mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 15 Jul 2026

392 papers

  1. Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RLWorld models → Embodied and robot world models
  2. Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic DialoguesSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  3. TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific ExamsLLM reasoning → Multimodal reasoning
  4. A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFDLLM agents and tool use → Web, search, and research agents
  5. X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  6. Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven SystemsLLM agents and tool use → Software engineering coding agents
  7. Unified Hallucination Fuzzing for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  8. SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning ApproachLLM agents and tool use → Web, search, and research agents
  9. CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  10. Local Brushstroke Quality Assessment via Vision-Language FeedbackMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  12. GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  13. The World According to a Social Robot -- Augmenting Human-Robot Dialogue With Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. Eddy-VL 1.9B: Structural Pruning and Layered Distillation for Edge-Deployable Multimodal EmbeddingKnowledge distillation → Multimodal distillation
  15. Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot DataWorld models → Latent predictive world models
  16. Cura 1T: Specialized Model for Agentic HealthcareLLM agents and tool use → Medical and scientific domain agents
  17. Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic ScalingLLM reasoning → Reinforcement learning for reasoning
  18. Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge FlywheelEfficient LLM inference and serving → KV cache optimization
  19. ConFlow: Constraints-Guided Learning with Flow Matching for Motion GenerationDiffusion models → Diffusion and flow policies for robotics
  20. Reward-Free Evolving Agents via Pairwise ValidatorLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QARetrieval-augmented generation → RAG robustness and adaptive retrieval
  22. Integration Matters: Rollout-Based Training for Constrained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  23. Why Git Is the Memory Solution for the Agentic Development LifecycleLLM agents and tool use → Software engineering coding agents
  24. Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous DrivingRetrieval-augmented generation → Multimodal RAG +1
  25. CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science AgentsLLM reasoning → Reasoning for agents, planning and code +1
  26. A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  27. When Is Delegated Play Truthful? Within-Range Regret and the Trilemma of Aligned DelegationLLM agents and tool use → Social simulation and multi-agent debate
  28. HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective OptimizationLLM reasoning → Reasoning benchmarks and evaluation
  29. The Prover Is the Judge: Verified Security Software from AI Coding Agents in Ada/SPARKLLM agents and tool use → Educational agents and math problem solving
  30. Copy-on-Write Scoring: Application-Specific Agent EvaluationsLLM agents and tool use → Software engineering coding agents
  31. MixCompress: Mixture of Experts for Variable Rate Learned Image CompressionMixture-of-experts → MoE large language models
  32. SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement LearningLLM reasoning → Multimodal reasoning +2
  33. PReM: Learning What to Preserve and When to Refresh for Context CompressionEfficient LLM inference and serving → KV cache optimization
  34. Tracing LLM Behavior to the Training Data with Empirical Next-Token DistributionsMechanistic interpretability → SAE features and their applications
  35. DCVC-MB: Neural B-Frame Video Compression using State Space ModelsState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  36. ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMsLLM agents and tool use → Agent threats, guardrails and governance +2
  37. DiMaS: Distribution Matching for Steering Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks +2
  38. Multi-Head Latent Control: A Unified Interface for LLM Agent Decision MakingLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. AI Agents Do Not Fail Alone:The Context Fails FirstLLM agents and tool use → Software engineering coding agents +1
  40. Lyapunov Guidance: A Unified Framework for Stabilizing Generative FlowsDiffusion models → Flow matching, time series and science
  41. MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  42. Automatic Hard Example Synthesis with Multi-Level Agentic Data CurationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  43. Implicit Reasoning Steering via Concept ChainingLLM reasoning → Prompting and chain-of-thought reasoning
  44. Align AI to Dynamic Human-AI WorkflowsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  45. Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force InjectionVision-language-action models → Tactile, force-aware and humanoid VLA
  46. Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene SimulationEnd-to-end autonomous driving → Generative simulation for driving
  47. Augmentations for Robust and Efficient Imitation Learning in Streamed Video GamesOffline RL and imitation learning from data → Imitation learning methods
  48. Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video ModelsLLM safety and security → Vision-language and text-to-image safety
  49. RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and ImaginationLLM reasoning → Spatial and embodied reasoning
  50. NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMsLLM agents and tool use → Agent skill learning and evolution
  51. Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied LearningWorld models → Embodied and robot world models
  52. Semantic Audio-driven Understanding for Dynamic Humanoid Whole Body ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  53. RENEW: Towards Learning World Models and Repairing Model Exploitation from PreferencesWorld models → Latent dynamics models and model-based RL +1
  54. ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent SystemLLM reasoning → Mathematical reasoning +1
  55. Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  56. When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World ModelsWorld models → World models for language agents
  57. Structured Feedback Improves Repair in an LLM Agent LoopLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control PrimitivesLLM agents and tool use → Agent threats, guardrails and governance
  59. From Pixels to States: Rethinking Interactive World Models as Game EnginesWorld models → Video-generation world models and simulators
  60. Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  61. Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case StudyMixture-of-experts → Expert routing strategies
  62. Early Adoption of Agentic Coding Tools by GitHub ProjectsLLM agents and tool use → Software engineering coding agents
  63. Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset PointsDeep reinforcement learning methods → RL for energy, networks and operations
  64. Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective ViolationLLM safety and security → Prompt injection and agent security
  65. M4World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long StreamingWorld models → World models for autonomous driving +1
  66. Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza PendulumDeep reinforcement learning methods → RL theory and sample complexity
  67. The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous CommerceLLM agents and tool use → Social simulation and multi-agent debate
  68. Agent Skill Security: Threat Models, Attacks, Defenses, and EvaluationLLM agents and tool use → Agent threats, guardrails and governance
  69. GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearchWorld models → Embodied and robot world models
  70. Discriminative Barrier Functions for Safe Adversarial Imitation Learning from ObservationOffline RL and imitation learning from data → Safe offline RL +1
  71. SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  72. Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving DataDiffusion models → Diffusion and flow policies for robotics
  73. S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  74. AIMO Interpretability ChallengeLLM reasoning → Mathematical reasoning
  75. Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  76. Experience Memory Graph: One-Shot Error Correction for AgentsLLM agents and tool use → Agent memory systems
  77. Learning Forward & Reverse Skills from a Single Unfinished Demonstration for Constrained Manipulation TasksOffline RL and imitation learning from data → Robot learning from demonstration
  78. Unleashing Multimodal Large Language Models for Training-free HOI Detection in the WildMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  79. Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV SystemsDeep reinforcement learning methods → RL for robot navigation and UAV control
  80. Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language ModelsLLM reasoning → Clinical and biomedical applications +1
  81. Inferentialist Game Semantics (Extended Abstract)LLM reasoning → Reasoning benchmarks and evaluation
  82. SPyCE: Skill-Policy Co-evolution for Multimodal AgentsDeep reinforcement learning methods → RL training of language and agent models
  83. Heavy-Tailed Flow Matching via Random ClocksDiffusion models → Flow matching, time series and science
  84. Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement LearningLLM agents and tool use → Multimodal and embodied agents
  85. TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion ModelDiffusion models → Medical imaging and segmentation
  86. EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration AgentLLM agents and tool use → Multimodal and embodied agents
  87. Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space CorrelationsDiffusion models → Video generation
  88. Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT CalibrationLLM reasoning → Test-time compute and efficient thinking +1
  89. DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-AttentionDeep reinforcement learning methods → Deep RL algorithms and representations
  90. How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to EnforcementLLM agents and tool use → Agent threats, guardrails and governance
  91. CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  92. Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  93. AgentCompass: A Unified Evaluation Infrastructure for Agent CapabilitiesLLM agents and tool use → General LLM agent frameworks and benchmarks
  94. nuTruck: Benchmarking Autonomous Driving Planning for Distributed Electric-drive TrucksEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  95. Social Simulations: from Agent-Based Modeling to Digital TwinsLLM agents and tool use → Social simulation and multi-agent debate
  96. DNA: Dual-stage Native Attribution for Generated Image Source TracingDiffusion models → Robustness, privacy and adversarial aspects
  97. HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-EvolutionLLM agents and tool use → Software engineering coding agents
  98. Towards Spatial Supersensing in the WildWorld models → Video-generation world models and simulators +1
  99. FreeLit: Paired-Free Indoor Relighting via Physics-Guided DiffusionDiffusion models → 3D, point cloud and scene generation
  100. Explaining Reinforcement Learning Agents via Inductive Logic ProgrammingDeep reinforcement learning methods → Interpretable and logic-guided RL
All 392
  1. Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile ManipulationLLM agents and tool use → Multimodal and embodied agents
  2. From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO MonitoringWorld models → Latent predictive world models
  3. Consensus as Privileged Context for Label-Free Self-DistillationLLM reasoning → Reinforcement learning for reasoning +1
  4. STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair OracleLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World ModelsWorld models → Latent predictive world models
  6. Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic SystemLLM agents and tool use → Web, search, and research agents
  7. Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight AnalysisLLM agents and tool use → Web, search, and research agents
  8. Semantic Anchoring for Robotic Action RepresentationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  9. SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE RoutingLLM agents and tool use → Agent threats, guardrails and governance
  10. Memory as a Controlled Process: Learned Adaptive Memory Management for LLM AgentsLLM agents and tool use → Agent memory systems
  11. Structured Reinforcement Learning for Bayesian Persuasion : Application to Intelligent Interactive DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  12. GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid ReasoningLLM reasoning → Chain-of-thought reasoning for driving
  13. Nexus: Native Mesh Generation with DiffusionDiffusion models → 3D, point cloud and scene generation
  14. Grounded world models in biological organisms and future embodied AIWorld models → World models for navigation
  15. Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  16. ThinkBLOX: 3D Indoor Scene Generation with Progressive ReasoningLLM reasoning → Spatial and embodied reasoning +1
  17. LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +2
  18. Attention-Free and Lightweight Token Reduction for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  19. Factorized Spectral Representations for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  20. A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  21. MyAG: A Graph-Based Framework for Designing and Analyzing Composable LLM Agent SystemsLLM agents and tool use → Software engineering coding agents
  22. DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous EnvironmentsLLM agents and tool use → GUI and mobile agents
  23. Joint On-and-Off Policy Learning for Vision-and-Language NavigationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  24. LPM: Industrial-Scale Generative Video RestorationDiffusion models → Inverse problems and image restoration
  25. GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial UnderstandingLLM reasoning → Spatial and embodied reasoning +1
  26. Adversarial Prompting Framework for AI Safety AssessmentLLM safety and security → Prompt injection and agent security
  27. Symbiosis-Inspired Knowledge Distillation for Incremental Object DetectionKnowledge distillation → Detection and dense prediction distillation
  28. DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability DetectionLLM reasoning → Reasoning for agents, planning and code +1
  29. Distributionally Robust and Safe Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  30. When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay ScoringLLM reasoning → Reasoning benchmarks and evaluation
  31. Discrete Diffusion Models: A Unified Framework from Tokenization to GenerationDiffusion models → Discrete and text diffusion
  32. Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication LeafletLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  33. Generalizable VLA Finetuning via Representation Anchoring and Language-Action AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  34. Evaluating Frontier AI Agents as Autonomous Clinical Security AuditorsLLM agents and tool use → Medical and scientific domain agents
  35. Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Embodiment AdaptationWorld models → World models for autonomous driving +1
  36. Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  37. Demystifying On-Policy Distillation: Roles, Pathologies, and RegulationsKnowledge distillation → On-policy and self-distillation for LLMs
  38. Set-shifting Behavioral Test for Harnessed AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  40. GFlowRL: Scaling Distribution-Matching RL to Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  41. FM2: Unified Federated Foundation Models for Heterogeneous Multimodal Medical ImagingMixture-of-experts → Medical and biomedical MoE
  42. Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring SystemRetrieval-augmented generation → Agentic RAG, agents and memory +1
  43. DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D GenerationDiffusion models → 3D, point cloud and scene generation
  44. Learning Latency-Aware Orchestration for Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach
  46. When Audit Quality Fails to Predict Downstream Utility: A Counterfactual Study of Synthetic-Data Selectors for Low-Resource African NLP
  47. LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation
  48. Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Review
  49. Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning
  50. Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction
  51. Myovox: Reading Speech from the Muscles of the Face
  52. How AI Assistants Respond to Repeated Abuse
  53. Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant
  54. Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification
  55. Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation
  56. NepKANUN: A RAG-Based Nepali Legal Assistant
  57. TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback
  58. The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models
  59. Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI
  60. Evidence-Grounded Mapping of Multimodal Human Sensing Psychological Transdiagnostic Dimensions
  61. UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles
  62. RIACT: A Responsible AI System for Personalized Study Habit Tracking and Early Burnout Signal Detection in University Students
  63. Proactive Road Safety Intervention in Australia: Predicting Risky Driving Hotspots from Connected Vehicle Data
  64. Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
  65. Nova: An End-to-End MLIR Compiler for Deep Learning
  66. Double-Scoring: Reliable Extraction of Strong Lottery Tickets
  67. AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks
  68. Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat
  69. SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction
  70. Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness
  71. Localization-Infused Vision-Language Semantic Fusion for Text-Guided Medical Image Segmentation
  72. RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings
  73. SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears
  74. ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
  75. Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations
  76. The Devil is in the Dark Pixels: Toward Brightness Bias-Robust Denoising
  77. Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis
  78. Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architecture-Agnostic Brain Tumor MRI Triage
  79. DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales
  80. Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers
  81. Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models
  82. HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects
  83. Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment
  84. CausalGraphX: A Counterfactual Graph Neural Network Framework for Explainable Systemic Risk Assessment
  85. K-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs
  86. LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration
  87. Decision Making Needs Uncertainty Quantification [Lecture Notes]
  88. Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
  89. CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models
  90. An offline approach to fNIRS-guided reinforcement learning for robot behavior
  91. A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30
  92. MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation
  93. Random Parameter Noise Does Not Make Exact ReLU Verification Easy
  94. Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion
  95. Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning
  96. NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes
  97. Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI
  98. Beyond Pairwise Relations: Dynamic Manipulation Hypergraphs for Vision-Based Human Activity Recognition
  99. Learning Who to Treat When Treatment is Missing
  100. Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
  101. Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution
  102. Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
  103. ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model
  104. Accounting for Hysteresis and Eddy Currents in Finite Element Simulations of Ferromagnetic Laminated Cores using a Recurrent Neural Network
  105. Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data
  106. Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models
  107. NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis
  108. Traccia: An OpenTelemetry-Based Governance Platform for AI Systems
  109. Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs
  110. Assessing AI in Introductory Physics Problem Solving
  111. Measuring How Students Rely on Generative AI in Academic Writing: Development and Multi-Source Validation of the Generative AI Reliance Types Scale (GenAI-RTS)
  112. Parsimonious Mixtures of Skewed Bilinear Factor Analyzers
  113. Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network
  114. XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation
  115. Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist
  116. MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning
  117. The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt
  118. MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
  119. 3D Lane Detection with Odometry for High-Speed Vehicle Racing
  120. The Steering Budget: Examples beat Knobs
  121. LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks
  122. SeeSE3: Emergence of 3D Space in Vision Features
  123. Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks
  124. KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation
  125. How Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment
  126. Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography
  127. Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning
  128. TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories
  129. A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization
  130. MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
  131. Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape
  132. Quantize with Confidence? An Empirical Study of Quantization for Code Generation
  133. OvAi Focus: AI-based Multi-class Segmentation of Functional Ovaries and Adnexal Masses in Gynecological Ultrasound
  134. Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features
  135. How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment
  136. The Cost and Network Limits of Space-Based AI Compute
  137. Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation
  138. A vision foundation model for single-cell biology via spatial gene cartography
  139. VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
  140. Leveraging unlabelled data for generalizable neural population decoding
  141. Linear Independent Component Analysis via Optimal Transport
  142. MetaPerch: Learning from metadata for bioacoustics foundation models
  143. Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
  144. Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
  145. Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters
  146. Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
  147. AI-accelerated End-to-End Framework for Rapid Professional Upskilling
  148. Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation
  149. Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
  150. Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
  151. Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
  152. TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
  153. Task-Specific Feature Fusion Method for Multi-Task Affective Behavior Analysis
  154. Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
  155. Screening Is Effective for Visual Recognition
  156. Music-to-Dance Generation via Atomic Movements
  157. Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis
  158. CF-Net: Conflict Fusion with Speaker Normalisation and Certainty Weighting for Ambivalence/Hesitancy Recognition
  159. DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation
  160. PlumeQuant: Uncertainty-aware consistency assessment of methane plume masks and emission-rate estimates
  161. Beyond the d2.5-mixing bound for Dikin walks on polytopes
  162. Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment
  163. A Self-Evolving Agent for Longitudinal Personal Health Management
  164. A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data
  165. VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
  166. Plausible Deniability Guarantees for Whistleblowers
  167. Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement
  168. Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
  169. DeepStress: Stress-Testing Deep Search Agents
  170. An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence
  171. Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
  172. The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides
  173. High-Order Question Generation in a Multilingual Educational Context
  174. RF Spectrogram Anomaly Detection with Quantum Kitchen Sinks: Architecture, Representation, and Hardware Validation
  175. PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
  176. Verifying formulas for interventional distributions
  177. AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling
  178. Relevance-Aware Rule: Structural Deletion of Irrelevant Conditions in Decision Trees
  179. Quantum Topological Data Encoding
  180. AI-Augmented Human Resource Management? Insights from German companies
  181. NodeImport: Imbalanced Node Classification with Node Importance Assessment
  182. Recursive ArUco Markers: A Scalable Fiducial Marker Design for Unmanned Aerial Vehicle Landing Pads
  183. Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning
  184. Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splatting
  185. AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization
  186. RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics
  187. Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
  188. Prospective clinical indication, post-hoc report leakage, and fusion design in multi-image chest radiograph classification: a patient-clustered evaluation
  189. CAS I: A Geometric Coding Theorem
  190. Regularity as seen by Alice and Bob
  191. Mono-Z Dark Matter Search with Neural Spline Flows Using CMS Run 2015D Open Data
  192. MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model
  193. Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
  194. Ablation-Corrected Evaluation of Attribution Maps in Echocardiographic Ejection-Fraction Models
  195. Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
  196. Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
  197. Cluster with Auctions for Vector Search
  198. Towards quantum machine learning for assessing the resilience of post-quantum cryptography
  199. Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoring
  200. The Test Oracle Problem in Synthetic LLM-as-Judge Corpora: Disappearance, Distortion and a Validation Protocol
  201. Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept
  202. Towards a Modular Bin-picking Framework for Handling Object Pose Uncertainties
  203. Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation
  204. Microstructure-Conditioned Surrogate Models for Graded Multiscale Optimization of Mycelium Composites
  205. Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
  206. When Variance Is Not an Error Map: Calibrated Uncertainty for Radiative Gaussian Splatting in Sparse-View CT
  207. When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects
  208. WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching
  209. Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge
  210. Fine-grained CLIP fine-tuning with self-annotated region alignment
  211. The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model
  212. T3HG-Editor: Text-driven 3D Human Garment Editing with Body Priors Embedded in SMPL-X
  213. Maximally Robust Satisficing Bayesian Optimization
  214. Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models
  215. Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction
  216. OvisOCR2 Technical Report
  217. How the Hessian-Spectrum of Neural Networks Depends on Data
  218. From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception
  219. UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
  220. FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy
  221. Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
  222. Video to All-in-focus Image Reconstruction Algorithm for Automated Microscopic Urinalysis
  223. Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
  224. From Prediction to Collaboration: Interactive Symbolic Music Analysis
  225. UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets
  226. Visual Place Recognition Using Rate-Encoded Spiking Neural Networks with Discrete STDP Learning
  227. Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
  228. Approximation of solutions of parameter-dependent problems by residual neural networks
  229. IMMNet: Hybrid Fusion of Model-based and Data-driven Approaches for Maneuvering Target Tracking
  230. Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
  231. Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering
  232. Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs
  233. UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
  234. AI advice suppresses people's willingness to say "I don't know", even when the advice is wrong and accuracy is incentivized
  235. Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
  236. Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning
  237. Cost-Pragmatic Quality Gating and Selection-Fusion Multi-Model Combiners for BioASQ Phases A+ and B
  238. Parallel gradient boosting for flexible estimation of conditional distributions
  239. How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
  240. From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing
  241. Clustering algorithms for multivariate wind farm SCADA data filtering
  242. When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
  243. VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation
  244. Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robots
  245. DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control
  246. ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
  247. CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs
  248. TRACE-PCa: Predicting Prostate Cancer Progression from Longitudinal MRI During Active Surveillance
  249. DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery
  250. M2P-AD: Memory-to-Prototype Learning with Boundary-aware Score Refinement for 3D Anomaly Detection
  251. CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction
  252. DeepLoop: Depth Scaling for Looped Transformers
  253. GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priors
  254. Topology-Agnostic Mesh Reconstruction of Deformable Objects from Sparse Touch
  255. Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation
  256. Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability
  257. EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal
  258. Bring Music The Horizon: Music-Driven 360^circ Video Generation
  259. Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
  260. HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
  261. PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification
  262. 2D Rotary Position Embedding for Scene Text Recognition with Transformers
  263. Live Gurbani Tracking: A Benchmark and Reference System for Captioning Sikh Kirtan
  264. TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects
  265. Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
  266. DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching
  267. CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification
  268. Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
  269. PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
  270. Data-Efficient Adaptation of LLMs via Attention Head Reweighting
  271. Temperature Scaling Is Not Enough: Calibration Gaps Under Human Label Distributions
  272. ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
  273. OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations
  274. Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents
  275. EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models
  276. MultiAnimate: A Unified Framework for Controllable Multi-Character Animation
  277. Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
  278. Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for Structured Data Classification
  279. AnomExpert: Identifying and Selecting Anatomical Planes for Prenatal Ultrasound Anomaly Diagnosis
  280. Price of Fairness in Bandits: A Tight Minimax Characterization
  281. The Caf'e in Amsterdam: When the Incumbent Becomes the Oracle
  282. Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
  283. Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks
  284. Learned Pairwise Deep Dual-Optimal Inequalities for Stabilizing Column Generation
  285. A POS Tier Is the Key to Automated Annotation for Low-Resource Language Documentation: Neural Interlinear Glossing for Irabu, a Southern Ryukyuan Language
  286. RoughNet: Mapping Arctic Sea Ice Roughness Using Diffusion-Based Super-Resolution of Satellite Imagery
  287. Detector Confidence Signals Presence Rather Than Occlusion in Cluttered Manipulation
  288. LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition
  289. The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
  290. Audio-Text Cross-Attention with Psycholinguistic Support Features for Ambivalence/Hesitancy Recognition
  291. EZSMT Version 3, Matured
  292. Marker-free deformable registration and fusion for augmented reality-guided positive margin localization during tumor resection surgery