mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 3 Apr 2026

381 papers

  1. OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone EnvironmentsLLM agents and tool use → GUI and mobile agents
  2. Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest RecommendationLLM reasoning → Multimodal reasoning +1
  3. ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling DialoguesLLM agents and tool use → Tool learning and function calling
  4. BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware CalibrationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language ModelsLLM reasoning → Reinforcement learning for reasoning
  6. TimelineReasoner: Advancing Timeline Summarization with Large Reasoning ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  7. Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. The Impact of LLM Self-Consistency and Reasoning Effort on Automated Scoring Accuracy and CostLLM reasoning → Mathematical reasoning
  9. Marginal-Contribution Policy Gradients under Filtered Feedback for Multi-Agent LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  10. Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM AdaptationLLM reasoning → Test-time compute and efficient thinking
  11. Measuring Representation Robustness in Large Language Models for GeometryLLM reasoning → Spatial and embodied reasoning
  12. The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers ReasonLLM reasoning → Reasoning benchmarks and evaluation
  13. MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM MidtrainingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RANLLM agents and tool use → Social simulation and multi-agent debate
  15. HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent DebateLLM agents and tool use → Social simulation and multi-agent debate
  16. NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network ConfigurationLLM agents and tool use → Software engineering coding agents
  17. Inside the Scaffold: A Source-Code Taxonomy of Coding Agent ArchitecturesLLM agents and tool use → Software engineering coding agents
  18. BioAlchemy: Distilling Biological Literature into Reasoning-Ready Reinforcement Learning Training DataLLM reasoning → Clinical and biomedical applications
  19. Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  20. VisionClaw: Always-On AI Agents through Smart GlassesLLM agents and tool use → Multimodal and embodied agents
  21. Large Language Models Align with the Human Brain during Creative ThinkingLLM reasoning → Reasoning benchmarks and evaluation
  22. The Tool Illusion: Rethinking Tool Use in Web AgentsLLM agents and tool use → Web, search, and research agents
  23. Physics-Constrained Adaptive Flow Matching for Climate DownscalingDiffusion models → Flow matching, time series and science
  24. Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-BenchRetrieval-augmented generation → RAG pipeline design and evaluation
  25. ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in PhotoshopDiffusion models → Image generation, text-to-image and editing
  26. MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder LatentsMechanistic interpretability → Sparse autoencoder training and evaluation
  27. Scaling Multi-agent Systems: A Smart Middleware for Improving Agent InteractionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  28. Inference-Path Optimization via Circuit Duplication in Frozen Visual Transformers for Marine Species ClassificationMechanistic interpretability → Interpreting vision and multimodal models
  29. Beauty in the Eye of AI: Aligning LLMs and Vision Models with Human Aesthetics in Network VisualizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  30. KiToke: Kernel-based Interval-aware Token Compression for Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  31. Generative AI for material design: A mechanics perspective from burgers to matterDiffusion models → Flow matching, time series and science
  32. Diffusion Policy with Bayesian Expert Selection for Active Multi-Target TrackingDiffusion models → Diffusion and flow policies for robotics
  33. Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom BehaviorLLM reasoning → Multimodal reasoning
  34. Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana ProLLM agents and tool use → Multimodal and embodied agents
  35. TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
  36. Learning Families of Fixed-Wing Aircraft Control Policies with Hypernetwork-Conditioned Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  37. CresOWLve: Benchmarking Creative Problem-Solving Over Real-World KnowledgeLLM reasoning → Reasoning benchmarks and evaluation
  38. ABTest: Behavior-Driven Testing for AI Coding AgentsLLM agents and tool use → Software engineering coding agents
  39. NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal ConditioningDiffusion models → Diffusion for compression and wireless
  40. Mixture-of-Experts in Remote Sensing: A SurveyMixture-of-experts → Vision mixture-of-experts
  41. CoME-VL: Scaling Complementary Multi-Encoder Vision-Language LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  42. VOSR: A Vision-Only Generative Model for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  43. Hierarchical Planning with Latent World ModelsWorld models → Latent predictive world models
  44. Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-HoardingLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. Learning the Signature of Memorization in Autoregressive Language ModelsLLM safety and security → Membership inference attacks
  46. From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull RequestsLLM agents and tool use → Software engineering coding agents
  47. Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive SummarizationKnowledge distillation → Knowledge distillation for LLMs
  48. The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model ScalingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  49. SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot PolicyDiffusion models → Diffusion and flow policies for robotics
  50. Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning ModelsLLM reasoning → Hallucination detection and mitigation +1
  51. Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented GenerationLLM reasoning → Reasoning benchmarks and evaluation +1
  52. Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  53. Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  54. InCoder-32B-Thinking: Industrial Code World Model for ThinkingLLM reasoning → Reasoning for agents, planning and code
  55. TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache SharingEfficient LLM inference and serving → Efficient reasoning and agent inference
  56. SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image SegmentationDiffusion models → Medical imaging and segmentation
  57. Self-Distilled RLVRKnowledge distillation → On-policy and self-distillation for LLMs
  58. An Independent Safety Evaluation of Kimi K2.5LLM agents and tool use → Agent threats, guardrails and governance +1
  59. Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
  60. Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  61. Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMsLLM safety and security → Machine unlearning
  62. Multi-Aspect Knowledge Distillation for Language Model with Low-rank FactorizationKnowledge distillation → Knowledge distillation for LLMs
  63. Co-Evolution of Policy and Internal Reward for Language AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  64. SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and HarnessesLLM agents and tool use → Agent skill learning and evolution
  65. Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill EcosystemsLLM agents and tool use → Agent threats, guardrails and governance
  66. Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASRLLM reasoning → Audio-language model reasoning
  67. MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  68. How Your Credentials Are Leaked by LLM Agent Skills: An Empirical StudyLLM agents and tool use → Agent threats, guardrails and governance
  69. Querying Structured Data Through Natural Language Using Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  70. JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token EfficiencyMixture-of-experts → MoE in reinforcement learning and robotics
  71. QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly DetectionLLM agents and tool use → Multimodal and embodied agents
  72. ARM: Advantage Reward Modeling for Long-Horizon ManipulationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  73. Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software EvolutionLLM agents and tool use → Software engineering coding agents
  74. Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  75. Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  76. Generating DDPM-based Samples from Tilted DistributionsDiffusion models → Diffusion foundations and sampling
  77. A Flow Matching Framework for Soft-Robot Inverse DynamicsDiffusion models → Diffusion and flow policies for robotics
  78. R2-Write: Reflection and Revision for Open-Ended Writing with Deep ReasoningLLM reasoning → Reinforcement learning for reasoning
  79. Mitigating Reward Hacking in RLHF via Advantage Sign RobustnessLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  80. Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM InferenceRetrieval-augmented generation → Generation and context integration +1
  81. Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive ExtrapolationDiffusion models → Video generation
  82. NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-NeuronsLLM reasoning → Reasoning benchmarks and evaluation
  83. InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information SeekingLLM agents and tool use → Web, search, and research agents
  84. FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  85. Visual Prototype Conditioned Focal Region Generation for UAV-Based Object DetectionDiffusion models → Image generation, text-to-image and editing
  86. Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLAVision-language-action models → Reasoning and chain-of-thought in VLA
  87. Collaborative Multi-Mode Pruning for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  88. LogicPoison: Logical Attacks on Graph Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  89. AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  90. Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and BiasLLM agents and tool use → Medical and scientific domain agents +1
  91. Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped RobotsWorld models → Humanoid and legged locomotion world models
  92. Toward an Artificial General Teacher: Procedural Geometry Data Generation and Visual Grounding with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  93. SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly DetectionMechanistic interpretability → Sparse autoencoder training and evaluation
  94. Token Warping Helps MLLMs Look from Nearby ViewpointsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  95. Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward CalibrationLLM agents and tool use → Reinforcement learning for LLM agents +1
  96. Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image SegmentationDiffusion models → Medical imaging and segmentation
  97. High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observationsDiffusion models → Flow matching, time series and science
  98. Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security AnalysisLLM agents and tool use → Agent threats, guardrails and governance
  99. ESL-Bench: An Event-Driven Synthetic Longitudinal Benchmark for Health AgentsLLM agents and tool use → Medical and scientific domain agents
  100. NavCrafter: Exploring 3D Scenes from a Single ImageDiffusion models → 3D, point cloud and scene generation
All 381
  1. Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time SelectionLLM reasoning → Prompting and chain-of-thought reasoning +1
  2. MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception ModelingDiffusion models → Video generation
  3. QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +2
  4. Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic SupervisionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  5. Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following TasksLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  6. CharTool: Tool-Integrated Visual Reasoning for Chart UnderstandingLLM reasoning → Multimodal reasoning
  7. LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion TransformersDiffusion models → Inverse problems and image restoration
  8. EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State DetectorsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  9. DynFOA: Generating First-Order Ambisonics with Conditional Diffusion for Dynamic and Acoustically Complex 360-Degree VideosDiffusion models → Audio, speech and music
  10. A Unified Perspective on Adversarial Membership Manipulation in Vision ModelsLLM safety and security → Membership inference attacks
  11. Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role ClarityLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  13. Random Is Hard to Beat: Active Selection in online DPO with Modern LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  14. Understanding Latent Diffusability via Fisher GeometryDiffusion models → Diffusion foundations and sampling
  15. Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM AgentsLLM agents and tool use → Agent memory systems
  16. DeltaLogic: Minimal Premise Edits Reveal Belief-Revision Failures in Logical Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  17. Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear MDPsDeep reinforcement learning methods → Safe and constrained RL
  18. GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement LearningLLM agents and tool use → Software engineering coding agents
  19. Generative Frontiers: Why Evaluation Matters for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  20. FluxMoE: Decoupling Expert Residency for High-Performance MoE ServingMixture-of-experts → Efficient MoE training and inference systems
  21. ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +2
  22. V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative ViewsLLM reasoning → Chain-of-thought reasoning for driving +3
  23. Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky HierarchyLLM reasoning → Reasoning benchmarks and evaluation
  24. Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic ConstraintsLLM reasoning → Reasoning benchmarks and evaluation
  25. DocShield: Towards AI Document Safety via Evidence-Grounded Agentic ReasoningLLM agents and tool use → Multimodal and embodied agents
  26. Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts MechanismMixture-of-experts → Vision mixture-of-experts
  27. Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMsLLM reasoning → Spatial and embodied reasoning +2
  28. MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials ExplorationLLM agents and tool use → Medical and scientific domain agents
  29. Beyond Semantic Manipulation: Token-Space Attacks on Reward ModelsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  30. Finding Belief Geometries with Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  31. Human Thinking under Plural LLM Assistance: Mathematical Problem Solving and Open-Ended WritingLLM reasoning → Reasoning benchmarks and evaluation
  32. Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  33. Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM AlignmentsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  34. Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  35. Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing CommitsLLM agents and tool use → Software engineering coding agents
  37. Generalization Limits of Reinforcement Learning AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  38. Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic FrameworkRetrieval-augmented generation → RAG pipeline design and evaluation
  39. AXELRAM: Quantize Once, Never DequantizeEfficient LLM inference and serving → KV cache quantization
  40. Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web AgentsLLM agents and tool use → Agent threats, guardrails and governance
  41. Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-JudgeLLM reasoning → Reinforcement learning for reasoning +1
  42. AutoVerifier: An Agentic Automated Verification Framework Using Large Language ModelsLLM agents and tool use → Web, search, and research agents
  43. Steerable but Not Decodable: Function Vectors Operate Beyond the Logit LensMechanistic interpretability → Activation steering methods
  44. Moondream Segmentation: From Words to MasksMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. Confidence Calibration in Large Language Models
  46. Beyond Compliance: How AI Could Help Creative Writers by Refusing Them
  47. Can AI be a moral victim? The role of moral patiency and ownership perceptions in ethical judgments of using AI-generated content
  48. Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories
  49. A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework
  50. Sociodemographic Biases in Educational Counselling by Large Language Models
  51. Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
  52. Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing
  53. BiTA: Bidirectional Gated Recurrent Unit-Transformer Aggregator in a Temporal Graph Network Framework for Alert Prediction in Computer Networks
  54. A General Framework for Generative Self-supervised Learning in Non-invasive Estimation of Physiological Parameters Using Photoplethysmography
  55. KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
  56. The Spectral Lifecycle of Transformer Training: Transient Compression Waves, Persistent Spectral Gradients, and the Q/K--V Asymmetry
  57. An Intelligent Fault Diagnosis Method for General Aviation Aircraft Based on Multi-Fidelity Digital Twin and FMEA Knowledge Enhancement
  58. Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
  59. Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG
  60. Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution
  61. Disentangled Dual-Branch Graph Learning for Conversational Emotion Recognition
  62. Bridging scalp and intracranial EEG in BCI via pretrained neural representations and geometric constraint embedding
  63. Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy
  64. PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data
  65. The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure
  66. R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inference
  67. Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part III -- Gradient Descent, Neural Plasticity, and the Emergence of Deep Intelligence
  68. Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
  69. PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space
  70. Learning Nonlinear Regime Transitions via Semi-Parametric State-Space Models
  71. Identification and Inference in Nonlinear Dynamic Network Models
  72. CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
  73. The Planetary Cost of AI Acceleration, Part II: The 10th Planetary Boundary and the 6.5-Year Countdown
  74. Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive Creativity
  75. ActionNex: A Virtual Outage Manager for Cloud Computing
  76. Multimodal Urban Tree Detection from Satellite and Street-Level Imagery via Annotation-Efficient Deep Learning Strategies
  77. Nonparametric Regression Discontinuity Designs with Survival Outcomes
  78. The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading
  79. Resource-Conscious Modeling for Next- Day Discharge Prediction Using Clinical Notes
  80. Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generation
  81. Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations
  82. RAIN-FIT: Learning of Fitting Surfaces and Noise Distribution from Large Data Sets
  83. Improving Feasibility via Fast Autoencoder-Based Projections
  84. Contextual Control without Memory Growth in a Context-Switching Task
  85. Investigating Data Interventions for Subgroup Fairness: An ICU Case Study
  86. Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition
  87. Evolutionary Search for Automated Design of Uncertainty Quantification Methods
  88. Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
  89. Recurrent Quantum Feature Maps for Reservoir Computing
  90. Super Agents and Confounders: Influence of surrounding agents on vehicle trajectory prediction
  91. SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
  92. Earth Embeddings Reveal Diverse Urban Signals from Space
  93. RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
  94. Neural Operators for Multi-Task Control and Adaptation
  95. Measuring LLM Trust Allocation Across Conflicting Software Artifacts
  96. Olmo Hybrid: From Theory to Practice and Back
  97. Agile Story-Point Estimation: Is RAG a Better Way to Go?
  98. Adversarial Robustness of Deep State Space Models for Forecasting
  99. Automated Segmentation and Tracking of Group Housed Pigs Using Foundation Models
  100. AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems
  101. Towards a theory of morphology-driven marking in the lexicon: The case of the state
  102. Zero-Shot Quantization via Weight-Space Arithmetic
  103. Adaptive Threshold-Driven Continuous Greedy Method for Scalable Submodular Optimization
  104. Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval
  105. DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping
  106. Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation
  107. SDVDiag: Using Context-Aware Causality Mining for the Diagnosis of Connected Vehicle Functions
  108. Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
  109. Hume's Representational Conditions for Causal Judgment: What Bayesian Formalization Abstracted Away
  110. Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation
  111. ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matching
  112. Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies
  113. The limits of bio-molecular modeling with large language models : a cross-scale evaluation
  114. Evaluating Artificial Intelligence Through a Christian Understanding of Human Flourishing
  115. From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models
  116. YOLOv11 Demystified: A Practical Guide to High-Performance Object Detection
  117. Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks
  118. Towards Intelligent Energy Security: A Unified Spatio-Temporal and Graph Learning Framework for Scalable Electricity Theft Detection in Smart Grids
  119. Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fields
  120. Learning Additively Compositional Latent Actions for Embodied AI
  121. Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction
  122. The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics Research
  123. Significance and Stability Analysis of Genotype-Environment Interaction using GxEStat
  124. NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure
  125. Apparent Age Estimation: Challenges and Outcomes
  126. Bridging the Dimensionality Gap: A Taxonomy and Survey of 2D Vision Model Adaptation for 3D Analysis
  127. Composer Vector: Style-steering Symbolic Music Generation in a Latent Space
  128. AICCE: AI Driven Compliance Checker Engine
  129. Enhancing Robustness of Federated Learning via Server Learning
  130. HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis
  131. Power one sequential tests exist for weakly compact mathscr P against mathscr Pc
  132. BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
  133. ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
  134. A Tsetlin Machine-driven Intrusion Detection System for Next-Generation IoMT Security
  135. PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction
  136. The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report
  137. Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis
  138. Gradient Boosting within a Single Attention Layer
  139. Reflective Context Learning: Studying the Optimization Primitives of Context Space
  140. PRISM: LLM-Guided Semantic Clustering for High-Precision Topics
  141. SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection
  142. EffiMiniVLM: A Compact Dual-Encoder Regression Framework
  143. BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation
  144. CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator
  145. DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
  146. HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of 1H MR spectroscopic imaging
  147. Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
  148. Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
  149. Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
  150. StoryScope: Investigating idiosyncrasies in AI fiction
  151. AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study
  152. A Systematic Security Evaluation of OpenClaw and Its Variants
  153. Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
  154. SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization
  155. ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality
  156. AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs
  157. A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification
  158. On Data-Driven Koopman Representations of Nonlinear Delay Differential Equations
  159. Automatic Textbook Formalization
  160. SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
  161. Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks
  162. Gram-MMD: A Texture-Aware Metric for Image Realism Assessment
  163. Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks
  164. Verbalizing LLMs' assumptions to explain and control sycophancy
  165. MECO: A Multimodal Dataset for Emotion and Cognitive Understanding in Older Adults
  166. STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
  167. Analyzing Healthcare Interoperability Vulnerabilities: Formal Modeling and Graph-Theoretic Approach
  168. GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model
  169. Learning Contractive Integral Operators with Fredholm Integral Neural Operators
  170. Comparing the Impact of Pedagogy-Informed Custom and General-Purpose GAI Chatbots on Students' Science Problem-Solving Processes and Performance Using Heterogeneous Interaction Network Analysis
  171. User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation
  172. Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition
  173. Rendering Multi-Human and Multi-Object with 3D Gaussian Splatting
  174. A penalised Saito functional for heuristic search of free line arrangements
  175. FedSQ: Optimized Weight Averaging via Fixed Gating
  176. Self-Optimizing Multi-Agent Systems for Deep Research
  177. Effect of Input Resolution on Retinal Vessel Segmentation Performance: An Empirical Study Across Five Datasets
  178. Exploring Motion-Language Alignment for Text-driven Motion Generation
  179. Inversion-Free Natural Gradient Descent on Riemannian Manifolds
  180. How Annotation Trains Annotators: Competence Development in Social Influence Recognition
  181. CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation
  182. Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
  183. Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in Female Mouse White Adipose Tissue After 37 Days of Microgravity: First AI/ML Analysis of NASA OSD-970
  184. MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion
  185. Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection
  186. PolyReal: A Benchmark for Real-World Polymer Science Workflows
  187. BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving
  188. Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms
  189. A Multi-head-based architecture for effective morphological tagging in Russian with open dictionary
  190. Efficient Logistic Regression with Mixture of Sigmoids
  191. Scalable Mean-Variance Portfolio Optimization via Subspace Embeddings and GPU-Friendly Nesterov-Accelerated Projected Gradient
  192. GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
  193. Split and Conquer Partial Deepfake Speech
  194. Corporations Constitute Intelligence
  195. Analysis of Optimality of Large Language Models on Planning Problems
  196. SentiAvatar: Towards Expressive and Interactive Digital Humans
  197. UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting
  198. BioUNER: A Benchmark Dataset for Clinical Urdu Named Entity Recognition
  199. RayMamba: Ray-Aligned Serialization for Long-Range 3D Object Detection
  200. Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation
  201. EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment
  202. Progressive Video Condensation with MLLM Agent for Long-form Video Understanding
  203. Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions
  204. Lipschitz bounds for integral kernels
  205. High-dimensional Many-to-many-to-many Mediation Analysis
  206. Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision
  207. One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
  208. InstructTable: Improving Table Structure Recognition Through Instructions
  209. Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework
  210. Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting
  211. HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
  212. LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
  213. EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
  214. LLM+Graph@VLDB'2025 Workshop Summary
  215. A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos
  216. Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule
  217. HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints
  218. Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations
  219. Deformation-based In-Context Learning for Point Cloud Understanding
  220. Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices
  221. Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces
  222. GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
  223. STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
  224. ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs
  225. CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification
  226. PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis
  227. UNICA: A Unified Neural Framework for Controllable 3D Avatars
  228. Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guarantees
  229. CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization
  230. Disrupting Cognitive Passivity: Rethinking AI-Assisted Data Literacy through Cognitive Alignment
  231. When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
  232. Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark
  233. Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models
  234. Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals
  235. InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging
  236. STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation
  237. DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
  238. Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation
  239. Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks
  240. Task-Guided Prompting for Unified Remote Sensing Image Restoration
  241. Cross Event Detection and Topic Evolution Mining in cross events for Man Made Disasters in Social Media Streams
  242. Quotient-Based Posterior Analysis for Euclidean Latent Space Models
  243. State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference
  244. THOM: Generating Physically Plausible Hand-Object Meshes From Text
  245. IndustryCode: A Benchmark for Industry Code Generation
  246. MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
  247. Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts
  248. A Rapid Instrument Exchange System for Humanoid Robots in Minimally Invasive Surgery
  249. LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks
  250. VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping
  251. XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis
  252. Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
  253. Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis
  254. Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network
  255. A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation
  256. SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models
  257. Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
  258. Transfer Learning for Meta-analysis Under Covariate Shift
  259. Drift-Resilient Temporal Priors for Visual Tracking
  260. Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
  261. Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
  262. Revealing the Learning Dynamics of Long-Context Continual Pre-training
  263. GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
  264. Speaking of Language: Reflections on Metalanguage Research in NLP
  265. Conditional Sampling via Wasserstein Autoencoders and Triangular Transport
  266. Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles
  267. Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training
  268. Analytic Drift Resister for Non-Exemplar Continual Graph Learning
  269. Toys that listen, talk, and play: Understanding Children's Sensemaking and Interactions with AI Toys
  270. Smart Transfer: Leveraging Vision Foundation Model for Rapid Building Damage Mapping with Post-Earthquake VHR Imagery
  271. Wavelength-multiplexed massively parallel diffractive optical information storage and image projection
  272. OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing
  273. Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis
  274. Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems
  275. Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transport
  276. Do Audio-Visual Large Language Models Really See and Hear?
  277. Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signals
  278. WGFINNs: Weak formulation-based GENERIC formalism informed neural networks
  279. LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
  280. Explorable Proofs: Making Written Proofs Explorable by Grounding Them in Formal Representations
  281. An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages