, and Discovering Structure in Physical Data
  340. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
  341. Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
  342. Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents
  343. VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
  344. TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour
  345. Language Steering for Multilingual In-Context Learning
  346. MolLangData: A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method
  347. The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
  348. FragmentFlow: Scalable Transition State Generation for Large Molecules
  349. Spark: Modular Spiking Neural Networks
  350. Decoupling Generalizability and Membership Privacy Risks in Neural Networks
  351. Hallucination or Creativity: How to Evaluate AI-Generated Scientific Stories?
  352. AROpt: An Optimization Method for Autoregressive Time Series Forecasting
  353. Cross-Lingual Stability of LLM Judges Under Controlled Generation: Evidence from Finno-Ugric Languages
  354. AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
  355. A Physical Theory of Backpropagation: Exact Gradients from the Least-Action Principle
  356. Bridging the Sim-to-Real Gap with multipanda_ros2: A Real-Time ROS2 Framework for Multimanual Systems
  357. HopFormer: Sparse Graph Transformers with Explicit Receptive Field Control
  358. OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data
  359. Unsupervised Physics-Informed Operator Learning through Multi-Stage Curriculum Training
  360. Segment to Focus: Guiding Latent Action Models in the Presence of Distractors
  361. Alignment-Aware Model Adaptation via Feedback-Guided Optimization
  362. Variational Entropic Optimal Transport
  363. Causal Inference for Preprocessed Outcomes with an Application to Functional Connectivity
  364. Interpretability in Deep Time Series Models Demands Semantic Alignment
  365. SEDformer: Event-Synchronous Spiking Transformers for Irregular Telemetry Time Series Forecasting
  366. Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts
  367. Show, Don't Tell: Morphing Latent Reasoning into Image Generation
  368. Spectral Superposition: A Theory of Feature Geometry
  369. Evaluating OCR Performance for Assistive Technology: Effects of Walking Speed, Camera Placement, and Camera Type
  370. MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
  371. Using Correspondence Patterns to Identify Irregular Words in Cognate sets Through Leave-One-Out Validation
  372. LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
  373. Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge
  374. Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism
  375. Generating Physically Sound Designs from Text and a Set of Physical Constraints
  376. Sinhala Physical Common Sense Reasoning Dataset for Global PIQA
  377. Cardinality-Preserving Attention Channels for Graph Transformers in Molecular Property Prediction
  378. State Rank Dynamics in Linear Attention LLMs
  379. PCA of probability measures: Sparse and Dense sampling regimes
  380. Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision
  381. Malware Detection Through Memory Analysis
  382. Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages
  383. STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
  384. SurvKAN: A Fully Parametric Survival Model Based on Kolmogorov-Arnold Networks
  385. AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?
  386. CIEC: Coupling Implicit and Explicit Cues for Multimodal Weakly Supervised Manipulation Localization
  387. Generalized Optimal Classification Trees: A Mixed-Integer Programming Approach
  388. Lung Nodule Image Synthesis Driven by Two-Stage Generative Adversarial Networks
  389. Self-Evolving Coordination Protocol in Multi-Agent AI Systems: An Exploratory Systems Feasibility Study
  390. Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding
  391. Interpretable Tabular Foundation Models via In-Context Kernel Regression
  392. Generating Causal Temporal Interaction Graphs for Counterfactual Validation of Temporal Link Prediction
  393. Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing
  394. Traffic-Aware Navigation in Road Networks
  395. Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
  396. Deep learning enables urban change profiling through alignment of historical maps
  397. Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model
  398. Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
  399. Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting
  400. Quantifying the Gap between Understanding and Generation within Unified Multimodal Models
  401. DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations
  402. Eliminating Registration Bias in Synthetic CT Generation: A Physics-Based Simulation Framework
  403. Two-Stage Grid Optimization for Group-wise Quantization of LLMs
  404. Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies
  405. MLV-Edit: Towards Consistent and Highly Efficient Editing for Minute-Level Videos
  406. The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning
  407. Training-free score-based diffusion for parameter-dependent stochastic dynamical systems
  408. Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs
  409. The Verification Crisis: Expert Perceptions of GenAI Disinformation and the Case for Reproducible Provenance
  410. Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning
  411. WADEPre: A Wavelet-based Decomposition Model for Extreme Precipitation Nowcasting with Multi-Scale Learning
  412. LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs
  413. UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstruction
  414. Efficient Swap Regret Minimization in Combinatorial Bandits
  415. Closing the Loop: Universal Repository Representation with RPG-Encoder
  416. Handling Covariate Mismatch in Collaborative Linear Prediction
  417. Active learning from positive and unlabeled examples
  418. Learning Half-Spaces from Perturbed Contrastive Examples
  419. AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
  420. Calibrating Adaptive Smoothing Methods for Freeway Traffic Reconstruction
  421. BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling
  422. Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data
  423. Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits
  424. FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
  425. Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks
  426. Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
  427. Twinning Complex Networked Systems: Data-Driven Calibration of the mABCD Synthetic Graph Generator
  428. Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization
  429. Canonical Intermediate Representation for LLM-based optimization problem formulation and code generation
  430. Hippasus: Effective and Efficient Automatic Feature Augmentation for Machine Learning Tasks on Relational Data
  431. Adaptive Quality-Diversity Trade-offs for Large-Scale Batch Recommendation
  432. Scale-covariant spiking wavelets
  433. Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
  434. DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
  435. Robust Domain Generalization under Divergent Marginal and Conditional Distributions
  436. Rethinking Genomic Modeling Through Optical Character Recognition
  437. SNAP: A Self-Consistent Agreement Principle with Application to Robust Computation
  438. Position: The Need for Ultrafast Training
  439. Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
  440. SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors
  441. From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
  442. Optimizing Tensor Train Decomposition in DNNs for RISC-V Architectures Using Design Space Exploration and Compiler Optimizations
  443. Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs
  444. SpikingGamma: Surrogate-Gradient Free and Temporally Precise Online Training of Spiking Neural Networks with Smoothed Delays
  445. Beyond Local Edits: Embedding-Virtualized Knowledge for Broader Evaluation and Preservation of Model Editing
  446. FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
  447. IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
  448. Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
  449. Zero-Shot Off-Policy Learning
  450. Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images
  451. Deep Multivariate Models with Parametric Conditionals
  452. Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network
  453. FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE Surrogates
  454. Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategy
  455. T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
  456. PIMCST: Physics-Informed Multi-Phase Consensus and Spatio-Temporal Few-Shot Learning for Traffic Flow Forecasting
  457. Large Language Model and Formal Concept Analysis: a comparative study for Topic Modeling
  458. LIEREx: Language-Image Embeddings for Robotic Exploration
  459. Probabilistic function-on-function nonlinear autoregressive model for emulation and reliability analysis of stochastic dynamical systems
  460. On the Inherent Privacy Amplification of Missing Data
  461. Bayesian Integration of Nonlinear Incomplete Clinical Data
  462. Embedding Learning on Multiplex Networks for Link Prediction
  463. PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks
  464. From Code-Centric to Concept-Centric: Teaching NLP with LLM-Assisted "Vibe Coding"
  465. GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs
  466. Reliable Real-Time Value at Risk Estimation via Quantile Regression Forest with Conformal Calibration
  467. DomusFM: A Foundation Model for Event-Based Behavioral Monitoring in Smart-Homes
  468. Propagating the prior from far to near offset: A self-supervised diffusion framework for progressively recovering near-offsets of towed-streamer data
  469. DSXFormer: Dual-Pooling Spectral Squeeze-Expansion and Dynamic Context Attention Transformer for Hyperspectral Image Classification
  470. Learning Sparse Visual Representations via Spatial-Semantic Factorization
  471. Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
  472. Multi-Task Learning for Robot Perception with Imbalanced Data
  473. Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design
  474. Internal Flow Signatures for Self-Checking and Refinement in LLMs
  475. Geometric Analysis of Token Selection in Multi-Head Attention
  476. ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding
  477. Autocorrelated Optimize-via-Estimate: Predict-then-Optimize versus Finite-sample Optimal
  478. PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
  479. Grappa: Gradient-Only Communication for Scalable Graph Neural Network Training
  480. GRAB: An LLM-Inspired Sequence-First Click-Through Rate Prediction Modeling Paradigm
  481. Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
  482. RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responses
  483. Time2Vec Transformer for Robust Gesture Recognition from Low-Density sEMG
  484. Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection
  485. How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
  486. WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?
  487. No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation
  488. CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
  489. SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection
  490. Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
  491. DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
  492. AXE: Low-Cost Cross-Domain Web Structured Information Extraction
  493. Efficient Cross-Country Data Acquisition Strategy for ADAS via Street-View Imagery
  494. Synesthesia of Vehicles: Tactile Data Synthesis from Visual Inputs
  495. Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
  496. Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It
  497. Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processes
  498. LDRNet: Large Deformation Registration Model for Chest CT Registration
  499. Spatio-Temporal Transformers for Long-Term NDVI Forecasting
  500. Automated Discontinuity Set Characterisation in Enclosed Rock Face Point Clouds Using Single-Shot Filtering and Cyclic Orientation Transformation
  501. Stein-Rule Shrinkage for Stochastic Gradient Estimation in High Dimensions
  502. Cost-Aware Bayesian Optimization for Prototyping Interactive Devices
  503. DIA-CLIP: a universal representation learning framework for zero-shot DIA proteomics
  504. <SOG_k>: One LLM Token for Explicit Graph Structural Understanding
  505. CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
  506. GDPR-Compliant Person Recognition in Industrial Environments Using MEMS-LiDAR and Hybrid Data
  507. A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
  508. MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
  509. Spot-Wise Smart Parking: An Edge-Enabled Architecture with YOLOv11 and Digital Twin Integration
  510. ObjEmbed: Towards Universal Multimodal Object Embeddings
  511. MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Network
  512. Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives
  513. Enhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training
  514. Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment
  515. Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
  516. Softmax Linear Attention: Reclaiming Global Competition
  517. Tail-Aware Post-Training Quantization for 3D Geometry Models
  518. MACD: Model-Aware Contrastive Decoding via Counterfactual Data
  519. Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models
  520. Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations
  521. Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting
  522. MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration
  523. Improving Backward Conformal Prediction via Non-Conformity Score Transformation
  524. Cross-Domain Fake News Detection on Unseen Domains via LLM-Based Domain-Aware User Modeling
  525. FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization
  526. Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark
  527. BBPE16: UTF-16-based byte-level byte-pair encoding for improved multilingual speech recognition
  528. Mechanistic Indicators of Steering Effectiveness in Large Language Models
  529. MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark
  530. Optimizing Prompts for Large Language Models: A Causal Approach
  531. Physics Informed Generative AI Enabling Labour Free Segmentation For Microscopy Analysis
  532. Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data
  533. Mitigating loss of control in advanced AI systems through instrumental goal trajectories
  534. Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection
  535. Functional Subspace, where language models can use vector algebra to solve problems
  536. The Strategic Foresight of LLMs: Evidence from a Fully Prospective Venture Tournament
  537. Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
  538. Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism
  539. Towards Autonomous Instrument Tray Assembly for Sterile Processing Applications
  540. VRGaussianAvatar: Integrating 3D Gaussian Avatars into VR
  541. Real-Time Loop Closure Detection in Visual SLAM via NetVLAD and Faiss
  542. AI-Assisted Adaptive Rendering for High-Frequency Security Telemetry in Web Interfaces
  543. Beyond Prediction-Set Size: Quantifying Conformal Uncertainty through Credal Geometry
  544. Moonworks Lunara Aesthetic II: An Image Variation Dataset
  545. TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
  546. From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction
  547. On the Spatiotemporal Dynamics of Generalization in Neural Networks
  548. De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion
  549. The Effect of Mini-Batch Noise on the Implicit Bias of Adam
  550. Chance-Constrained Inference for Hallucination Risk Control in Large Language Models
  551. COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection
  552. HuPER: A Human-Inspired Framework for Phonetic Perception
  553. Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classification
  554. AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift
  555. Toward Enhancing Representation Learning in Federated Multi-Task Settings
  556. Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?
  557. CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption
  558. SUSD: Structured Unsupervised Skill Discovery through State Factorization
  559. SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
  560. AgroFlux: A Spatial-Temporal Benchmark for Carbon and Nitrogen Flux Prediction in Agricultural Ecosystems
  561. ToPT: Task-Oriented Prompt Tuning for Urban Region Representation Learning
  562. Minimax optimal differentially private synthetic data for smooth queries
  563. Universal Redundancies in Time Series Foundation Models
  564. Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
  565. The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR
  566. The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation
  567. UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception
  568. Two-chart Beltrami Optimization for Distortion-Controlled Spherical Bijection with Application to Brain Surface Registration
  569. Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
  570. A Lightweight Sparse Interaction Network for Time Series Forecasting
  571. On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations
  572. DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning
  573. Visible Light Positioning With Lam'e Curve LEDs: A Generic Approach for Camera Pose Estimation
  574. When Is Generalized Bayes Bayesian? A Decision-Theoretic Characterization of Loss-Based Updating
  575. LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
  576. DREAMS: A Social Exchange Theory-Informed Modeling of Misinformation Engagement on Social Media
  577. Local exponential stability of mean-field Langevin descent-ascent and associated particle system
  578. Argument Rarity-based Originality Assessment for AI-Assisted Writing
  579. Combined Flicker-banding and Moire Removal for Screen-Captured Images
  580. How Implicit Bias Accumulates and Propagates in LLM Long-term Memory
  581. Autonomous Question Formation for Large Language Model-Driven AI Systems
  582. Plain Transformers are Surprisingly Powerful Link Predictors
  583. FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training
  584. Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
  585. Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units
  586. PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
  587. Toward a Machine Bertin: Why Visualization Needs Design Principles for Machine Cognition
  588. The Inlet Rank Collapse in Implicit Neural Representations: Diagnosis and Unified Remedy
  589. You Need an Encoder for Native Position-Independent Caching
  590. Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection
  591. White-Box Neural Ensemble for Vehicular Plasticity: Quantifying the Efficiency Cost of Symbolic Auditability in Adaptive NMPC
  592. RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment
  593. MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
  594. Enhancing Generalization in Evolutionary Feature Construction for Symbolic Regression through Vicinal Jensen Gap Minimization
  595. Harnessing Flexible Spatial and Temporal Data Center Workloads for Grid Regulation Services
  596. Governance at the Edge of Architecture: Regulating NeuroAI and Neuromorphic Systems
  597. TreeLoc: 6-DoF LiDAR Global Localization in Forests via Inter-Tree Geometric Matching
  598. Draw2Learn: A Human-AI Collaborative Tool for Drawing-Based Science Learning
  599. OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference