mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 22 May 2026

433 papers

  1. AutoFOAM: The Self-Refining Autonomous OpenFOAM AgentLLM agents and tool use → Web, search, and research agents
  2. Fence: Specialized SLM Guardrails for LLM ApplicationsLLM safety and security → Safety alignment, refusal and guardrails
  3. Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed FirmsLLM reasoning → Reasoning for agents, planning and code
  4. Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM SystemsLLM reasoning → Reasoning for agents, planning and code +1
  5. State commitment learning: training language models to distinguish computation from memoryLLM reasoning → Test-time compute and efficient thinking
  6. From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  7. BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM QuantizationMixture-of-experts → MoE large language models
  8. TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation ModelsKnowledge distillation → Knowledge distillation for LLMs
  9. PrismFlow: Residual Dynamics for Flow Matching in Time-Series GenerationDiffusion models → Flow matching, time series and science
  10. Emergent Semantic Representations in World Models through Physical Interaction without Linguistic SupervisionWorld models → World models for language agents
  11. Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recommendation: A 37,000-Run AuditRetrieval-augmented generation → RAG for recommendation
  12. MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue AgentsLLM agents and tool use → Agent memory systems
  13. FD-RAG: Federated Dual-System Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  14. Tackling Multimodal Learning Challenges with Mixture-of-Expert: A SurveyMixture-of-experts → Multimodal MoE models
  15. VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding AgentsLLM agents and tool use → Software engineering coding agents
  16. TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  17. Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  18. ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding SessionsLLM agents and tool use → Social simulation and multi-agent debate
  19. Safety-Oriented Routing Analysis of Mixtral MoE Under Benign and Harmful PromptsMixture-of-experts → Expert routing strategies +1
  20. Attested Tool-Server Admission: A Security Extension to the Model Context ProtocolLLM agents and tool use → Agent threats, guardrails and governance
  21. Deep-Research Agents Can Be Poisoned via User-Generated ContentLLM agents and tool use → Agent threats, guardrails and governance
  22. Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial WorkflowsLLM agents and tool use → Medical and scientific domain agents
  23. QUEST: Training Frontier Deep Research Agents with Fully Synthetic TasksLLM agents and tool use → Web, search, and research agents
  24. Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  25. Afford-VLA: Action-Aligned Visual Planning via Internalized AffordanceLLM reasoning → Spatial and embodied reasoning +1
  26. When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing TradeoffsLLM agents and tool use → Reinforcement learning for LLM agents
  27. A Sober Look at Agentic Misalignment in Automated WorkflowsLLM agents and tool use → Software engineering coding agents
  28. Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion GeneralizationDiffusion models → Diffusion foundations and sampling
  29. Extracting Training Data from Diffusion Language Models via InfillingDiffusion models → Discrete and text diffusion
  30. Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  31. Neuro-Inspired Inverse Learning for Planning and ControlOffline RL and imitation learning from data → Inverse reinforcement learning
  32. HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  33. Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game DevelopmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI AgentsLLM agents and tool use → Software engineering coding agents
  35. EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative InteractionsLLM agents and tool use → Software engineering coding agents
  36. D2-V2X: Depth-Driven Cooperative V2X Reasoning for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  37. Not All Transitions Matter: Evidence from PPODeep reinforcement learning methods → Deep RL algorithms and representations
  38. When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  39. fMRI-Diffusion: Generating fMRI Time Series Via a Temporal Transformer Diffusion Model for Major Depressive Disorder DiagnosisDiffusion models → Medical imaging and segmentation
  40. Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete DiffusionDiffusion models → Discrete and text diffusion
  41. Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained TransformersMechanistic interpretability → Circuits and mechanistic analysis
  42. Feature Lottery? A Bifurcation Theory of Concept EmergenceMechanistic interpretability → Circuits and mechanistic analysis
  43. SkillOpt: Executive Strategy for Self-Evolving Agent SkillsLLM agents and tool use → Agent skill learning and evolution +1
  44. PiD: Fast and High-Resolution Latent Decoding with Pixel DiffusionDiffusion models → Diffusion foundations and sampling
  45. SPACENUM: Revisiting Spatial Numerical Understanding in VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  46. ETCHR: Editing To Clarify and Harness ReasoningLLM reasoning → Multimodal reasoning +1
  47. Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE ModelsMixture-of-experts → Expert routing strategies
  48. PGT: Procedurally Generated Tasks for improving visual grounding in MLLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  49. LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video GenerationDiffusion models → Video generation
  50. Training-Free Looped TransformersMixture-of-experts → Expert routing strategies
  51. Strong Teacher Not Needed? On Distillation in LLM PretrainingKnowledge distillation → Knowledge distillation for LLMs
  52. Point Tracking Improves World Action ModelsWorld models → Embodied and robot world models
  53. Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger InsertionOffline RL and imitation learning from data → Robot manipulation imitation learning
  54. Learning a Particle Dynamics Model with Real-world VideosWorld models → Latent predictive world models
  55. Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  56. Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace AlignmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  57. Agentic Proving for Program VerificationLLM agents and tool use → Educational agents and math problem solving
  58. PhotoFlow: Agentic 3D Virtual Photography MissionsLLM agents and tool use → Multimodal and embodied agents
  59. HyperParallel-MoE: Multi-Core Interleaved Scheduling for Fast MoE Training on Ascend NPUsMixture-of-experts → Efficient MoE training and inference systems
  60. Direct Dynamic Retargeting for Humanoid Imitation Learning from VideosOffline RL and imitation learning from data → Real-world robot offline RL
  61. LLM-driven design of physics-constrained constitutive models: two agents are better than oneLLM agents and tool use → Medical and scientific domain agents
  62. MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly DetectionLLM agents and tool use → Agent threats, guardrails and governance
  63. CRONOS: Benchmarking Counterfactual Physical Consistency in Video ModelsWorld models → Video-generation world models and simulators
  64. ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  65. OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  66. CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image PerceptionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  67. One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game AgentsLLM agents and tool use → Social simulation and multi-agent debate
  68. Learning Kernel-Based MDPs from Episodic Preferential FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  69. Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in TamarinDeep reinforcement learning methods → Adversarial robustness and RL in finance
  70. Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG SystemsRetrieval-augmented generation → Generation and context integration
  71. DiLaDiff: Distilled Latent-Augmented Diffusion for Language ModelingDiffusion models → Discrete and text diffusion
  72. GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow ScenesDiffusion models → 3D, point cloud and scene generation
  73. When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and KwaiLLM safety and security → Safety alignment, refusal and guardrails
  74. Safety, Liveness, and Fairness in Quantitative Argumentation DialoguesLLM reasoning → Reasoning for agents, planning and code
  75. Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. Understanding Goal Generalisation in Sequential Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  77. Goal-Conditioned Agents that Learn Everything All at OnceDeep reinforcement learning methods → Deep RL algorithms and representations
  78. Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching ModelsDiffusion models → Diffusion and flow policies for robotics +1
  79. B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring SegmentationLLM agents and tool use → Multimodal and embodied agents +1
  80. Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question AnsweringRetrieval-augmented generation → Legal and financial RAG
  81. EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  82. CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit TestLLM reasoning → Reinforcement learning for reasoning +1
  83. Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear AttentionEfficient LLM inference and serving → Visual token pruning in multimodal models
  84. DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video GenerationDiffusion models → Video generation
  85. Socially fluent AI decouples conversational signals from source identity in online interactionLLM agents and tool use → Social simulation and multi-agent debate
  86. Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  87. When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  88. What Linear Probes Miss: Multi-View Probing for Weight-Space LearningMechanistic interpretability → Circuits and mechanistic analysis
  89. RS2AD-LiDAR: End-to-End Autonomous Driving LiDAR Data Generation from Roadside Sensor ObservationsEnd-to-end autonomous driving → End-to-end system architecture
  90. Hybrid Quantum-Classical Corrective Diffusion Modeling for Meteorological DownscalingDiffusion models → Flow matching, time series and science
  91. Convex Compositional Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  92. Every Component Is a Lookup: One Linear Graph for Interaction, Composition and AttributionMechanistic interpretability → Circuits and mechanistic analysis
  93. AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving SystemEfficient LLM inference and serving → Serving systems and request scheduling
  94. Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation SignalsLLM reasoning → Reinforcement learning for reasoning
  95. From Correctness to Preference: A Framework for Personalized Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  96. VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and EstimationDiffusion models → Flow matching, time series and science
  97. Curriculum reinforcement learning with measurable task representation learningDeep reinforcement learning methods → Deep RL algorithms and representations
  98. Score-Based One-step MeanFlow Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  99. Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete DiffusionDiffusion models → Diffusion foundations and sampling
  100. SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World ModelsWorld models → Video-generation world models and simulators
All 433
  1. CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMsLLM reasoning → Hallucination detection and mitigation +1
  2. Sparse Compositional Flow Matching by geometric assembly from motion primitivesDiffusion models → Diffusion and flow policies for robotics
  3. Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference LearningLLM agents and tool use → Medical and scientific domain agents
  4. Convergence Without Understanding: When Language Models Agree on Representations but Disagree on ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  5. DART: Semantic Recoverability for Structured Tool AgentsLLM agents and tool use → Tool learning and function calling
  6. General Hazard DetectionLLM reasoning → Chain-of-thought reasoning for driving
  7. Parallel Context Compaction for Long-Horizon LLM Agent ServingLLM agents and tool use → Agent memory systems
  8. NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM InferenceMixture-of-experts → Efficient MoE training and inference systems
  9. Reinforcement Learning for Graph Generation under a Hard Assortativity ConstraintDeep reinforcement learning methods → RL for games and combinatorial optimization
  10. Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  11. Self-Refining Topology Optimization via an LLM-Based Multi-Agent FrameworkLLM agents and tool use → Multimodal and embodied agents
  12. ChainFlow-VLA: Causal Flow Planning with Vision-Language ModelsLLM reasoning → Chain-of-thought reasoning for driving +2
  13. A Simple Plug-in for Improving Eviction-Based KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  14. Convex Optimization for Alignment and Preference Learning on a Single GPULLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. GENSTRAT: Toward a Science of Strategic Reasoning in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  16. WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model AgentsWorld models → World model security and GUI agents
  17. Foundation Protocol: A Coordination Layer for Agentic SocietyLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question AnsweringLLM reasoning → Multimodal reasoning +1
  19. FastKernels: Benchmarking GPU Kernel Generation in ProductionLLM agents and tool use → Software engineering coding agents
  20. Adaptive Mass-Segmented KV Compression for Long-Context ReasoningLLM reasoning → Test-time compute and efficient thinking
  21. Prompt Overflow: What the Guardrail Inspects Is Not What the Model InfersLLM safety and security → Safety alignment, refusal and guardrails
  22. Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video EditingDiffusion models → Video generation
  23. GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging SequencesMixture-of-experts → Medical and biomedical MoE
  24. Pure Exploration for a Good Policy in Reinforcement Learning with Bandit FeedbackDeep reinforcement learning methods → RL theory and sample complexity
  25. Redrawing the AI Map: A Theory of Accountability Boundaries in Agentic EcosystemsLLM agents and tool use → Agent threats, guardrails and governance
  26. DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  27. Robust LLM Watermarking with Minimal Semantic Distortion for IP ProtectionLLM safety and security → Watermarking generated content and models
  28. Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning BenchmarksLLM reasoning → Test-time compute and efficient thinking
  29. Autonomous Frontier-Based Exploration with VLM GuidanceLLM reasoning → Spatial and embodied reasoning
  30. Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous DrivingVision-language-action models → VLA for autonomous driving +2
  31. Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  32. Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case RobustnessDeep reinforcement learning methods → RL theory and sample complexity
  33. Classical State Preparation for Variational Quantum Algorithms via Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  34. π0-EqM: Equilibrium Matching for Closed-Loop Vision-Language-Action ControlVision-language-action models → Efficient VLA inference and adaptation +1
  35. CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly DetectionLLM reasoning → Chain-of-thought reasoning for driving
  36. Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs
  37. Beyond Sentiment: Comparing Traditional NLP and LLM-Based Multi-Dimensional Analysis for Political News Evaluation
  38. TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking
  39. Game AI Not Fun? A Scoping Review and Meta-Analysis on the Differences in Enjoyment between Human and Computer Opponents
  40. A Systematic Survey on Image Description Techniques for STEM Domains
  41. PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs
  42. Information Discernment in Large Language Models
  43. The Economics of Autonomy: Real-Time Risk Indexing for Insurable AI-Driven 6G Systems
  44. What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?
  45. Divergent Recommendations, Convergent Diagnoses: Cross-Provider Failure-Mode Convergence in AI Commercial Recommendation
  46. A Multi-Layer AI Framework for Information Landscape Analysis
  47. Estimating Learners' Skill Acquisition Without Temporal Information
  48. Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection
  49. Understanding Privacy by Formalizing It
  50. CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora
  51. Synthetic Resonance: A Framework for Growth-Oriented Human-AI Relationships
  52. Multi-Fidelity Learning with Shallow Recurrent Decoders for Multi-Physics Applications
  53. A differentiable machine learning small-angle X-ray scattering analysis framework for structure elucidation of lipid nanoparticles
  54. Automatic-Differentiation-Enabled Finite Element Model Updating: Learning Constitutive Neural Networks from Structural Deformation Data
  55. An accurate nucleic acid-small molecule docking framework via geometric deep learning with large-scale pretraining
  56. TGSD: Topology-Guided State-Space Diffusion Framework for EEG Spatial Super-Resolution
  57. Making Brain-Computer Interfaces More Secure
  58. Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent
  59. Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning
  60. SentimentLens: Reconciling Sentiment and Ratings via Dual-Modality in the Hospitality Sector
  61. Hoeffding Concept Bottleneck Models with Applications to Overhead Images
  62. DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions
  63. Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems
  64. Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications
  65. Improved Belief-Attention in Vision Task
  66. DefocusTrackerAI -- A Generalized Framework for the Automatic Detection of Defocused Particle Images
  67. Representation Alignment Rests on Linear Structure
  68. Balancing Multimodal Learning through Label Space Reshaping
  69. Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
  70. The Cognitive Categorical Transformer: Category-Theoretic Inductive Biases for Language Modeling
  71. A Unified Structured Query Understanding Framework for Industrial Semantic Search
  72. Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline
  73. RE-TRIANGLE: Does TRIANGLE Enable Multimodal Alignment Beyond Cosine Similarity in Retrieval?
  74. When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference
  75. Heterogeneous Multi-Agent Modeling for Measurement and Network Analysis of the Data Service Market
  76. Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking
  77. Neural Bayesian Sequential Routing
  78. Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains
  79. AssetGen: Deployable 3D Asset Generation at Interactive Speed
  80. Enhancing Reliability in LLM-Based Secure Code Generation
  81. LLMs Show No Signs Of Individuated Metacognition
  82. An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods
  83. Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering
  84. When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification
  85. Private Adaptive Covariance Estimation via Gaussian Graphical Models
  86. Concept Drift Adaptation Using Self-Supervised and Reinforcement Learning In Android Malware Detection
  87. Rubato: Transcribing Piano Music with Timestamps
  88. Memory, Roughness, and Information Persistence in Financial Markets: A Structural Approach to Volatility Forecasting
  89. Fourier Feature Pyramids for Physics-Informed Neural Networks
  90. A lift for input-convex neural net training
  91. Plume Segmentation from MethaneSAT with Cross-Sensor Transfer Learning and Physics-Informed Postprocessing
  92. DRInQ: Evaluating Conversational Implicature with Controlled Context Variation
  93. An Interactive Paradigm for Deep Research
  94. Optimizing Digital Therapeutic Interventions: Online Learning under Endogenous Adherence
  95. CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Representation and Retrieval
  96. Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
  97. PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets
  98. Improving Labeling Consistency with Detailed Constitutional Definitions and AI-Driven Evaluation
  99. MEDAL: Manifold Embedding Distillation via Autoencoder Learning
  100. GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer
  101. Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Intelligence
  102. Toward Enactive Artificial Intelligence
  103. How Well Do Models Follow Their Constitutions?
  104. Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks
  105. Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
  106. Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction
  107. Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation
  108. Characterizing the Representational Capacity of Neural Processes
  109. Incorporating Deep Learning Design in Database Queries
  110. Radiuma: A Unified Zero-Code Executable Graphical Workflow Generator for Reproducible and Shareable Medical Image Analysis and Machine Learning
  111. Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering
  112. Music Transcription with (Almost) No Supervision
  113. AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery
  114. Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment
  115. Loki: Representation over Architecture for Diffusion-Based Portrait Animation
  116. EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages
  117. PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection
  118. Learning dynamical systems with biochemically informed neural ordinary differential equations
  119. Inference Time Context Sparsity: Illusion or Opportunity?
  120. CUNY at CLPsych 2026: A Pipeline Approach to Classification and Summarization of Mental Health Changes
  121. Knowledge Graph Modulated Deep Learning for Limited-Sample Clinical Data Analysis
  122. EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound
  123. An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation
  124. EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
  125. MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
  126. Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries
  127. Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination
  128. ImPartial: Multi-channel Whole-Cell Segmentation using Partial Annotations
  129. SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
  130. COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing
  131. Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
  132. MASt3R-Nav: WayPixel Navigation in Relative 3D Maps
  133. Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference
  134. The Time is Here for Just-in-Time Systems: Challenges and Opportunities
  135. Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
  136. TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
  137. LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability
  138. Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines
  139. WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation
  140. Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
  141. Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs
  142. Seeing Inside the Storm: Improving Nowcasting by Integrating Meteorological Drivers
  143. Distance-Aware Joint Spatio-Temporal Graph Contrastive Learning for Major Depressive Disorder Diagnosis
  144. Federated Learning over Human-Body Communication for On-Body Edge Intelligence: A Survey, Taxonomy, and BODYFED-HBC Scheduling Vignette
  145. Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning
  146. Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions
  147. Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
  148. Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing
  149. Geo-Align: Video Generation Alignment via Metric Geometry Reward
  150. LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
  151. From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
  152. From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain
  153. Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
  154. Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
  155. HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
  156. GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
  157. CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces
  158. Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
  159. On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
  160. Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
  161. Vision Transformers Need Better Token Interaction
  162. Human Decision-Making with Persuasive and Narrative LLM Explanations
  163. Leveraging Foundation Models for Causal Generative Modeling
  164. Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries
  165. MuellerPT: Decomposition Driven Pretraining for Dense Learning in Mueller Polarimetry
  166. Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval
  167. It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt
  168. Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence
  169. Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
  170. Advanced AI Service Provisioning in O-RAN through LLM Engine Integration
  171. Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based model
  172. The physics of AI weather models
  173. Machine learning applied to emerald gemstone grading: framework proposal and creation of a public dataset
  174. A Novel Approach for the Counting of Wood Logs Using cGANs and Image Processing Techniques
  175. SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrieval
  176. Approaching I/O-optimality for Approximate Attention
  177. Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox
  178. Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series
  179. Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
  180. Optimal Dimension-Free Sampling for Regularized Classification
  181. NLG Evaluation: Past, Present, Future
  182. Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach
  183. A graph-based analysis of semantic types and coercion in contextualized word embeddings
  184. Learning Dynamic Stability Landscapes in Synchronization Networks
  185. Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks
  186. Graph-based Complexity Forecasts in UK En Route Airspace Using Relevant Aircraft Interactions
  187. Optimization of randomized neural networks for transfer operator approximation
  188. Relevant Walk Search for Explaining Graph Neural Networks
  189. RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video
  190. OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
  191. Detecting Drunk Driving Using Off-the-Shelf Smartwatches
  192. Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
  193. ExpOS: Explainable Open-Surgery Skills Assessment Using 3D Hand Reconstruction
  194. How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework
  195. Learning Through Noise: Why Subliminal Learning Works and When It Fails
  196. Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks
  197. DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection
  198. Gaussian Mixture Copula Processes for Irregular Time Series
  199. DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
  200. How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness
  201. Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection
  202. EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation
  203. Preisach Attention: A Hysteretic Model of Sequential Memory
  204. Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
  205. Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
  206. Solving the Aircraft Disassembly Scheduling Problem
  207. Asymmetric Scaling Laws from Sparse Features
  208. Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
  209. How Many Training Samples Are Needed for the Inverse Kinematics Solutions by Artificial Neural Networks
  210. Calibration-Informative Region Selection for Online LiDAR--Camera Calibration in Agricultural Environments
  211. HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
  212. CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem
  213. MARS: Magnitude-Aware Rank Statistics
  214. ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
  215. PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA
  216. Is Dimensionality a Barrier for Retrieval Models?
  217. Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos
  218. RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs
  219. When One Point Is Not Enough: Addressing Ambiguous Instances in Dimensionality Reduction by Splitting
  220. Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity
  221. PixIE: Prompted Pixel-Space Low-Light Image Enhancement
  222. ComPose: When to Trust Hands for Object Pose Tracking
  223. VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
  224. Learning partially observed systems with neural Hamiltonian ordinary differential equations
  225. DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
  226. MDS-DETR: DETR with Masked Duplicate Suppressor
  227. VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
  228. Multimodal Distribution Matching for Vision-Language Dataset Distillation
  229. PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction
  230. Non-normal spectral signatures of instability in neural network training dynamics
  231. Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension
  232. Rethinking Transfer Learning for Industrial Inspection: DINOv3 vs. ImageNet Pretraining Across RGB and X-ray Tasks
  233. CBANet: A Compact Attention-Based CNN-BiLSTM Network for Aggressive Driving Event Detection
  234. Learning Individual Dynamics from Sparse Cross-Sectional Snapshots
  235. S3GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
  236. Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
  237. AI Assurance: A Comprehensive Testing Strategy for Enterprise AI Systems
  238. One-Forcing: Towards Stable One-Step Autoregressive Video Generation
  239. ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning
  240. Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance
  241. Commutator-Induced Uncertainty in VAEs
  242. AI Security Research Should Better Incentivize Defense Research
  243. Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
  244. SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
  245. Onsager-Machlup Posterior Transport for Deep Gaussian Processes
  246. FAST-ME: Foundation-aware Adaptive Stopping for Motion Estimation for Efficient IoT Video Analysis
  247. Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating
  248. Hinge Regression Trees and HRT-Boost: Newton-Optimized Oblique Learning for Compact Tabular Models
  249. Naturalistic measure of social norms alignment
  250. An Open-Source Training Dataset for Foundation Models for Black-box Optimization
  251. Articulatory strategy as a source of variation in acoustic vowel dynamics
  252. EquiSumm : A Gender Bias-Aware Framework for Inclusive Tweet Summarization
  253. Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
  254. Online Hand Gesture Recognition Using 3D Convolutional Neural Networks
  255. Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
  256. Joint Target-Less Intrinsic and Extrinsic Camera-LiDAR Calibration using Deep Point Correspondences
  257. Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization
  258. Selective Ambulance Dispatch Under Contextual Travel-Time Uncertainty
  259. Instance-Optimal Estimation with Multiple LLM Judges on a Budget
  260. Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization
  261. Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
  262. XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
  263. Cultural Adaptation in Large Language Models for Political Discourse
  264. Emotion Recognition in Sign Language Conversation
  265. GFSR: Geometric Fidelity and Spatial Refinement for Reliable Lane Detection
  266. ClimateChat-300K: A Multi-Modal Facebook Dataset for Understanding Diverse Perspectives in Climate Communication
  267. AraHopeCorpus: Annotation Guidelines and Dataset for Hope Speech in Arabic Social Media Crisis Discourse
  268. Enhancing Blood Cells Classification using Hybrid Quantum Neural Networks
  269. Efficient Learned Image Compression without Entropy Coding
  270. SpinFlow: A Physics-Informed Spin Field Framework for Traffic Phase Inference and Transition Detection
  271. Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trustworthy AI Systems
  272. Accelerating ground state search of spatial photonic Ising machines with genetic-simulated annealing hybrid algorithm
  273. Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition
  274. LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
  275. Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
  276. DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection
  277. When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming
  278. U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025
  279. When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
  280. EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
  281. Coupled Training with Privileged Information and Unlabeled Data
  282. Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
  283. 6G Communication Networks Enabling Embodied Agents: Architecture and Prototype
  284. Designing Benchmarks for Knowledge Work
  285. Multi-Gate Residuals
  286. Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
  287. Learning-Augmented Online Scheduling with Parsimonious Preemption
  288. CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
  289. Enhancing Deep Neural Network Reliability with Refinement and Calibration
  290. Accelerating Divisible Load Processing Through Machine Learning: A Practical Framework for Large-Scale Workloads
  291. SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
  292. Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks
  293. RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
  294. Self-supervised Adversarial Purification for Graph Neural Networks
  295. StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
  296. Convex Low-resource Accent-Robust Language Detection in Speech Recognition
  297. Assessing Predictive Models for Fairness Based on Activity-Space Patterns
  298. Beyond Normal References: Discriminative Few-Shot Anomaly Detection
  299. Entropy Equivalence Testing
  300. PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows
  301. AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
  302. Lipschitz Optimization for Formal Verification of Homographies
  303. Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
  304. Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
  305. CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening
  306. Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
  307. Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
  308. Empirical Bayes Conformal Prediction for Vision and Language Models
  309. IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction
  310. Self-Improving In-Context Learning
  311. Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
  312. LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement
  313. Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
  314. PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
  315. Semantic-Aware Guided Drone Exploration for Language-Conditioned 3D Indoor Mapping
  316. Generative AI and the Reorganization of Labor Demand
  317. What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
  318. Any-Dimensional Invariant Universality
  319. Convex Hybrid Modeling: An Operator-Based Approach
  320. When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening
  321. As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
  322. Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
  323. SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection
  324. VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
  325. CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection
  326. STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding
  327. Archimedean Copula Inference via Taylor-Mode AD
  328. When Determinants Are Not Enough: Private Rare Switching
  329. Defining AI Fatigue in Academic Contexts: Dimensions, Indicators, and a Stage-Based Model Using Grounded Theory
  330. Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking
  331. Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift
  332. Inconsistency-aware Multimodal Schr"odinger Bridge for Deepfake Localization
  333. Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems