mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 4 May 2026

427 papers

  1. Large Language Models Show Metacognitive Sensitivity in Medical ReasoningLLM reasoning → Clinical and biomedical applications
  2. AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow AutomationLLM agents and tool use → Web, search, and research agents
  3. Mapping Text to Multiplex Graph: Prompt Compression as L'evy Walk-Guided Graph PruningEfficient LLM inference and serving → Prompt and context compression
  4. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  5. A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  6. When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  7. ANNEAL: Adapting LLM Agents via Governed Symbolic Patch LearningLLM agents and tool use → Agent skill learning and evolution
  8. Understanding Asynchronous Inference Methods for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  9. HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  10. SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM InferenceEfficient LLM inference and serving → Speculative decoding
  11. Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal RepresentationsLLM agents and tool use → Social simulation and multi-agent debate
  12. DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent SystemsLLM agents and tool use → Tool learning and function calling
  13. AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  14. Towards Dependable Retrieval-Augmented Generation Using Factual Confidence PredictionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  15. MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image SegmentationDiffusion models → Robustness, privacy and adversarial aspects
  16. TSCG: Deterministic Tool-Schema Compilation for Agentic LLM DeploymentsLLM agents and tool use → Tool learning and function calling
  17. Safeguarding LLM Agents against Long-Horizon Threats via Shadow MemoryLLM agents and tool use → Agent threats, guardrails and governance
  18. Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  19. Self-Mined Hardness for Safety Fine-TuningLLM safety and security → Jailbreaking
  20. Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin LesionsDiffusion models → Medical imaging and segmentation
  21. Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic InterpretabilityMechanistic interpretability → Probing deception, bias and beliefs
  22. Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover ManagementLLM agents and tool use → Agentic AI for wireless networks
  23. When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  24. ADAPTS: Agentic Decomposition for Automated Protocol-agnostic Tracking of SymptomsLLM agents and tool use → Medical and scientific domain agents
  25. Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?LLM agents and tool use → Software engineering coding agents
  26. Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axisMechanistic interpretability → SAE features and their applications
  27. Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous AgentsLLM agents and tool use → Software engineering coding agents
  28. Pact: A Choreographic Language for Agentic EcosystemsLLM agents and tool use → Social simulation and multi-agent debate
  29. Evaluating Retrieval-Augmented Generation for Explainable Malware AnalysisRetrieval-augmented generation → Privacy and security of RAG
  30. Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function ApproximationDeep reinforcement learning methods → Multi-agent reinforcement learning
  31. ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault LocalizationLLM agents and tool use → Software engineering coding agents
  32. Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak DefensesLLM safety and security → Jailbreaking
  33. Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical AblationLLM safety and security → Machine unlearning
  34. Evaluating Reasoning Models for Queries with PresuppositionsLLM reasoning → Reasoning benchmarks and evaluation
  35. ARIS: Autonomous Research via Adversarial Multi-Agent CollaborationLLM agents and tool use → Web, search, and research agents
  36. Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber DefenseLLM agents and tool use → Agent threats, guardrails and governance
  37. Information Theory and Statistical LearningDiffusion models → Diffusion foundations and sampling
  38. SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma SelectionEfficient LLM inference and serving → Speculative decoding
  39. MolmoAct2: Action Reasoning Models for Real-world DeploymentLLM reasoning → Spatial and embodied reasoning +1
  40. Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and HyperparametersDeep reinforcement learning methods → RL for robot locomotion and manipulation
  41. Semantic Risk-Aware Heuristic Planning for Robotic Navigation in Dynamic Environments: An LLM-Inspired ApproachLLM reasoning → Spatial and embodied reasoning
  42. Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone DetectionKnowledge distillation → Knowledge distillation for LLMs
  43. Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled DiffusionDiffusion models → Diffusion for compression and wireless
  44. TRACE: Temporal Reasoning over Context and Evidence for Activity Recognition in Smart HomesLLM reasoning → Spatial and embodied reasoning
  45. SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
  46. Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry DefenseLLM agents and tool use → Agent threats, guardrails and governance
  47. Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration TracesLLM agents and tool use → Reinforcement learning for LLM agents
  48. Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
  49. TOC-SR: Task-Optimal Compact diffusion for Image Super ResolutionDiffusion models → Inverse problems and image restoration
  50. Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data AugmentationVision-language-action models → Generalist VLA models and benchmarks
  51. Bolek: A Multimodal Language Model for Molecular ReasoningLLM reasoning → Clinical and biomedical applications
  52. AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven DevelopmentLLM agents and tool use → Software engineering coding agents
  53. Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model InferenceVision-language-action models → Efficient VLA inference and adaptation
  54. Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMsLLM reasoning → Multimodal reasoning
  55. Perceptual Flow Network for Visually Grounded ReasoningLLM reasoning → Multimodal reasoning +1
  56. Augmenting Interface Usability Heuristics for Reliable Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  57. ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization ModelingLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Scientific Domain Knowledge Improves Vision-Language Fundus ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  59. Federated Reinforcement Learning for Efficient Mobile Crowdsensing under Incomplete InformationDeep reinforcement learning methods → RL for energy, networks and operations
  60. Executor-Side Progressive Risk-Gated Actuation for Agentic AI in Wireless Supervisory ControlLLM agents and tool use → Agentic AI for wireless networks
  61. Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  62. ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-ReviewLLM agents and tool use → Web, search, and research agents
  63. ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational PrimingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  64. Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoEMixture-of-experts → Multimodal MoE models
  65. AutoFocus: Uncertainty-Aware Active Visual Search for GUI GroundingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  66. Gradient-Gated DPO: Stabilizing Preference Optimization in Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  67. Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms RaceLLM agents and tool use → Social simulation and multi-agent debate
  68. Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  69. CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  70. Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
  71. Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling SequencesLLM agents and tool use → Agentic AI for wireless networks
  72. Stylistic Attribute Control in Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  73. VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language ModelsLLM safety and security → Watermarking generated content and models
  74. Recurrent Deep Reinforcement Learning for Chemotherapy Control under Partial ObservabilityDeep reinforcement learning methods → RL for clinical treatment and surgery
  75. Strategy-Aware Optimization Modeling with Reasoning LLMsLLM reasoning → Test-time compute and efficient thinking
  76. Sim-to-Real Transfer and Robustness Evaluation of Reinforcement Learning Control with Integrated Perception on an ASV for Floating Waste CaptureDeep reinforcement learning methods → RL for robot navigation and UAV control
  77. Beyond Specialization: Robust Reinforcement Learning Navigation via Procedural Map GeneratorsDeep reinforcement learning methods → RL for robot navigation and UAV control
  78. A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive MemoryLLM reasoning → Spatial and embodied reasoning
  79. Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical StudyRetrieval-augmented generation → Medical and biomedical RAG
  80. DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data AnalysisLLM agents and tool use → Financial trading and forecasting agents
  81. Efficient Preference Poisoning Attack on Offline RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  82. From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard ModelRetrieval-augmented generation → Agentic RAG, agents and memory +1
  83. GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced IndexingLLM agents and tool use → Web, search, and research agents
  84. Shadow-Loom: Causal Reasoning over Graphical World Models of NarrativesWorld models → World models for language agents +1
  85. Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal AdjudicationLLM reasoning → Reasoning for agents, planning and code
  86. ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR ReconstructionDiffusion models → Inverse problems and image restoration
  87. When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  88. Middle-mile logistics through the lens of goal-conditioned reinforcement learningDeep reinforcement learning methods → RL for games and combinatorial optimization
  89. Position: How can Graphs Help Large Language Models?LLM reasoning → Knowledge- and tool-augmented reasoning
  90. Mtextsuperscript4Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor SegmentationMixture-of-experts → Medical and biomedical MoE
  91. Measuring AI Reasoning: A Guide for ResearchersLLM reasoning → Reasoning benchmarks and evaluation
  92. Mixture Prototype Flow Matching for Open-Set Supervised Anomaly DetectionDiffusion models → Flow matching, time series and science
  93. ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  94. Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based AdaptationDeep reinforcement learning methods → RL for energy, networks and operations
  95. Statistically-Lossless Quantization of Large Language ModelsEfficient LLM inference and serving → KV cache quantization
  96. HeavySkill: Heavy Thinking as the Inner Skill in Agentic HarnessLLM reasoning → Reasoning for agents, planning and code +1
  97. Verifiable Counterfactual Supervision for Process Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  98. A Low-Code Approach for the Automatic Personalization of Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  99. Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization SystemsLLM agents and tool use → Social simulation and multi-agent debate
  100. Enhancing Multimodal In-Context Learning via Inductive-Deductive ReasoningLLM reasoning → Multimodal reasoning +1
All 427
  1. Binary Rewards and Reinforcement Learning: Fundamental ChallengesLLM reasoning → Reinforcement learning for reasoning
  2. A Compound AI Agent for Conversational Grant DiscoveryLLM agents and tool use → Web, search, and research agents
  3. Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended GenerationLLM reasoning → Reasoning benchmarks and evaluation +1
  4. LLM-enabled Social AgentsLLM agents and tool use → Social simulation and multi-agent debate
  5. ANO: Robust Policy Optimization via Bounded, Redescending Gain FieldsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. SOTOPIA-TOM: Evaluating Privacy and Information Management in Multi-Agent Interaction with Theory of MindLLM agents and tool use → Agent threats, guardrails and governance
  7. A Meta Reinforcement Learning Approach to Goals-Based Wealth ManagementDeep reinforcement learning methods → Adversarial robustness and RL in finance
  8. Graph Federated Unlearning for Privacy PreservationLLM safety and security → Federated unlearning and poisoning
  9. Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher DecodingLLM reasoning → Prompting and chain-of-thought reasoning
  10. EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible SolutionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. CECOR: Correction-oriented synthetic data construction for factual error correctionSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  12. Towards Understanding Specification Gaming in Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  13. Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement LearningLLM reasoning → Diffusion reasoning and test-time scaling
  14. WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference OptimizationEfficient LLM inference and serving → KV cache quantization
  15. On the Privacy of LLMs: An Ablation StudyRetrieval-augmented generation → Privacy and security of RAG +1
  16. The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  17. PhysicianBench: Evaluating LLM Agents in Real-World EHR EnvironmentsLLM agents and tool use → Medical and scientific domain agents
  18. Generative Modeling with Orbit-Space Particle Flow MatchingDiffusion models → Flow matching, time series and science
  19. CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative DecodingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  20. Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified ScoreMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  21. CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  22. MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory WritingLLM agents and tool use → Agent memory systems
  23. SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model DistillationDiffusion models → Inverse problems and image restoration
  24. DurableUn: Quantization-Induced Recovery Attacks in Machine UnlearningLLM safety and security → Machine unlearning
  25. PipeMax: Enhancing Offline LLM Inference on Commodity GPU ServersEfficient LLM inference and serving → Serving systems and request scheduling
  26. Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  27. T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  28. Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese TextLLM reasoning → Reasoning benchmarks and evaluation
  29. Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  31. DocSync: Agentic Documentation Maintenance via Critic-Guided ReflexionLLM agents and tool use → Software engineering coding agents
  32. AAFLOW: Scalable Patterns for Agentic AI WorkflowsLLM reasoning → Reasoning for agents, planning and code +1
  33. Combining Trained Models in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  34. SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic LockingDiffusion models → Image generation, text-to-image and editing
  35. From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  36. Soft-to-Hard Routing in Sparse Mixture-of-Experts ModelsMixture-of-experts → Expert routing strategies
  37. Reinforcement Learning Trained Observer Control for Bearings-Only TrackingDeep reinforcement learning methods → RL theory and sample complexity
  38. Adversarial Update-Based Federated Unlearning for Poisoned Model RecoveryLLM safety and security → Federated unlearning and poisoning
  39. Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance
  40. So Many Opinions, So Many LLMs: Comparing Large Language Models to Traditional Machine Learning for Open- Ended Survey Analysis
  41. ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
  42. SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
  43. Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars
  44. Liberating LLM Capabilities in Full-Duplex Speech Models
  45. Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
  46. AI-Driven Controlled Environment Agriculture as Resilient Infrastructure for U.S. Fresh-Produce Supply Chains
  47. Forecasting Medium-Horizon Alzheimer's Disease Progression: Residual Gap-Aware Transformers for 24-Month CDR-SB Change from ADNI Clinical and Biomarker Histories
  48. Noise2Params: Unification and Parameter Determination from Noise via a Probabilistic Event Camera Model
  49. SignMuon: Communication-Efficient Distributed Muon Optimization
  50. Elastic Spiking Transformers for Efficient Gesture Understanding
  51. Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov-Arnold Networks
  52. Augmented Equivariant Mesh Networks for Anatomical Segmentation
  53. Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count
  54. Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation
  55. Optimized Culprit Identification Using Mobilenet and Attention Mechanisms
  56. Digital Image Forgery Detection Using Transfer Learning
  57. parHSOM: A novel parallel Hierarchical Self-Organizing Map implementation
  58. MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing
  59. Advanced Tumor Segmentation in PET/CT Imaging: A Training Strategy Study with nnU-Net for AutoPET III
  60. WATCH: Wide-Area Archaeological Site Tracking for Change Detection
  61. LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
  62. Temporal-Decay Shapley: A Time-Aware Data Valuation Framework for Time-Series Data
  63. Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures
  64. Memory-Efficient EDA Denoising via Knowledge Distillation for Wearable IoT Under Severe Motion Artifacts and Underwater Conditions
  65. Resource Utilization of Differentiable Logic Gate Networks Deployed on FPGAs
  66. Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance
  67. cotomi Act: Learning to Automate Work by Watching You
  68. Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
  69. Beyond Activation Alignment: The Geometry of Neural Sensitivity
  70. MenuNet: A Strategy-Proof Mechanism for Matching Markets
  71. Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets
  72. From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry
  73. A Partition-Based Generating Function for Row-Convex Polyominoes
  74. Stop Automating Peer Review Without Rigorous Evaluation
  75. Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability
  76. Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning
  77. Enhancing AI-Based ECG Delineation with Deep Learning Denoising Techniques
  78. DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery
  79. Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting
  80. OCRR: A Benchmark for Online Correction Recovery under Distribution Shift
  81. Are you with me? A Framework for Detecting Mental Model Discrepancies in Task-Based Team Dialogues
  82. Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction
  83. Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls
  84. NucEval: A Robust Evaluation Framework for Nuclear Instance Segmentation
  85. Instance-Level Costs for Nuanced Classifier Evaluation
  86. Bayesian inference with sources of uncertainty: from confidence modelling to sparse estimation
  87. EMOVIS: Emotion-Optimized Image Processing
  88. PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization
  89. Benchmarking Local Language Models for Social Robots using Edge Devices
  90. Cascade Token Selection for Transformer Attention Acceleration
  91. Gated Subspace Inference for Transformer Acceleration
  92. Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter
  93. MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
  94. Programmatic Context Augmentation for LLM-based Symbolic Regression
  95. One Sequence to Segment Them All: Efficient Data Augmentation for CT and MRI Cross-Domain 3D Spine Segmentation
  96. When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift
  97. Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach
  98. Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification
  99. From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
  100. Adaptive Data Compression and Reconstruction for Memory-Bounded EEG Continual Learning
  101. Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings
  102. From Tool to Agent: How Worker Needs Reorganize Across the Agentic Roles of Workplace AI
  103. AdNGCL: Adaptive Negative Scheduling for Graph Contrastive Learning
  104. Refining Compositional Diffusion for Reliable Long-Horizon Planning
  105. The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
  106. Distributed Deep Variational Approach for Privacy-preserving Data Release
  107. Computing Thiele Rules on Interval Elections and their Generalizations
  108. OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
  109. From Information Geometry to Jet Substructure: A Triality of Cumulant Tensors, Energy Correlators, and Hypergraphs
  110. Dynamic Vine Copulas: Detecting and Quantifying Time-Varying Higher-Order Interactions
  111. Learning to Segment using Summary Statistics and Weak Supervision
  112. Approaching human parity in the quality of automated organoid image segmentation
  113. How Language Models Process Negation
  114. TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
  115. Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
  116. AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion
  117. Unsupervised Machine Learning for Detecting Structural Anomalies in European Regional Statistics
  118. Multi-fidelity surrogates for mechanics of composites: from co-kriging to multi-fidelity neural networks
  119. Laplacian Frequency Interaction Network for Rural Thematic Road Extraction
  120. Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions
  121. From Sensors to Insight: Rapid, Edge-to-Core Application Development for Sensor-Driven Applications
  122. Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring
  123. (POSTER) From Sensors to Insight: Rapid, Edge-to-Core Application Development for Sensor-Driven Applications
  124. A second-order method landing on the Stiefel manifold via Newtonunicodex2013Schulz iteration
  125. A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification
  126. VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
  127. HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems
  128. Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces
  129. First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
  130. The Bayesian Reflex: Online Learning as the Autonomic Nervous System of Modern and Future AI
  131. FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
  132. IConFace: Fine-Grained Identity Conditioning for Reference-Aware Face Restoration
  133. AIs and Humans with Agency
  134. Measuring Accuracy and Energy-to-Solution of Quantum Fine-Tuning of Foundational AI Models
  135. Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models
  136. FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework
  137. Static Analysis of Recursive SHACL
  138. HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar
  139. When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
  140. Fine-Grained Graph Generation through Latent Mixture Scheduling
  141. Linearizing Vision Transformer with Test-Time Training
  142. Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle
  143. U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
  144. FoR-Net: Focus-on-Regions Network for Semantic Segmentation
  145. Unified Map Prior Encoder for Mapping and Planning
  146. DynoSLAM: Dynamic SLAM with Generative Graph Neural Networks for Real-World Social Navigation
  147. Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
  148. Mitigating Misalignment Contagion by Steering with Implicit Traits
  149. Virtual Scanning for NSCLC Histology: Investigating the Discriminatory Power of Synthetic PET
  150. Triple Spectral Fusion for Sensor-based Human Activity Recognition
  151. Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation
  152. Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
  153. AI and Open-data Driven Scalable Solar Power Profiling
  154. SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training
  155. Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
  156. Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
  157. OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis
  158. mdok-style at SemEval-2026 Task 10: Finetuning LLMs for Conspiracy Detection
  159. An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
  160. Temporally Consistent Object 6D Pose Estimation for Robot Control
  161. SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT
  162. ProPACT: A Proactive AI-Driven Adaptive Collaborative Tutor for Pair Programming
  163. Robust and Fast Training via Per-Sample Clipping
  164. Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
  165. mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection
  166. Random-Effects Algorithm for Random Objects in Metric Spaces
  167. ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data
  168. Caliper-in-the-Loop: Black-Box Optimization for Hyperledger Fabric Performance Tuning
  169. MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
  170. Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models
  171. The Design and Composition of Structural Causal Decision Processes
  172. Online Generalised Predictive Coding
  173. The 2026 ACII Dyadic Conversations (DaiKon) Workshop & Challenge
  174. An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES
  175. AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs
  176. Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study
  177. AcademiClaw: When Students Set Challenges for AI Agents
  178. Biological Spatial Priors Regularize Foundation Model Representations for Cross-Site MSI Generalization in Colorectal Cancer
  179. Human Activity Recognition Method for Moderate Violence Detection
  180. Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective
  181. CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation
  182. Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
  183. ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
  184. Convolutional Neural Networks in Vis-NIR Chemometrics: From Contradiction to Conditional Design
  185. Mapping Discourse Reframing: A Multi-Layer Network Approach to Italian HPV Vaccine Discourse on X (2010-2024)
  186. Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective
  187. Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations
  188. Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval
  189. SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing
  190. Global-Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection
  191. TRACED: In vivo imaging of extracellular intrinsic diffusivity, tortuosity, cell size distribution and cell density in human glioma patients
  192. Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples
  193. Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach
  194. Gradient-Discrepancy Acquisition for Pool-Based Active Learning
  195. Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages
  196. Counterfactual Reasoning in Automated Planning
  197. SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
  198. Isotropic Fourier Neural Operators
  199. HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound
  200. Gradient Boosted Risk Scores
  201. Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions
  202. Representation learning from OCT images
  203. StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation
  204. Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation
  205. Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI
  206. On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
  207. StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k
  208. Automated In-the-Wild Data Collection for Continual AI Generated Image Detection
  209. Low-Latency Embedded Driver Monitoring System with a Multi-Task Neural Network
  210. TemPose-TF-ASF: Two-Stage Bidirectional Stroke Context Fusion for Badminton Stroke Classification
  211. Double Rectified Linear Unit-based Modular Semantics for Quantitative Bipolar Argumentation Framework
  212. Improving Model Safety by Targeted Error Correction
  213. Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
  214. Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems
  215. A Coupled Physics-Informed Neural Network for Greenhouse Climate State Reconstruction and Parameter Identification under Sparse Sensor Measurements
  216. MooD: Perception-Enhanced Efficient Affective Image Editing via Continuous Valence-Arousal Modeling
  217. Evaluating Tabular Representation Learning for Network Intrusion Detection
  218. MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC
  219. A Novel Preprocessing-Driven Approach to Remaining Useful Life (RUL) Prediction Using Temporal Convolutional Networks (TCN)
  220. Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis
  221. A multilingual hallucination benchmark: MultiWikiQHalluA
  222. Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks
  223. Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation
  224. Efficient Temporal Datalog Materialisation for Composite Event Recognition
  225. Multispectral Blind Image Super-Resolution for Standing Dead Tree Segmentation
  226. Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
  227. ATLAS: Article Tracking, Linking, and Analysis of Swedish Encyclopedias
  228. Black-box optimization of noisy functions with unknown smoothness
  229. Active multiple matrix completion with adaptive confidence sets
  230. Leveraging Argument Structure to Predict Content Hatefulness
  231. LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering
  232. Causal Software Engineering: A Vision and Roadmap
  233. Testing General Relativity Through Gravitational Wave Classification: A Convolutional Neural Network Framework
  234. PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention
  235. HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
  236. Anomaly-Preference Image Generation
  237. Multi-Rater Calibrated Segmentation Models
  238. Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning
  239. The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
  240. DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing
  241. Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks
  242. Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
  243. FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
  244. Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications
  245. Automatic Reflection Level Classification in Hungarian Student Essays
  246. The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
  247. FEAT: Fashion Editing and Try-On from Any Design
  248. Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval
  249. Entanglement is Half the Story: Post-Selection vs. Partial Traces
  250. UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation
  251. Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation
  252. Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
  253. Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning
  254. InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
  255. When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
  256. Predicting Post Virality with Temporal Cross-Attention over Trend Signals
  257. Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis
  258. ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
  259. MolViBench: Evaluating LLMs on Molecular Vibe Coding
  260. A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
  261. APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks
  262. FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training
  263. Improving Imbalanced Multi-Label Chest X-Ray Diagnosis via CBAM-Enhanced CNN Backbones
  264. Denoising data using convex relaxations
  265. When Attention Collapses: Residual Evidence Modeling for Compositional Inference
  266. Can Causal Discovery Algorithms Help in Generating Legal Arguments?
  267. Anon: Extrapolating Adaptivity Beyond SGD and Adam
  268. Open-access model for detecting openly dumped dispersed municipal solid waste from crowdsourced UAV imagery in Sub-Saharan Africa
  269. Differentiable Kernel Ridge Regression for Deep Learning Pipelines
  270. Structural Dilemmas and Developmental Pathways of Legal Argument Mining in the Era of Artificial Intelligence
  271. Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification
  272. A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets
  273. LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory
  274. Complexity Horizons of Compressed Models in Analog Circuit Analysis
  275. Beyond Known Objects: A Novel Framework for Open-Set Object Detection using Negative-Aware Norm
  276. Rethinking Electro-Optical Vision Foundation Models for Remote Sensing Retrieval: A Controlled Comparison with Generalist VFM
  277. Variational Matrix-Learning Fourier Networks for Parametric Multiphysics Surrogates
  278. Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations
  279. HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
  280. EdgeLPR: On the Deep Neural Network trade-off between Precision and Performance in LiDAR Place Recognition
  281. A Systematic Benchmark of Machine Transliteration Models for the Tajik-Farsi Language Pair: A Comparative Study from Rule-Based to Transformer Architectures
  282. Reliability-Oriented Multilingual Orthopedic Diagnosis: A Domain-Adaptive Modeling and a Conceptual Validation Framework
  283. Measuring Differences between Conditional Distributions using Kernel Embeddings
  284. An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection
  285. SpectraDINO: Modality-Conditioned Adaptation of RGB Vision Foundation Models Across Infrared Bands
  286. A Study of Belief Revision Postulates in Multi-Agent Systems (Extended Version)
  287. Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning
  288. Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography
  289. Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
  290. Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
  291. Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
  292. InfiltrNet: Dual-Branch CNN-Transformer Architecture for Brain Tumor Infiltration Risk Prediction
  293. Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization
  294. NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results
  295. Submodular Benchmark Selection
  296. MultiSense-Pneumo: A Multimodal Learning Framework for Pneumonia Screening in Resource-Constrained Settings
  297. 2D Stability Selection: Design Jittering for Doubly Stable Feature Selection
  298. Super-Resolution of Airborne Laser Scanning Point Clouds for Forest Inventory
  299. ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
  300. Trees and Graphs with Non Log-concave Dominating Set Sequence via AI Tools
  301. KANs need curvature: penalties for compositional smoothness
  302. RAFNet: Region-Aware Fusion Network for Pansharpening
  303. Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
  304. The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
  305. Intervention Complexity as a Canonical Reward and a Measure of Intelligence
  306. CLaC at SemEval-2026 Task 6: Response Clarity Detection in Political Discourse
  307. Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation
  308. Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution
  309. Cross-Polarization Fusion of VV AND VH SAR Observations for Improved Flood Mapping
  310. H3: A Healthcare Three-Hop Index for Physician Referral Network Prediction
  311. Projection-Free Transformers via Gaussian Kernel Attention
  312. Personalized Federated Learning for Gradient Alignment
  313. On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
  314. FLoRA: Fusion-Latent for Optical Reconstruction and Flood Area Segmentation via Cross-Modal Multi-Task Distillation Network
  315. Video Generation with Predictive Latents
  316. LUMINA: A Grid Foundation Model for Benchmarking AC Optimal Power Flow Surrogate Learning
  317. A Parameter-Free First-Order Algorithm for Non-Convex Optimization with tildemkern1mu O(ε-5/3) Global Rate
  318. Ultrasound Vision-Language Alignment via Contrastive Learning
  319. FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Training
  320. Context-Aware Wireless Token Communication via Joint Token Masking and Detection
  321. STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
  322. Statistical Consistency and Generalization of Contrastive Representation Learning
  323. Geometric and Spectral Alignment for Deep Neural Network II
  324. Detecting Adversarial Data via Provable Adversarial Noise Amplification
  325. Geometric and Spectral Alignment for Deep Neural Network I
  326. The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence
  327. Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting