mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 23 Jul 2026

390 papers

  1. Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  2. Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUsRetrieval-augmented generation → RAG pipeline design and evaluation +1
  3. World models of environment, agent and joint agent-environment systemsWorld models → World models for language agents +1
  4. AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  5. Spectral Dynamics of Semantic Drift in Clinical Multi-Agent Language Model NetworksLLM agents and tool use → Medical and scientific domain agents
  6. LeAct: Learning to Reason from Expert ActionsLLM reasoning → Test-time compute and efficient thinking
  7. ToolGuardian: Declarative Security for AI Agent-Tool InteractionsLLM agents and tool use → Agent threats, guardrails and governance
  8. How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull RequestsLLM agents and tool use → Software engineering coding agents
  9. Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified DefenseLLM agents and tool use → Agent threats, guardrails and governance
  10. Adversarial Prompts for Acceptance Collapse in Speculative DecodingEfficient LLM inference and serving → Speculative decoding +1
  11. Agentic Evaluation of Copyright Law ComplianceLLM agents and tool use → Social simulation and multi-agent debate
  12. QLPO: Quadrant-weighted Sampling for Length-aware Policy OptimizationLLM reasoning → Test-time compute and efficient thinking
  13. Bespoke Visual Assistance: What and How do Blind and Low-Vision People Create with Agentic Programming?LLM agents and tool use → GUI and mobile agents
  14. Co-design of LLM-based preference agents: participation may drive overtrustLLM agents and tool use → Social simulation and multi-agent debate +1
  15. What AI Red-Team Evaluations Can and Cannot ProveLLM safety and security → Prompt injection and agent security
  16. Addressing the Orchestration Gap in Generalist Robots via Physical AgencyVision-language-action models → Failure recovery and robustness
  17. Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency ConstraintsLLM reasoning → Multimodal reasoning +1
  18. Learning What Matters: Supervising Global Context Pruning with Causal Evidence SetsKnowledge distillation → On-policy and self-distillation for LLMs
  19. Persistent Computational State: A Session-Centric Runtime for Generative World ModelsWorld models → Video-generation world models and simulators
  20. Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRARetrieval-augmented generation → Agentic RAG, agents and memory +1
  21. Output Format x Model Identity: Interaction Effects in Single-Round Coding Agent PerformanceLLM agents and tool use → Software engineering coding agents
  22. Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and ImagesMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  23. 3D-Aware VLMs with Implicit and Explicit GeometriesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. Streaming Multi-Agent Autoregressive Diffusion Model with World State RegistersWorld models → Video-generation world models and simulators +1
  25. Inference-Time Scaling of Diffusion Models via Progressive Seed PruningLLM reasoning → Diffusion reasoning and test-time scaling +1
  26. Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  27. Visual Contrastive Self-DistillationKnowledge distillation → Multimodal distillation
  28. SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video GenerationDiffusion models → Video generation
  29. MIRROR: Learning from the Other View for Multi-Modal ReasoningLLM reasoning → Multimodal reasoning +1
  30. X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy AlignmentLLM reasoning → Audio-language model reasoning +1
  31. Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token ContextEfficient LLM inference and serving → Speculative decoding
  32. ElasticTTT: Prior-Preserving Test-Time Tuning for Video EditingDiffusion models → Video generation
  33. GS-Agent: Creating 4D Physical Worlds With Generative SimulationLLM agents and tool use → Multimodal and embodied agents
  34. Diffusion Language Model for RecommendationDiffusion models → Diffusion recommenders
  35. Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent MediationLLM agents and tool use → Agent threats, guardrails and governance
  36. Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  37. Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture ProblemsLLM agents and tool use → Agent memory systems
  38. Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  39. Compact Latent Coordination for Autonomous Vehicles at Unsignalized IntersectionsEnd-to-end autonomous driving → Cooperative and V2X driving +1
  40. Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasksLLM agents and tool use → Web, search, and research agents
  41. Thinkink: 2D Spatial Ink-native Interaction with LLMsLLM reasoning → Multimodal reasoning
  42. AREX: Towards a Recursively Self-Improving Agent for Deep ResearchLLM agents and tool use → Web, search, and research agents +1
  43. Test-Time Scaling via Error LocalizationLLM reasoning → Test-time compute and efficient thinking
  44. KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  45. Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  46. Context-weighted Discrete Flow MatchingDiffusion models → Flow matching, time series and science
  47. PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  48. Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via PrologLLM reasoning → Reasoning benchmarks and evaluation +1
  49. A Diffusion-Model Subpopulation Digital Twin for Mobile Health Deployment: A Case Study on the HeartSteps InterventionDiffusion models → Diffusion foundations and sampling
  50. When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time ModerationLLM reasoning → Reasoning for agents, planning and code +1
  51. Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score EntropyDiffusion models → Diffusion foundations and sampling
  52. FedAgentKE: Federated Semantic Knowledge Evolution for Heterogeneous AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  53. Emergent Misalignment Recruits a Pre-existing Persona SubspaceLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  54. Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class UnlearningLLM safety and security → Machine unlearning
  55. SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  56. SlerpFlow: Spherical Trajectory Correction for Rectified Flow InversionDiffusion models → Image generation, text-to-image and editing
  57. GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAGRetrieval-augmented generation → Agentic RAG, agents and memory +1
  58. Expert Behavior Prior Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  59. Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM UnlearningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  60. Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMsLLM reasoning → Test-time compute and efficient thinking
  61. The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What WorksLLM reasoning → Reinforcement learning for reasoning +1
  62. pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory DevelopmentLLM agents and tool use → Financial trading and forecasting agents
  63. Progressive Cramming: Reliable Token Compression and What It RevealsEfficient LLM inference and serving → Visual token pruning in multimodal models
  64. ICAE-Bench: Evaluating Coding Agents as Interactive Project BuildersLLM agents and tool use → Software engineering coding agents
  65. Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and ForecastingDiffusion models → Flow matching, time series and science
  66. Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic SystemsLLM reasoning → Reasoning benchmarks and evaluation
  67. Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive ApplicationsLLM safety and security → Safety alignment, refusal and guardrails
  68. Out of Sight, Still in Mind: Token Compression for Omni-LLMsEfficient LLM inference and serving → Audio and omni-modal token compression
  69. Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-ResolutionDiffusion models → Inverse problems and image restoration
  70. CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQAMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  71. V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling FailureLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  72. Deep Reinforcement Learning for Adaptive Gain Tuning in Control of Teleoperation Manipulators with Joint Flexibility and Time-Varying DelaysDeep reinforcement learning methods → RL for robot locomotion and manipulation
  73. Approximate Quantum State Preparation Through Proximal Policy OptimizationDeep reinforcement learning methods → Quantum reinforcement learning
  74. Relative Value LearningDeep reinforcement learning methods → RL theory and sample complexity
  75. TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
  76. AttriMem: Attribution-Guided Process Feedback for Agent Memory ConstructionLLM agents and tool use → Agent memory systems
  77. HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  78. Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  79. C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  80. PrefReward: Learning User Preference Matrix for Personalized Text GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  81. Do Pathology Vision-Language Models Truly See Pathology?Multimodal LLMs / vision-language models → Medical vision-language models
  82. GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  83. Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUsDiffusion models → Audio, speech and music
  84. GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image InterpretationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  85. ProCap: Prominence-guided Object Rectification for Faithful and Comprehensive Video CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  86. EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent SpecializationLLM reasoning → Audio-language model reasoning +3
  87. Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence MemoryState-space sequence models (S4, Mamba) → Core SSM architectures for language
  88. Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  89. Sparse Concept Channels in Frozen 3D CT Vision EncodersMultimodal LLMs / vision-language models → Medical vision-language models
  90. HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous DrivingWorld models → World models for autonomous driving +2
  91. GuardianAgentBench: Where Agents Fail and How to Guard ThemLLM agents and tool use → Agent threats, guardrails and governance
  92. Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge IntelligenceMixture-of-experts → Multimodal MoE models +1
  93. Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous RacingDeep reinforcement learning methods → RL for autonomous driving and traffic
  94. Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding AgentsLLM agents and tool use → Agent memory systems
  95. From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric DataMixture-of-experts → MoE for time series and graphs
  96. The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess ReasoningLLM reasoning → Test-time compute and efficient thinking
  97. Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and AttentionDiffusion models → Video generation
  98. Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular ScratchpadLLM reasoning → Clinical and biomedical applications
  99. SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information IntegrationLLM agents and tool use → Web, search, and research agents
  100. MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-TransferDiffusion models → Image generation, text-to-image and editing
All 390
  1. Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model FinetuningDiffusion models → Diffusion foundations and sampling
  2. Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task ConstructionLLM agents and tool use → Software engineering coding agents
  3. RadioTrace: Transmitter-Aware Diffusion for Radio Map Estimation without Deployment-Time Fine-TuningDiffusion models → Diffusion for compression and wireless
  4. Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel GenerationLLM reasoning → Reinforcement learning for reasoning
  5. Learning to recover: Adaptive local branching with reinforcement learning for log-truck routing and scheduling under disruptionsDeep reinforcement learning methods → RL for autonomous driving and traffic
  6. Is Deep Research Reliable? Misleading Knowledge Induces False ConclusionsLLM agents and tool use → Web, search, and research agents
  7. ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?LLM reasoning → Spatial and embodied reasoning +1
  8. Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout GenerationLLM agents and tool use → Multimodal and embodied agents
  9. Code Monitor Red Teaming for Public-Test-Passing CodeLLM safety and security → Prompt injection and agent security
  10. Offline RL with Hierarchical Action ChunkingOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  11. REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  12. Auditing Provenance Sensitivity in LLM Agent Action SelectionLLM agents and tool use → Agent threats, guardrails and governance
  13. Robust Asynchronous Q-Learning under Reward and State Corruption via BatchingDeep reinforcement learning methods → RL theory and sample complexity
  14. The Geometry of Personality: Activation Steering with Jungian Cognitive FunctionsMechanistic interpretability → Activation steering methods
  15. TatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar
  16. Recursive Language Models Generalize Out of Domain
  17. Reviser: Writing and Editing Text with Autoregressive Cursor Actions
  18. Support Thresholds, Not Algorithms, Limit Rare-Association Recovery in Co-Purchase Networks
  19. Fine-Tuning Models for Biomedical Relation Extraction
  20. LEO Satellite Internet of Things: Architecture, Technology, and On-Orbit Verification
  21. Benchmarking Large Language Models for Biomedical Relation Extraction
  22. A Lifecycle Cost Analysis of Smart-Contract-Coordinated Federated Learning Marketplaces
  23. CriticGen: Generation-Aware Evaluation as Actionable Feedback
  24. Distributional Validity of a Korean Synthetic Persona Panel: Evidence From the Korea Media Panel Survey
  25. STAGEET: Stage-wise Typed Edit Tagging for Grammatical Error Correction with Arabic as a Case Study
  26. DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling
  27. Optimizing Energy Efficiency and Grid Stability via Public EV Charging Flexibility
  28. Transit Destination Inference from Tap-In-Only Bus Smart-Card Data: A Hierarchical Bayesian Approach
  29. A Multi-Cohort Validation of Censoring-Aware Conformal Lower Predictive Bounds for Pathology Survival Models
  30. Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study
  31. Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations
  32. Improving Rare Medication Recommendation with Counterfactual Data Augmentation and Large Language Models
  33. An Integrated Deep Learning and Statistical Framework for Whole-Network Gene--Environment Association with Leaf Vascular Architecture
  34. TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure
  35. DRC-Aid: Design-Rule Correction via Agentic Framework utilizing Inference-Time Large Language Models
  36. Benchmarking LLMs for Verilog Design Flows
  37. Hierarchical Grading in Large Language Models
  38. pyALDIC: A Python Implementation of Augmented Lagrangian Digital Image Correlation with a GUI, Adaptive Meshing, and Mask-Aware Subset Splitting
  39. Real-time Reconstruction of Human Visual Perception from fMRI
  40. Beyond Error-vs-Discard Characteristic: Toward Stable and Reliable Evaluation for Face Image Quality Assessment
  41. Commitment To Cooperation With Self-Negotiated Contracts
  42. Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention
  43. Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence
  44. Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
  45. AI-generated Images Challenge Visual Trust in High-risk Scenarios
  46. QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
  47. When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies
  48. Scaling Laws for Classical Machine Learning on Tabular Data: A Benchmark Study
  49. Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
  50. EviDAG: Auditable Causal DAG Authoring with Biomedical Literature
  51. Searching the Space of Feed-Forward Neural-Network Weight-Update Rules with Fixed Depth Symbolic Regression
  52. SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes
  53. Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering
  54. Distributional Determinantal Point Process for Repulsive Clustering of Distributions
  55. Simulation-Based Empirical Bayes
  56. Quantifying Political Partisanship for Cross-Platform Analyses
  57. Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet
  58. Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification
  59. Reconstruction of Enhanced Causal Omnidirectional Network (RECON)
  60. A Graph-Based Control Interface for Traffic Signals on Heterogeneous Road Networks
  61. Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA
  62. Probing Speaker Identity Sensitivity in Audio Deepfake Detectors
  63. Longitudinal Random Forests for Sparse and Irregular Response Trajectories
  64. Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness
  65. Natural Invariant Measures for Chaotic Game Dynamics: Finding Order in Chaos
  66. A Dual Path Framework with Hotspot Guided Fusion for Three Dimensional CT to PET Synthesis in Head and Neck Cancer
  67. Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling
  68. What Happens to Accuracy When Photo Lineups Contain Non-Mated Rank-One Images From Large Galleries?
  69. Risk-Routed Implicit Boundary Refinement for Robust Ultrasound Image Segmentation
  70. From Seasonality to Semantics: Benchmarking a Hybrid Probabilistic Forecasting System for Roadblocks in Bolivia
  71. MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery
  72. Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms
  73. Graph-Theoretic Neural Network Fragmentation with Covariant Direct Molecular Force Learning: Enabling Coupled-Cluster Accuracy AIMD for Fluxional Systems
  74. AI-Integrated Scientific Inquiry: A Practice-Centered Vision for Science Education
  75. Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection
  76. Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders
  77. Smart predict-then-robustly-optimize
  78. Reliability-Aware Bayesian Optimization of 1310 nm PCSELs with FDTD Verification
  79. Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks
  80. Encoding orders and trees in real-valued functions
  81. Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing
  82. Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting
  83. Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection
  84. Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery
  85. RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory
  86. Priors learned from legacy reconstructions inherit undetectable overconfidence
  87. A Defense of the Quadratic Model
  88. An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
  89. Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On
  90. Explainable quantum-compressed machine learning for complex fluid flows
  91. Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark
  92. CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting
  93. Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy
  94. Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields
  95. Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration
  96. Neural Feature Governance: Extending Atom Prevalence
  97. Ordered Action Tokens for Visuomotor Policy Learning
  98. Physically Constrained Federated Additive Models for O-RAN SLA-Risk Prediction
  99. Unified Video Dense Prediction from Disjoint Data
  100. Expanding Flow Maps
  101. Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation
  102. GraphVid: Interactive Graph-Controllable Video Generation
  103. Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension n≥ 4
  104. Synthetic data generation framework for quality control automation in gravure printing
  105. Self-Supervised Learning of Structured Dynamics from Videos
  106. Surprisal Theory is Tautological (without Rational Grounding)
  107. Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
  108. MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
  109. Scene Parameter Saliency via Differentiable Light Transport
  110. EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides
  111. Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
  112. OpenForgeRL: Train Harness-native Agents in Any Environment
  113. Neural solutions of coupled ghost and gluon Dyson--Schwinger equations in Landau gauge
  114. The Boundaries of Automation: A Theory of Persistent Human Participation
  115. UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging
  116. Towards Robust Iris Recognition Through Occlusion Identification and Conditional Diffusion-Based Reconstruction
  117. Zero-Flow Two-Sample Tests
  118. Optimal use of a black-box learner in semiparametric estimation
  119. DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages
  120. From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs
  121. Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving
  122. Improved lower bounds for the Shannon capacity of odd cycles
  123. Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
  124. Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
  125. What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
  126. Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
  127. Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
  128. Error Certificates for KV-Cache Eviction via Randomized Design
  129. Future Rendering neq Future Surface: A Benchmark and Dataset for Dynamic Surface Reconstruction Beyond the Observed Window
  130. CLUIE: Clustering-Aware Recurrent Propagation with Local Structural Compensation for Underwater Image Enhancement
  131. Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
  132. SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation
  133. GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
  134. RUMBA: Russian User Memory Benchmark
  135. When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs
  136. Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility
  137. DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV
  138. Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
  139. Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
  140. Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
  141. An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations
  142. Learning and Structurally Validating Simulation Scenario Continuations in Dynamic Graph Systems
  143. Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach
  144. GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition
  145. Logical Regression for Planning with Axioms
  146. QSTAR: Quantum Selective Transfer with Adaptive Routing
  147. Cautious optimism for deep parameterized quantum circuits
  148. Cycle-Consistent and Uncertainty-Aware Neural Surrogates for Tokamak Edge Plasmas
  149. Anti-Periodic Positional Encoding: M"obius Boundary Conditions Make In-Context Retrieval Reliable
  150. MemTools: A Unified Research Framework for Interoperable Agent Memory
  151. MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning
  152. VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
  153. Word meaning co-determines vowel-inherent spectral change. A corpus-based investigation of conversational Mandarin
  154. Multimodal Pretraining for Generalizable EEG Representation Learning
  155. Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
  156. DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation
  157. ASTRA-Net: Anatomy-Specific Transfer and Representation Alignment for Drug-Induced Sleep Endoscopy Segmentation
  158. Incremental Optimal Assignment for Real-Time Crowd Tracking
  159. Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
  160. SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning
  161. How Much Can a LoRA Adapter Memorize? Measuring Adapter Capacity in Bits
  162. Quality-Aware Multimodal Fusion Reveals Implicit Identity in Valence-Arousal Features
  163. Regulating autonomous and agentic AI
  164. M3-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
  165. Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable
  166. Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin
  167. From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics
  168. Cryptographically verifiable authorization for autonomous AI agents: a falsifiable hypothesis and proof of concept
  169. PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
  170. Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study
  171. AI Assistants Overassist
  172. An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models
  173. Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
  174. news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling
  175. HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors
  176. A Unified Moral-Value Dataset for Instruction Tuning
  177. A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset
  178. Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform
  179. BasketEvent: Understanding Who Did What and When in Basketball Videos
  180. Filter Learning for Subgraphs: Algebras and Performance Risk Bounds
  181. slang.gr as a Large-Scale Crowdsourced Resource for Non-Standard Greek
  182. Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks
  183. Stokes-Informed Diffusion for Robust Linear Polarization Estimation
  184. Logic Programming Semantics for Causal Processes
  185. T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video
  186. DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
  187. Learning-based Seam Correspondence Reconstruction in Sewing Patterns
  188. Explainable Belief Harmonization under Dynamic Epistemic Partitions
  189. Explainability Framework for Policy-Aware Autonomous Agents
  190. How Rules Represent Causal Knowledge: Causal Modeling with Probabilistic Logic Programming
  191. A New Well-Supported Semantics for Description Logic Programs
  192. Hybrid MKNF with Classical Negation in the Rule Component
  193. Bound-Founded Semantics for Answer Set Programming with Difference Constraints: Preliminary Report
  194. Towards a Certifying Grounder
  195. Declarative Problem Solving in UAM Strategic Deconfliction
  196. Case study: solving P-99 with LPTP and an LLM
  197. Chessdb: A framework for working with large chess game datasets
  198. Animation, Verification and Visualisation of Prolog Transition Systems with ProB
  199. Encoding Event-B Proof Rules in Prolog: An Interactive Sequent Prover for ProB
  200. Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy
  201. Identifying Good Rules for Efficient SAT Encodings of Single-Constant Multiplication Using Machine Learning
  202. Case study: proving sqrt(2) irrational with LPTP and an LLM
  203. Do emulated quantum circuits change what CNNs look at? Performance and explainability comparison in medical image classification
  204. Explaining Weather Bulletins via ILP
  205. Representative Sets in Propositional Abduction
  206. Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines
  207. Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference
  208. SafeStep: AI-powered Travel Assistance for Elderly People with Frailty or Dementia
  209. One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies
  210. DTIF: Robust Loop Closure Detection via Delaunay Triangle Topology in Complex Forests
  211. Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation
  212. Demographically-Informed Heat-Mortality Risk Curves via Risk Graph Neural Networks
  213. Hardware-Software Co-Design for Float16 On-Device Training on RISC-V Single-Core
  214. Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents
  215. The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results
  216. GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
  217. Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation
  218. Smooth Neural Point Processes via B-Splines
  219. A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
  220. Training Large Language Models for Self-Explanation Faithfulness
  221. Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance
  222. CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
  223. Automatic knot selection in smooth additive models
  224. Nipping the Butterfly Effect in the Bud: Self-Output Fine-Tuning for Autoregressive Weather Prediction
  225. The RealDefocus Benchmark for Defocus Deblurring
  226. VibeVoice-ASR-BitNet Technical Report
  227. Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers
  228. Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
  229. TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects
  230. From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
  231. Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification
  232. QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
  233. MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement
  234. Achieving Text-based Person Retrieval with Any Granularity
  235. Sample-Efficient Learning from Agent Experience
  236. HyperImageNet: A Large-Scale High-Spatial Resolution Hyperspectral Imagery Classification Benchmark
  237. Regularized Optimization on Grassmann Manifold: Theory, Algorithm and Applications
  238. Spectral-Spatial Synergistic Guided Network for Hyperspectral Salient Object Detection
  239. GroupVideo: Multi-Identity Customized Text-to-Video Generation
  240. WAT3R: Feedforward Underwater 3D Reconstruction
  241. HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices
  242. CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages
  243. Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers
  244. Explainable Deepfake Detection Challenge
  245. Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
  246. AUCH-Net: Action Unit-Based Consistency-Aware Hypergraph Network for Cross-Domain Few-Shot Facial Expression Recognition
  247. ADABORD: a novel AdaBoost approach for ordinal classification
  248. Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
  249. Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imaging
  250. Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval
  251. Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks
  252. FSB-Net: Frequency-Spatial Boundary Network for Brain Stroke Lesion Segmentation in Non-Contrast CT
  253. Best-of-Evidence: Best-of-N Selection under Partial Verification
  254. RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection
  255. From a Word-Level Dictionary to Sentence-Level Semantics: Multilingual Grievance Labelling with Contextual Models
  256. An Analytically Trained Variational Surrogate for Quantum Phase Estimation on NISQ Hardware
  257. Interaction Dynamics Modeling and Predictive Control for Safe Steerable Catheter--Tissue Interaction
  258. Clustered Edge Intelligence: Beyond Just Convergence of Edge Computing and AI
  259. Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development
  260. Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluation and Structural Authority
  261. Scientific exploration, collaboration and labor division in the large language model era
  262. FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
  263. OPOD: On-Policy Omni Distillation
  264. Traceable Scholarship: Page Anchors and Ariadne's Thread for Humanistic Inquiry in the Age of Generative AI
  265. Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning
  266. Sidewalk Moments: Are Richer Representations Always More Human-Aligned? Evidence from City-Walk Videos
  267. Anti-Goal Reasoning: Rethinking the Theory of Goal Reasoning in Non-Axiomatic Logic
  268. DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing
  269. MAGE-Vein: Multi-Instance Age and Gender Estimation from Finger Vein Images
  270. HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology
  271. Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
  272. Engine-Native Editable 3D World Reconstruction with Objects and Lighting
  273. TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging
  274. WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing
  275. Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning
  276. LegalCiteTrust: Benchmarking Citation Trustworthiness in Chinese Long-Form Legal Research Reports
  277. Machine Learning for Charge State Characterization of Isolated Double Quantum Dots
  278. Position Bias is Hidden Behind Ceiling Effects: A Permutation Diagnostic for LLM Benchmarks
  279. Probabilistic Residual Learning for Online Recommendations
  280. CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation
  281. Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
  282. Auditing Evidence Use in Medical LLM Diagnosis
  283. Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
  284. Efficient and Interpretable Body-Based Emotion Recognition with Lightweight Temporal Convolutional Networks
  285. Explainable graph attention network for stress recognition (StressGAT) via differential action units
  286. Self-Balancing Sequential Sampling: Fast Convergence with Controlled Predictability
  287. Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs
  288. SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization
  289. New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
  290. Profiling Lightweight Large Language Models