mlsanityData to 7 Oct 2026

Papers

New on arXiv

Thu 21 May 2026

573 papers

  1. Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo DatasetLLM agents and tool use → Medical and scientific domain agents
  2. KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model InferenceEfficient LLM inference and serving → KV cache optimization
  3. OncoTriad-QA: A Patient-Level Radiology-Pathology-Genomics Benchmark for Pan-Cancer ReasoningLLM reasoning → Clinical and biomedical applications
  4. VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page DocumentsRetrieval-augmented generation → Multimodal RAG +1
  5. DecodeShare: Tracing the Shared Subspace of LLM Decode-Time DecisionsEfficient LLM inference and serving → Early exit and edge inference
  6. FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula GenerationSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  7. Structured Synthetic Reasoning Data for Arithmetic Fine-Tuning of Small Language ModelsLLM reasoning → Mathematical reasoning +1
  8. Simulating Hate Speech Cascades with Multi-LLM Agents: Empirical Grounding, Modeling Fidelity, and Intervention StrategiesLLM agents and tool use → Social simulation and multi-agent debate
  9. Molecular Lead Optimization via Agentic Tool PlanningLLM agents and tool use → Medical and scientific domain agents
  10. E3-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative InferenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security ImplicationsLLM safety and security → Membership inference attacks
  12. More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill LibrariesLLM agents and tool use → Agent skill learning and evolution
  13. Mixture of Complementary Agents for Robust LLM EnsembleLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent DebateLLM agents and tool use → Social simulation and multi-agent debate
  15. Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent DynamicsWorld models → Latent predictive world models
  16. The Attribution Contract for Generative Language ModelsMixture-of-experts → MoE large language models
  17. GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMsMixture-of-experts → MoE large language models
  18. PathCal: State-Aware Reflection-Marker Calibration for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
  19. Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching ModelsDiffusion models → Flow matching, time series and science
  20. What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QALLM agents and tool use → Agent memory systems
  21. A measurement substrate for agentic Kubernetes operations: Methodology and a case study in retrieval-compounding falsificationLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  23. Model Collapse as Cultural EvolutionSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  24. DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG MethodsRetrieval-augmented generation → Medical and biomedical RAG
  25. HawkesLLM: Semantic Uncertainty Propagation in Agentic Text SimulationLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic TopographyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  27. Brain-LLM Alignment Tracks Training Data, Not TypologyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. World Machine: Towards Generative World Modeling for Time-SeriesWorld models → World models for language agents
  29. How to Steer Your Multi-Agent System: Human-LLM Collaborative PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. PACE: Two-Timescale Self-Evolution for Small Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in AutismLLM agents and tool use → Medical and scientific domain agents
  32. Test-Time Training Undermines Safety GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
  33. Learned Relay Representations for Forward-Thinking Discrete Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  34. MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model CoordinationLLM agents and tool use → General LLM agent frameworks and benchmarks
  35. Learnability-Informed Fine-Tuning of Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  36. RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query GenerationLLM reasoning → Test-time compute and efficient thinking
  37. AI-Friendly LaTeX: Using LaTeX Code as a Knowledge Source for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  38. Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  39. Transcoders Trace Visual Grounding and Hallucinations in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  40. From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular DataLLM reasoning → Clinical and biomedical applications
  41. Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +1
  42. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid ControlDiffusion models → Diffusion and flow policies for robotics
  43. Tensor Cache: Eviction-conditioned Associative Memory for TransformersEfficient LLM inference and serving → KV cache optimization
  44. MotiMotion: Motion-Controlled Video Generation with Visual ReasoningLLM reasoning → Multimodal reasoning
  45. AwareVLN: Reasoning with Self-awareness for Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning +1
  46. GesVLA: Gesture-Aware Vision-Language-Action Model Embedded RepresentationsVision-language-action models → Generalist VLA models and benchmarks
  47. MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. Gated DeltaNet-2: Decoupling Erase and Write in Linear AttentionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  49. LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents +1
  50. DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/RollbackLLM agents and tool use → Software engineering coding agents
  51. FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly DetectionMixture-of-experts → Expert routing strategies
  52. DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation AutoencodersDiffusion models → Diffusion foundations and sampling
  53. SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival AnalysisDiffusion models → Diffusion foundations and sampling
  54. MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking DataState-space sequence models (S4, Mamba) → Vision Mamba backbones
  55. Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State ReformulationDiffusion models → Diffusion foundations and sampling
  56. Advancing Mathematics Research with AI-Driven Formal Proof SearchLLM reasoning → Mathematical reasoning
  57. SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept GenerationDiffusion models → Image generation, text-to-image and editing
  58. ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  59. The Value of Covariance Matching in Gaussian DDPMs and the Lanczos SamplerDiffusion models → Diffusion foundations and sampling
  60. Self-Evolving Multi-Agent Systems via Decentralized MemoryLLM agents and tool use → Agent memory systems
  61. WorldKV: Efficient World Memory with World Retrieval and CompressionDiffusion models → Video generation +1
  62. Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music GeneratorsDiffusion models → Audio, speech and music
  63. Abstraction for Offline Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  64. Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary SignalsLLM reasoning → Reinforcement learning for reasoning
  65. Scientific reasoning does not reliably translate into scientific forecasting in frontier AILLM reasoning → Knowledge- and tool-augmented reasoning
  66. Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  67. From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action ModelVision-language-action models → Generalist VLA models and benchmarks
  68. SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  69. MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in FinanceLLM agents and tool use → Financial trading and forecasting agents
  70. SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning SegmentationLLM reasoning → Multimodal reasoning
  71. What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language PretrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  72. AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image PromptersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  73. Boiling the Frog: A Multi-Turn Benchmark for Agentic SafetyLLM agents and tool use → Agent threats, guardrails and governance
  74. Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement LearningLLM agents and tool use → Financial trading and forecasting agents
  75. Two is better than one: A Collapse-free Multi-Reward RLIF Training FrameworkLLM reasoning → Reinforcement learning for reasoning
  76. Agentic CLEAR: Automating Multi-Level Evaluation of LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
  78. Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score NetworkDiffusion models → Diffusion and flow policies for robotics
  79. A Tutorial on Diffusion Theory: From Differential Equations to Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  80. VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video SynthesisLLM reasoning → Spatial and embodied reasoning +1
  81. LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint GuidanceLLM reasoning → Reasoning benchmarks and evaluation
  82. GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent ServingLLM reasoning → Reasoning for agents, planning and code +1
  83. SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent EvaluationsLLM agents and tool use → Tool learning and function calling
  84. GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene ReasoningLLM reasoning → Spatial and embodied reasoning +1
  85. F-TIS: Harnessing Diverse Models in Collaborative GRPOLLM reasoning → Reinforcement learning for reasoning
  86. SpaceDG: Benchmarking Spatial Intelligence under Visual DegradationLLM reasoning → Spatial and embodied reasoning +1
  87. Why Are Agentic Pull Requests Merged or Rejected? An Empirical StudyLLM agents and tool use → Software engineering coding agents
  88. "Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue ResolutionLLM agents and tool use → Software engineering coding agents
  89. Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented ReasoningLLM reasoning → Reasoning for agents, planning and code
  90. LACO: Adaptive Latent Communication for Collaborative DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
  91. Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less CostLLM agents and tool use → Software engineering coding agents
  92. Understanding Multimodal Failure in Action-Chunking Behavioral CloningOffline RL and imitation learning from data → Robot manipulation imitation learning
  93. Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight RecyclingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  94. MaSC: A Masked Similarity Metric for Evaluating Concept-Driven GenerationDiffusion models → Image generation, text-to-image and editing
  95. Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model RolloutsWorld models → Embodied and robot world models +1
  96. Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer InferenceState-space sequence models (S4, Mamba) → Core SSM architectures for language
  97. From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document UnderstandingLLM reasoning → Multimodal reasoning
  98. Unified Data Selection for LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  99. Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  100. Boundary-targeted Membership Inference Attacks on Safety ClassifiersLLM safety and security → Membership inference attacks
All 573
  1. AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in AgricultureLLM agents and tool use → Multimodal and embodied agents
  2. Integrating Chain-of-Thought into Generative Retrieval: A Preliminary StudyLLM reasoning → Knowledge- and tool-augmented reasoning
  3. Bernini: Latent Semantic Planning for Video DiffusionLLM reasoning → Multimodal reasoning +2
  4. From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow MatchingDiffusion models → Flow matching, time series and science
  5. Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  6. ASEval: Automated Trajectory-Level Security Testing for Autonomous AgentsLLM agents and tool use → Agent threats, guardrails and governance
  7. PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
  8. Spatial Memory for Out-of-Vision Manipulation in Vision-Language-ActionVision-language-action models → 3D and spatial-aware VLA
  9. Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task TransferabilityMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  10. MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-AnsweringLLM reasoning → Test-time compute and efficient thinking +1
  11. Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  12. Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation RewritingLLM safety and security → Safety alignment, refusal and guardrails
  13. Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk PlayLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. SGR-Bench: Benchmarking Search Agents on State-Gated RetrievalLLM agents and tool use → Web, search, and research agents
  15. Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RLSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  16. CLORE: Content-Level Optimization for Reasoning EfficiencyLLM reasoning → Test-time compute and efficient thinking
  17. GALAR-TemporalNet v2: Anatomy-Guided Dual-Branch Temporal Classification with Bidirectional Mamba and Dual-Graph GCN for Video Capsule Endoscopy -- after competition resultsState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  18. EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven LearningMultimodal LLMs / vision-language models → Image editing and quality assessment +2
  19. Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural DocumentsRetrieval-augmented generation → Multimodal RAG
  20. Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  21. Enhancing Multimodal Large Language Models for Safety-Critical Driving Video AnalysisMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  22. Action with Visual PrimitivesVision-language-action models → Generalist VLA models and benchmarks
  23. Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  24. Measuring Cross-Modal Synergy: A Benchmark for VLM ExplainabilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  25. Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM AgentsLLM agents and tool use → Software engineering coding agents
  26. World Model Control by Trajectory Reachability MetricsWorld models → Latent predictive world models
  27. ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  28. One-Way Policy Optimization for Self-Evolving LLMsLLM reasoning → Reinforcement learning for reasoning +1
  29. IdleSpec: Exploiting Idle Time via Speculative Planning for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  31. One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent SystemsLLM agents and tool use → Multimodal and embodied agents
  32. Efficient Agentic Reasoning Through Self-Regulated Simulative PlanningWorld models → World models for language agents +2
  33. Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-ConsistencyLLM reasoning → Reasoning benchmarks and evaluation
  34. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  35. ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  36. ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time ScalingLLM reasoning → Reasoning for agents, planning and code +1
  37. A Comparative Study of Language Models for Khmer Retrieval-Augmented Question AnsweringRetrieval-augmented generation → RAG pipeline design and evaluation
  38. Narrative Sharpens Gender Gaps: Surveying Film Characters with LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  39. LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving ModelWorld models → World models for autonomous driving +2
  40. RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow MatchingDiffusion models → Audio, speech and music
  41. JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model EvaluationMultimodal LLMs / vision-language models → Medical vision-language models
  42. Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and GriddingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  43. From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  44. Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual AttentionLLM reasoning → Multimodal reasoning +1
  45. FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task RoutingLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  46. EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX GenerationMixture-of-experts → Vision mixture-of-experts
  47. Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded GenerationsDiffusion models → Diffusion foundations and sampling
  48. Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision SupportLLM reasoning → Clinical and biomedical applications
  49. RADAR: Defending RAG Dynamically against Retrieval CorruptionRetrieval-augmented generation → Privacy and security of RAG
  50. GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning
  51. SO-Mamba: State-Ownership Mamba for Unrolled MRI ReconstructionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  52. Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion PredictionDiffusion models → Video generation
  53. ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion AccelerationDiffusion models → Diffusion foundations and sampling +1
  54. PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-ThoughtLLM reasoning → Spatial and embodied reasoning
  55. LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent ReasoningLLM reasoning → Audio-language model reasoning +1
  56. Rethinking Token Reduction for Diffusion Models via Output-Similarity-AwarenessDiffusion models → Diffusion foundations and sampling +1
  57. Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  58. The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic SystemsLLM agents and tool use → Agent memory systems
  59. From Patches to Trajectories: Privileged Process Supervision for Software-Engineering AgentsLLM agents and tool use → Software engineering coding agents
  60. RiT: Vanilla Diffusion Transformers Suffice in Representation SpaceDiffusion models → Flow matching, time series and science
  61. Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information FlowMultimodal LLMs / vision-language models → Multimodal emotion understanding
  62. Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMsLLM reasoning → Reasoning for agents, planning and code
  63. Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal GroundingLLM reasoning → Multimodal reasoning
  64. Reinforced Preference Optimization for Reasoning-Augmented RecommendationsLLM reasoning → LLM reasoning for recommendation
  65. SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval AgentsLLM agents and tool use → Web, search, and research agents
  66. ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care DataWorld models → Medical and surgical world models
  67. Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM PipelinesLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. Detecting Offensive Cyber Agents: A Detection-in-Depth ApproachLLM agents and tool use → Agent threats, guardrails and governance
  69. MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention CuesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  70. NasZip: Software and Hardware Co-Design to Accelerate Approximate Nearest Neighbor Search with DIMM-Based Near-Data ProcessingRetrieval-augmented generation → Vector search and ANN indexes +1
  71. Dynamic Mixture of Latent Memories for Self-Evolving AgentsMixture-of-experts → Mixture of LoRA experts
  72. Claim-Selective Certification for High-Risk Medical Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  73. Visual-Advantage On-Policy Distillation for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  74. MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning TasksLLM reasoning → Multimodal reasoning +2
  75. Noise Schedule Design for Diffusion Models: An Optimal Control PerspectiveDiffusion models → Diffusion foundations and sampling
  76. Guided Trajectory Optimization with Sparse Scaling for Test-Time DiffusionDiffusion models → Diffusion foundations and sampling
  77. Token-weighted Direct Preference Optimization with AttentionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  78. Thermo-VL: Extending Vision-Language Models to Thermal Infrared PerceptionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  79. EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot ControlVision-language-action models → Efficient VLA inference and adaptation
  80. PhylaFlow: Hybrid Flow Matching in Billera-Holmes-Vogtmann Tree Space for Phylogenetic InferenceDiffusion models → Flow matching, time series and science
  81. The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT TruncationLLM reasoning → Prompting and chain-of-thought reasoning
  82. CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization +2
  83. Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  84. OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  85. ACC: Compiling Agent Trajectories for Long-Context TrainingLLM reasoning → Reasoning for agents, planning and code +1
  86. STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets
  87. When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL
  88. RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates
  89. Dream machine -- the next creative economy
  90. From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages
  91. Distributed Quantum Learning over Near-term Devices: Convergence Analysis and Security Design
  92. Trust in Generative AI for Health Information Consumption and the Effect of Learned Dependency: An Experimental Investigation
  93. Tracking Urban Atmospheric Pollutants using Sentinel-5P Satellite Data
  94. Rashomon-Seeded Annealing for Robust Bayesian Inference in Factorial Designs
  95. CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention
  96. Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
  97. Self-Play Reinforcement Learning under Imperfect Information in Big 2
  98. Comment on "Spin-1/2 Kagome Heisenberg Antiferromagnet: Machine Learning Discovery of the Spinon Pair-Density-Wave Ground State"
  99. Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
  100. Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception
  101. SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection
  102. EMMA: Extracting Multiple physical parameters from Multimodal Data
  103. A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?
  104. LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
  105. Hidden-State Privacy Has an Empty Middle
  106. Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
  107. Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction
  108. Aurora Hunter: A Two-Stage Framework for Probabilistic Visibility Forecasting
  109. Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling
  110. WTKO-CNN: Deep Learning Reveals Sequence Motifs Distinguishing Wild-Type and Knockout ATAC-seq Peaks
  111. Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
  112. Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering
  113. Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study
  114. A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Collected Works
  115. LLM Sparsity Prior for Robust Feature Selection
  116. Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression
  117. Encrypted Neural Networks without Overflows
  118. Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Plane Augmentation Study on BRISC 2025
  119. A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses
  120. Security of LLM-generated Code: A Comparative Analysis
  121. The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
  122. KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
  123. ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention
  124. The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
  125. DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
  126. RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering
  127. Orbax: Distributed Checkpointing with JAX
  128. Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
  129. Millimeter-wave Imaging for Anthropometric Body Measurement
  130. Anytime Training with Schedule-Free Spectral Optimization
  131. DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks
  132. Decomposing and Measuring Evaluation Awareness
  133. The TIME Machine: On The Power of Motion for Efficient Perception
  134. Steered Generation via Gradient-Based Optimization on Sparse Query Features
  135. Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs
  136. Open datasets and machine learning for two-phase heat transfer: a review following a spatial-temporal taxonomy
  137. Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
  138. Uncovering the Latent Potential of Deep Intermediate Representations
  139. RADAR: Relative Angular Divergence Across Representations
  140. The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems
  141. Smoothed Elicitation Complexity for Approximate Gamma-calibration of Discrete Classification Tasks
  142. MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
  143. Scene Reconstruction as Mapping Priors for 3D Detection
  144. CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration
  145. Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
  146. Active Sensing Subserves Task-Level Control
  147. Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
  148. Memorization Dynamics of Fill-in-the-Middle Pretraining
  149. A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text
  150. LLM Code Smells: A Taxonomy and Detection Approach
  151. When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance
  152. Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
  153. A mathematical theory of balancing relational generalization and memorization
  154. Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs
  155. Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics
  156. Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
  157. Graph Alignment Topology as an Inductive Bias for Grounding Detection
  158. GazeBehavior Annotation Toolkit (GBAT): AI-powered toolkit for automatic annotation of egocentric eye-tracking and video data of child-caregiver interaction
  159. FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data
  160. Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
  161. Improved Vision-to-Chart Buoy Association with Learned World-to-Image Projection
  162. Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning
  163. Building a privacy-preserving Federated Recommender system for mobile devices
  164. VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
  165. EVE-Agent: Evidence-Verifiable Self-Evolving Agents
  166. Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations
  167. Mediative Fuzzy Logic: From Type-1 Foundations to Type-2, Type-3 and Quantum Extensions
  168. FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
  169. L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark
  170. Is TabPFN the Silver Bullet for Insurance Pricing?
  171. Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems
  172. Extending Deep Event Visual Odometry with Sparse Point-Cloud Export
  173. Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology
  174. ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
  175. Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs
  176. Tokenisation via Convex Relaxations
  177. Integrable Elasticity via Neural Demand Potentials
  178. Cambrian-P: Pose-Grounded Video Understanding
  179. Vector Policy Optimization: Training for Diversity Improves Test-Time Search
  180. Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
  181. Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
  182. The Matching Principle: When Does a Training Penalty Cover Deployment Shift?
  183. Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
  184. Evaluating Commercial AI Chatbots as News Intermediaries
  185. CogAdapt: Adapting Clinical ECG Foundation Models for Wearable Cognitive Load Assessment
  186. Deep Reinforcement Learning for Flexible Job Shop Scheduling with Random Job Arrivals
  187. Reducing Political Manipulation with Consistency Training
  188. Understanding Data Temporality Impact on Large Language Models Pre-training
  189. Synthetic Data Alone is Enough? Rethinking Data Scarcity in Pediatric Rare Disease Recognition
  190. Towards a General Intelligence and Interface for Wearable Health Data
  191. Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
  192. Spectral Tail Auxiliary Learning for AI-Generated Image Detection
  193. Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
  194. Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
  195. Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
  196. Ternary Decision Trees with Locally-Adaptive Uncertainty Zones
  197. Proxy-Based Approximation of Shapley and Banzhaf Interactions
  198. The Distillation Game: Adaptive Evaluations & Efficient Defenses
  199. Optimization over the intersection of manifolds
  200. HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools
  201. Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models
  202. Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
  203. Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning
  204. Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts
  205. Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
  206. Parametric Modular Answer Set Programs Made Declarative
  207. AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
  208. AMEL: Accumulated Message Effects on LLM Judgments
  209. Beyond the Org Chart: AI and the Transformation of Invisible Work
  210. Tokenization with Split Trees
  211. Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions
  212. Improving Viewpoint-Invariance and Temporal Consistency for Action Detection
  213. Scout-Assisted Planning for Heterogeneous Robot Teams under Partially Known Environments
  214. Latent Spectroscopy: Posterior Collapse as a Feature
  215. ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification
  216. Swift Sampling: Selecting Temporal Surprises via Taylor Series
  217. Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment
  218. Self-Policy Distillation via Capability-Selective Subspace Projection
  219. Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most
  220. Holographic functions and neural networks
  221. Claw AI Lab: An Autonomous Multi-Agent Research Team
  222. Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
  223. Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs
  224. The Secretary Problem with a Stochastic Precursor
  225. Whose Voice Counts? Mapping Stakeholder Perspectives on AI Through Public Submissions to the U.S. Government
  226. From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder
  227. Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
  228. More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
  229. The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
  230. Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
  231. AtomicMotion: Learning Human Motion From Different Human Parts
  232. H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
  233. A note on convergence of Wasserstein policy optimization
  234. UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection
  235. GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT
  236. Chinese sensorimotor and embodiment norms for 3,000 lexicalized concepts
  237. Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
  238. Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions
  239. Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
  240. Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
  241. Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection
  242. Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms
  243. MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
  244. Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
  245. Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure
  246. SceneAligner: 3D-Grounded Floorplan Localization in the Wild
  247. Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
  248. Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping
  249. SegGuidedNet: Sub-Region-Aware Attention Supervision for Interpretable Brain Tumor Segmentation
  250. Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
  251. Cell Phantom Video Generation in Elliptical Fourier Descriptor Domain
  252. Regret-Based (ε,δ)-optimal Stopping Criteria for Bayesian Optimization
  253. Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
  254. ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation
  255. FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning
  256. MOTOR: A Multimodal Dataset for Two-Wheeler Rider Behavior Understanding
  257. A Martingale Kernel Independence Test
  258. MKG-CARE: Case-Aware Reasoning with Multimodal Knowledge Graphs for Explainable Medical Image Diagnosis
  259. One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
  260. Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning
  261. Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
  262. Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
  263. TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
  264. Relational Linear Properties in Language Models: An Empirical Investigation
  265. Disentanglement Beyond Generative Models with Riemannian ICA
  266. A Subjective Logic-based method for runtime confidence updates in safety arguments
  267. Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets
  268. Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systems
  269. Reflecti-Mate: A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinking
  270. Generative Modeling by Value-Driven Transport
  271. EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
  272. Towards Direct Evaluation of Harness Optimizers via Priority Ranking
  273. BeLink: Biomedical Entity Linking Meets Generative Re-Ranking
  274. The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning
  275. The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
  276. Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline
  277. Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
  278. Polite on the Surface, Broken in Practice: A Curated Dataset for Fixing Generation and Register Failures in Low-Resource Bangla Text Generation
  279. When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
  280. Implicit Regularization of Mini-Batch Training in Graph Neural Networks
  281. DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval
  282. Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
  283. Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
  284. Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers
  285. BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
  286. SADGE: Structure and Appearance Domain Gap Estimation of Synthetic and Real Data
  287. In Silico Modeling of the RAMPHO Buffer: Dissociating Informational and Energetic Masking via Phonetic Entropy in Deep Neural Networks
  288. Reinforcement learning for ion shuttling on trapped-ion quantum computers
  289. From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models
  290. KAPPS: A knowledge-based CPPS Architecture for the Circular Factory
  291. Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning
  292. Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
  293. Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
  294. S2ED: From Story to Executable Descriptions for Consistency-Aware Story Illustration
  295. Cohesion-6K: An Arabic Dataset for Analyzing Social Cohesion and Conflict in Online Discourse
  296. A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers
  297. Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions
  298. Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection
  299. Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation
  300. AMUSE: Anytime Muon with Stable Gradient Evaluation
  301. Time-varying rPPG signal separation via block-sparse signal model
  302. Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance
  303. FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
  304. Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
  305. The Neglected Baseline in Model Interpretation
  306. Towards Clinically Interpretable Ophthalmic VQA via Spatially-Grounded Lesion Evidence
  307. DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory
  308. Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering
  309. Translating Signals to Languages for sEMG-Based Activity Recognition
  310. Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology
  311. Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings
  312. A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
  313. Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market
  314. Efficient Higher-order Subgraph Attribution via Message Passing
  315. Multi-Stage Training for Abusive Comment Detection in Indic Languages
  316. Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning
  317. Towards Explainability of SLMs by investigating Token Level Activation
  318. Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions
  319. ASAP: Attention Sink Anchored Pruning
  320. VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
  321. TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
  322. Scaling Observation-aware Planning in Uncertain Domains
  323. Incentive-Aligned Vehicle-to-Vehicle Energy Trading via Nash-Integrated Multi-Agent Reinforcement Learning
  324. GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction
  325. VEELA: A Clinically-Constrained Benchmark for Liver Vessel Segmentation in Computed Tomography Angiography
  326. Modeling Pathology-Like Behavioral Patterns in Language Models Through Behavioral Fine-Tuning
  327. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
  328. QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks
  329. Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
  330. The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers
  331. Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
  332. 4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting
  333. A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
  334. Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction
  335. Learning Causal Orderings for In-Context Tabular Prediction
  336. Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
  337. SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection
  338. Symbolic Classification-Enabled LHC Limits for BSM Global Fits
  339. 3D LULC classification using multispectral LiDAR and deep learning: current and prospective schemes
  340. Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning
  341. Pattern-and-root inflectional morphology: the Arabic broken plural
  342. ACCoRD: Actor-Critic Conflict Resolution with Deep learning for O-RAN xApps
  343. Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
  344. Evaluation of Pipelines for Data Integration into Knowledge Graphs
  345. Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence
  346. One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
  347. Long-term Fairness with Selective Labels
  348. Detection of Virus and Small Cell Patches in Foci Images Using Switchable Convolution and Feature Pyramid Networks
  349. SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
  350. EmoTrack: Clinical-Semantic Modeling for Text-Based Depression Severity Estimation
  351. Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations
  352. Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
  353. Impact of Atmospheric Turbulence and Pointing Error on Earth Observation
  354. Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
  355. Automatic Contextual Audio Denoising
  356. An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion
  357. What are the Right Symmetries for Formal Theorem Proving?
  358. Direct content-based retrieval from music scores images
  359. D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities
  360. No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
  361. IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions
  362. Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies
  363. Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations
  364. Unlocking Proactivity in Task-Oriented Dialogue
  365. Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference
  366. Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics
  367. REACH: Hand Pose Estimation from Room Corners
  368. GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysis
  369. How Many Different Outputs Can a Transformer Generate?
  370. ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
  371. Can Transformers Learn to Verify During Backtracking Search?
  372. A Robust Semantic Segmentation Pipeline for the CVPR 2026 8th UG2+ Challenge Track 2
  373. Towards a compositional semantics for quantitative confidence assessment in assurance arguments
  374. Kernel-Based Safe Exploration in Deep Reinforcement Learning
  375. Temporal Coding as a Substrate for Sensorimotor Object Inference: A Spiking Reinterpretation of Thousand Brains Architecture
  376. Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
  377. Audience Engagement with Arabic Women's Social Empowerment and Wellbeing: A Decadal Corpus
  378. Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance
  379. Zero-Shot Temporal Action Localization Through Textual Guidance
  380. OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025
  381. Ultra-High-Definition Image Quality Assessment via Graph Representation Learning
  382. Bandit Convex Optimization with Gradient Prediction Adaptivity
  383. No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
  384. From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal k-Sparse GLMs
  385. Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
  386. IKNO: Infinite-order Kernel Neural Operators
  387. Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
  388. LLM-Metrics: Measuring Research Impact Through Large Language Model Memory
  389. SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?
  390. Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning
  391. Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference
  392. Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
  393. Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?
  394. Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
  395. Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues
  396. EventGait: Towards Robust Gait Recognition with Event Streams
  397. Atom-level Protein Representation Learning Improves Protein Structure Prediction
  398. Accelerating Vision Foundation Models with Drop-in Depthwise Convolution
  399. AesFormer: Transform Everyday Photos into Beautiful Memories
  400. From Betting to Empirical Bernstein LIL
  401. Adversarial Trust Poisoning in Vehicular Collaborative Perception
  402. MotionDPS: Motion-Compensated 3D Brain MRI Reconstruction
  403. Self-Supervised ConvLSTM for Fermi Large Area Telescope Transient Detection
  404. Aerodynamic force reconstruction using physics-informed Gaussian processes
  405. OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization
  406. MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
  407. TextTeacher: What Can Language Teach About Images?
  408. Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
  409. VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results
  410. Not Yet: Humans Outperform LLMs in a Colonel Blotto Tournament
  411. Knowledge Graph Re-engineering Along the Ontological Continuum (extended version)
  412. A Camera-Cooperative ISAC Framework for Multimodal Non-Cooperative UAVs Sensing
  413. GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
  414. CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation
  415. ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination
  416. Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
  417. Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes
  418. TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
  419. COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
  420. Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos
  421. Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
  422. Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
  423. Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
  424. Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
  425. LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
  426. Physiology and Anatomy Aware Inverse Inference of Myocardial Infarction for Cardiac Digital Twin
  427. CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
  428. Secure and Parallel Determinant Computation for Large-Scale Matrices in Edge Environments
  429. HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering
  430. AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding
  431. ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
  432. FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments
  433. Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
  434. Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
  435. Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
  436. From TF-IDF to Transformers: A Comparative and Ensemble Approach to Sentiment Classification
  437. ConvNeXt-FD: A Fractal-Based Deep Model for Robust Biomedical Image Segmentation
  438. Virtual 3D H&E Staining from Phase-contrast Back-illumination Interference Tomography
  439. Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
  440. Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
  441. ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
  442. Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
  443. Echo: Learning from Experience Data via User-Driven Refinement
  444. Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection
  445. Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables
  446. How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability
  447. Entropy-Guided Self-Supervised Learning for Medical Image Classification
  448. LLM Retrieval for Stable and Predictable Ad Recommendations
  449. An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
  450. Dual-Integrated Low-Latency Single-Lens Infrared Computational Imaging for Object Detection
  451. AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems
  452. Bounding-Box Trajectories Matter for Video Anomaly Detection
  453. SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
  454. Optimal Guarantees for Auditing R'enyi Differentially Private Machine Learning
  455. Thermodynamic Irreversibility of Training Algorithms
  456. EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
  457. CausalGuard: Conformal Inference under Graph Uncertainty
  458. SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals
  459. A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
  460. CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
  461. Multi-scale interaction network for stereo image super-resolution
  462. Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining
  463. Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review
  464. Planning in the LLM Era: Building for Reliability and Efficiency
  465. Two-Stage Multimodal Framework for Emotion Mimicry Intensity Prediction
  466. When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
  467. Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models
  468. Robust Statistical Estimators with Bounded Empirical Sensitivity
  469. Hypergraph as Language
  470. Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
  471. Causal Discovery in Structural VAR Models Under Equal Noise Variance
  472. Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity
  473. Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention