mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 20 Mar 2026

415 papers

  1. Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing SynthesisLLM agents and tool use → Agent threats, guardrails and governance
  2. PersonaVLM: Long-Term Personalized Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant TasksLLM agents and tool use → Tool learning and function calling
  5. Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination ProbingMechanistic interpretability → Hallucination detection from model internals
  6. Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student EvaluationsLLM agents and tool use → Educational agents and math problem solving
  7. Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex TradingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  8. Mixture of Experts with Soft Nearest Neighbor Loss: Resolving Expert Collapse via Representation DisentanglementMixture-of-experts → Vision mixture-of-experts
  9. Contextual inference from single objects in Vision-Language modelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation LearningMixture-of-experts → MoE for time series and graphs
  12. Emergency Preemption Without Online Exploration: A Decision Transformer ApproachOffline RL and imitation learning from data → Imitation and offline RL for driving
  13. When Negation Is a Geometry Problem in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. Understanding Behavior Cloning with Action QuantizationOffline RL and imitation learning from data → Imitation learning methods
  15. An Industrial-Scale Retrieval-Augmented Generation Framework for Requirements Engineering: Empirical Evaluation with Automotive Manufacturing DataRetrieval-augmented generation → RAG pipeline design and evaluation
  16. Memory Over Maps: 3D Object Localization Without ReconstructionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Does This Gradient Spark Joy?Deep reinforcement learning methods → RL theory and sample complexity
  18. Delightful Distributed Policy GradientDeep reinforcement learning methods → RL theory and sample complexity
  19. Grounded Chess Reasoning in Language Models via Master DistillationLLM reasoning → Reasoning for agents, planning and code
  20. Measuring Weak-to-Strong Legibility of Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  21. AE-LLM: Adaptive Efficiency Optimization for Large Language ModelsMixture-of-experts → MoE large language models
  22. CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning AttributionLLM reasoning → Spatial and embodied reasoning +1
  23. DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  24. Diffutron: A Masked Diffusion Language Model for Turkish LanguageDiffusion models → Discrete and text diffusion
  25. Regret Bounds for Reinforcement Learning from Multi-Source Imperfect PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  26. Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  27. A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-ImprovementSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  28. Deep reflective reasoning in interdependence constrained structured data extraction from clinical notes for digital healthLLM reasoning → Clinical and biomedical applications
  29. Coding Agents are Effective Long-Context ProcessorsLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture TranslationLLM reasoning → Mathematical reasoning
  31. KV Cache Optimization Strategies for Scalable and Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
  32. SymCircuit: Bayesian Structure Inference for Tractable Probabilistic Circuits via Entropy-Regularized Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  33. Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance ClassifierDiffusion models → Diffusion foundations and sampling
  34. The production of meaning in the processing of natural languageMechanistic interpretability → Knowledge and representations inside LLMs
  35. Memory poisoning and secure multi-agent systemsLLM agents and tool use → Agent threats, guardrails and governance
  36. ContractSkill: Repairable Contract-Based Skills for Multimodal Web AgentsLLM agents and tool use → Web, search, and research agents
  37. Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed GraphsLLM safety and security → Backdoor and data poisoning attacks
  38. Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent RepresentationsWorld models → Video-generation world models and simulators
  39. When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM PipelinesLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual HintsLLM reasoning → Multimodal reasoning
  41. LumosX: Relate Any Identities with Their Attributes for Personalized Video GenerationDiffusion models → Video generation
  42. Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free MethodsDiffusion models → Diffusion foundations and sampling
  43. Improving Image-to-Image Translation via a Rectified Flow ReformulationDiffusion models → Image generation, text-to-image and editing
  44. VideoSeek: Long-Horizon Video Agent with Tool-Guided SeekingLLM agents and tool use → Multimodal and embodied agents
  45. AI Agents Can Already Autonomously Perform Experimental High Energy PhysicsLLM agents and tool use → Web, search, and research agents
  46. Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought EvaluationLLM reasoning → Prompting and chain-of-thought reasoning
  47. Learning Dynamic Belief Graphs for Theory-of-mind ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  48. EgoForge: Goal-Directed Egocentric World SimulatorWorld models → Embodied and robot world models
  49. Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMDDiffusion models → Diffusion foundations and sampling
  50. Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology ReasoningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  51. AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  52. Reasoning Gets Harder for LLMs Inside A DialogueLLM reasoning → Reasoning benchmarks and evaluation
  53. An Agentic Multi-Agent Architecture for Cybersecurity Risk ManagementLLM agents and tool use → Agent threats, guardrails and governance
  54. Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language ModelsLLM safety and security → Jailbreaking
  55. Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  56. Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competitionLLM safety and security → Backdoor and data poisoning attacks
  57. Pitfalls in Evaluating Interpretability AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  59. How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  60. Agentic Harness for Real-World CompilersLLM agents and tool use → Software engineering coding agents
  61. MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space ModelsState-space sequence models (S4, Mamba) → Vision Mamba backbones
  62. Fine-tuning Timeseries Predictors Using Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  63. Structured Latent Dynamics in Wireless CSI via Homomorphic World ModelsWorld models → Latent predictive world models
  64. Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMsLLM reasoning → Reinforcement learning for reasoning
  65. Detached Skip-Links and R-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCRLLM reasoning → Multimodal reasoning +1
  66. RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
  67. AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture SearchSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  68. Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline EngineeringDeep reinforcement learning methods → RL training of language and agent models
  69. An Agentic Approach to Generating XAI-NarrativesLLM agents and tool use → Multimodal and embodied agents
  70. MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUIMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  71. Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov StatesLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  72. X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End DrivingWorld models → World models for autonomous driving +1
  73. Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped GuidanceLLM agents and tool use → Agent threats, guardrails and governance +2
  74. Interpreting Reinforcement Learning Model Behavior via Koopman with ControlDeep reinforcement learning methods → RL theory and sample complexity
  75. HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report PredictionMultimodal LLMs / vision-language models → Medical vision-language models
  76. Timestep-Aware Block Masking for Efficient Diffusion Model InferenceDiffusion models → Diffusion foundations and sampling
  77. Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM AgentsLLM agents and tool use → Agent memory systems
  78. SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast AsiaLLM agents and tool use → General LLM agent frameworks and benchmarks
  79. ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image AnalysisState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  80. DALI: LLM-Agent Enhanced Dual-Stream Adaptive Leadership Identification for Group RecommendationsLLM agents and tool use → Agentic recommender systems
  81. Utility-Guided Agent Orchestration for Efficient LLM Tool UseLLM agents and tool use → General LLM agent frameworks and benchmarks
  82. What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test TimeLLM reasoning → Reinforcement learning for reasoning +1
  83. On the Dynamics & Transferability of Latent Generalization during MemorizationMechanistic interpretability → Circuits and mechanistic analysis
  84. MedQ-Engine: A Closed-Loop Data Engine for Evolving MLLMs in Medical Image Quality AssessmentMultimodal LLMs / vision-language models → Medical vision-language models
  85. IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal AlignmentMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  86. FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  87. HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action TasksVision-language-action models → Aerial and drone VLA
  88. Geometric Risk Control for Vision-Language Model OCRMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  89. Embodied Science: Closing the Discovery Loop with Agentic Embodied AILLM agents and tool use → Web, search, and research agents
  90. One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic AssessmentLLM reasoning → Multimodal reasoning +1
  91. FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  92. Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM BenchmarkingLLM reasoning → Reasoning benchmarks and evaluation
  93. FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  94. PoC: Performance-oriented Context Compression for Large Language Models via Performance PredictionEfficient LLM inference and serving → Prompt and context compression
  95. Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question ReformulationLLM agents and tool use → General LLM agent frameworks and benchmarks
  96. LoopRPT: Reinforcement Pre-Training for Looped Language ModelsLLM reasoning → Test-time compute and efficient thinking
  97. WorldAgents: Can Foundation Image Models be Agents for 3D World Models?World models → Video-generation world models and simulators +1
  98. DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  99. A Subgoal-driven Framework for Improving Long-Horizon LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  100. GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
All 415
  1. ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  2. DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous DrivingWorld models → World models for autonomous driving +1
  3. Making Video Models Adhere to User Intent with Minor AdjustmentsDiffusion models → Video generation
  4. Load--Reserve Wasserstein Propagation for Isotropic Diffusion SamplersDiffusion models → Diffusion foundations and sampling
  5. The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer InferenceEfficient LLM inference and serving → KV cache optimization
  6. CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  7. PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy OptimizationLLM agents and tool use → Social simulation and multi-agent debate
  8. Heavy-Tailed and Long-Range Dependent Noise in Stochastic Approximation: A Finite-Time AnalysisDeep reinforcement learning methods → RL theory and sample complexity
  9. OmniDiT: Extending Diffusion Transformer to Omni-VTON FrameworkDiffusion models → 3D, point cloud and scene generation
  10. HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  11. BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page SelectionEfficient LLM inference and serving → Prompt and context compression
  12. ContractionPPO: Certified Reinforcement Learning via Differentiable Contraction LayersDeep reinforcement learning methods → RL for robot locomotion and manipulation
  13. DeepStock: Reinforcement Learning with Policy Regularizations for Inventory ManagementDeep reinforcement learning methods → RL for energy, networks and operations
  14. OrbitNVS: Harnessing Video Diffusion Priors for Novel View SynthesisDiffusion models → 3D, point cloud and scene generation
  15. ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative DecodingEfficient LLM inference and serving → Fast autoregressive visual generation
  16. FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified FlowDiffusion models → 3D, point cloud and scene generation
  17. All-Mem: Agentic Lifelong Memory via Dynamic Topology EvolutionLLM agents and tool use → Agent memory systems
  18. PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power ManagementLLM agents and tool use → GUI and mobile agents
  19. Skilled AI Agents for Embedded and IoT Systems DevelopmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  21. MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-GenerationDiffusion models → Medical imaging and segmentation
  22. CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory ManagementMultimodal LLMs / vision-language models → Video understanding with MLLMs
  23. TextReasoningBench: Does Reasoning Really Improve Text Classification in Large Language Models?LLM reasoning → Reasoning benchmarks and evaluation
  24. Planning Autonomous Vehicle Maneuvering in Work Zones Through Game-Theoretic Trajectory GenerationEnd-to-end autonomous driving → Cooperative and V2X driving
  25. FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug AssessmentLLM reasoning → Clinical and biomedical applications
  26. Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities
  27. Architecture of an AI-Based Automated Course of Action Generation System for Military Operations
  28. Algorithm Selection with Zero Domain Knowledge via Text Embeddings
  29. CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
  30. SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning
  31. An Edge-Cloud Collaborative Architecture for Proactive Elderly Care: Real-Time Risk Assessment and Three-Level Emergency Response
  32. DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs
  33. EVE: A Domain-Specific LLM Framework for Earth Intelligence
  34. Curation of a Palaeohispanic Dataset for Machine Learning
  35. Leveraging Machine Learning Techniques to Investigate Media and Information Literacy Competence in Tackling Disinformation
  36. Can We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in the LLM Era
  37. Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
  38. Logic-Gated Time-Shared Feedforward Networks for Alternating Finite Automata: Exact Simulation and Learnability
  39. Smartphone-Based Identification of Unknown Liquids via Active Vibration Sensing
  40. AI in Work-Based Learning: Understanding the Purposes and Effects of Intelligent Tools Among Student Interns
  41. Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion
  42. SEAR: Schema-Based Evaluation and Routing for LLM Gateways
  43. The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating
  44. A Multimodal Deep Learning Framework for Edema Classification Using HCT and Clinical Data
  45. Capability Safety as Datalog: A Foundational Equivalence
  46. An Annotation-to-Detection Framework for Autonomous and Robust Vine Trunk Localization in the Field by Mobile Agricultural Robots
  47. Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
  48. PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA
  49. Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
  50. Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms
  51. Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models
  52. Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction
  53. Trained Persistent Memory for Frozen Decoder-Only LLMs
  54. Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression
  55. Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
  56. A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance
  57. Hybrid Associative Memories
  58. DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
  59. A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
  60. AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations
  61. How Can Machine Learning Emulators Best Support Climate Science?
  62. Sparsely-Supervised Data Assimilation via Physics-Informed Schr"odinger Bridge
  63. A graph neural network based chemical mechanism reduction method for combustion applications
  64. ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
  65. Enhancing AI-Based Tropical Cyclone Track and Intensity Forecasting via Systematic Bias Correction
  66. A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
  67. Permutation-Consensus Listwise Judging for Robust Factuality Evaluation
  68. LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
  69. Towards Practical Multimodal Hospital Outbreak Detection
  70. Revenue-Sharing as Infrastructure: A Distributed Business Model for Generative AI Platforms
  71. Epistemic Observability in Language Models
  72. RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
  73. CogFormer: Learn All Your Models Once
  74. End-to-End Optimization of Polarimetric Measurement and Material Classifier
  75. Evaluating Large Language Models on Historical Health Crisis Knowledge in Resource-Limited Settings: A Hybrid Multi-Metric Study
  76. ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation
  77. Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time
  78. Distributed Gradient Clustering: Convergence and the Effect of Initialization
  79. Efficient Counterfactual Reasoning in ProbLog via Single World Intervention Programs
  80. Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference
  81. PARHAF, a human-authored corpus of clinical reports for fictitious patients in French
  82. Spatio-Temporal Grid Intelligence: A Hybrid Graph Neural Network and LSTM Framework for Robust Electricity Theft Detection
  83. Profiling learners' affective engagement: Emotion AI, intercultural pragmatics, and language learning
  84. From Data to Laws: Neural Discovery of Conservation Laws Without False Positives
  85. Goal-oriented learning of stochastic differential equations using error bounds on path-space observables
  86. Double Machine Learning for Static Panel Data with Instrumental Variables: New Method and Applications
  87. Shift-Invariant Feature Attribution in the Application of Wireless Electrocardiograms
  88. Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs
  89. SDE-Driven Spatio-Temporal Hypergraph Neural Networks for Irregular Longitudinal fMRI Connectome Modeling in Alzheimer's Disease
  90. Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
  91. Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis
  92. Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
  93. Verifiable Error Bounds for Physics-Informed Neural KKL Observers
  94. When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal
  95. Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis
  96. Leveraging Natural Language Processing and Machine Learning for Evidence-Based Food Security Policy Decision-Making in Data-Scarce Making
  97. PEARL: Personalized Streaming Video Understanding Model
  98. Hawkeye: Reproducing GPU-Level Non-Determinism
  99. CRANE: Correcting Errors in Raw Nanopore Signals Using Hidden Markov Models
  100. Data-driven discovery of roughness descriptors for surface characterization and intimate contact modeling of unidirectional composite tapes
  101. SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
  102. Meta-Learning for Repeated Bayesian Persuasion
  103. Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP
  104. Hetero-Net: An Energy-Efficient Resource Allocation and 3D Placement in Heterogeneous LoRa Networks via Multi-Agent Optimization
  105. FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection
  106. Compression is all you need: Modeling Mathematics
  107. Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
  108. CAMA: Exploring Collusive Adversarial Attacks in c-MARL
  109. A chemical language model for reticular materials design
  110. From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
  111. Jigsaw Regularization in Whole-Slide Image Classification
  112. Multi-Stage Fine-Tuning of Pathology Foundation Models with Head-Diverse Ensembling for White Blood Cell Classification
  113. Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams
  114. WebNavigator: Global Web Navigation via Interaction Graph Retrieval
  115. Comprehensive Description of Uncertainty in Measurement for Representation and Propagation with Scalable Precision
  116. Operator Learning for Smoothing and Forecasting
  117. Leum-VL Technical Report
  118. Scene Representation using 360deg Saliency Graph and its Application in Vision-based Indoor Navigation
  119. The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
  120. MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
  121. Toward a Multi-View Brain Network Foundation Model: Cross-View Consistency Learning Across Arbitrary Atlases
  122. G2DR: A Genotype-First Framework for Genetics-Informed Target Prioritization and Drug Repurposing
  123. Interpretable Multiple Myeloma Prognosis with Observational Medical Outcomes Partnership Data
  124. Low-pass Personalized Subgraph Federated Recommendation
  125. High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation
  126. GEM: A Native Graph-based Index for Multi-Vector Retrieval
  127. Hybrid Autoencoder-Isolation Forest approach for time series anomaly detection in C70XP cyclotron operation data at ARRONAX
  128. Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
  129. Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms
  130. Measure flow path recovery in Bayes Hilbert spaces
  131. Decorrelation, Diversity, and Emergent Intelligence: The Isomorphism Between Social Insect Colonies and Ensemble Machine Learning
  132. Prompt-Free Lightweight SAM Adaptation for Histopathology Nuclei Segmentation with Strong Cross-Dataset Generalization
  133. DCG-Net: Dual Cross-Attention with Concept-Value Graph Reasoning for Interpretable Medical Diagnosis
  134. NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation
  135. From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering
  136. Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentation
  137. CoVR-R:Reason-Aware Composed Video Retrieval
  138. Learning Sampled-data Control for Swarms via MeanFlow
  139. NOUS: Video-Driven 3D Human Reaction Generation via Observation-Reaction Mutual Steering
  140. Kolmogorov-Arnold causal generative models
  141. Improving Generalization on Cybersecurity Tasks with Multi-Modal Contrastive Learning
  142. Adaptive Greedy Frame Selection for Long Video Understanding
  143. LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis
  144. TinyML Enhances CubeSat Mission Capabilities
  145. The Robot's Inner Critic: Self-Refinement of Social Behaviors through VLM-based Replanning
  146. Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models
  147. Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
  148. Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case
  149. Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification
  150. Synergistic Perception and Generative Recomposition: A Multi-Agent Orchestration for Expert-Level Building Inspection
  151. Revisiting Gene Ontology Knowledge Discovery with Hierarchical Feature Selection and Virtual Study Group of AI Agents
  152. Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives
  153. Conditioning Protein Generation via Hopfield Pattern Multiplicity
  154. Current LLMs still cannot 'talk much' about grammar modules: Evidence from syntax
  155. Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech
  156. Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning
  157. GO-GenZip: Goal-Oriented Generative Sampling and Hybrid Compression
  158. The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus
  159. Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
  160. LLM-Enhanced Semantic Data Integration of Electronic Component Qualifications in the Aerospace Domain
  161. Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
  162. Predicting States of Understanding in Explanatory Interactions Using Cognitive Load-Related Linguistic Cues
  163. A Unified Platform and Quality Assurance Framework for 3D Ultrasound Reconstruction with Robotic, Optical, and Electromagnetic Tracking
  164. Antenna Array Beamforming Based on a Hybrid Quantum Optimization Framework
  165. The monotonicity of the Franz-Parisi potential is equivalent with Low-degree MMSE lower bounds
  166. The End of Rented Discovery: How AI Search Redistributes Power Between Hotels and Intermediaries
  167. DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment
  168. Investigating a Policy-Based Formulation for Endoscopic Camera Pose Recovery
  169. LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families
  170. Federated Hyperdimensional Computing for Resource-Constrained Industrial IoT
  171. Continual Learning as Shared-Manifold Continuation Under Compatible Shift
  172. CoverageBench: Evaluating Information Coverage across Tasks and Domains
  173. Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs
  174. Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
  175. Layered Quantum Architecture Search for 3D Point Cloud Classification
  176. ODySSeI: An Open-Source End-to-End Framework for Automated Detection, Segmentation, and Severity Estimation of Lesions in Invasive Coronary Angiography Images
  177. CFCML: A Coarse-to-Fine Crossmodal Learning Framework For Disease Diagnosis Using Multimodal Images and Tabular Data
  178. Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features
  179. A Super Fast K-means for Indexing Vector Embeddings
  180. Physics-Informed Long-Range Coulomb Correction for Machine-learning Hamiltonians
  181. NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness
  182. When Contextual Inference Fails: Cancelability in Interactive Instruction Following
  183. Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts
  184. Promoting Critical Thinking With Domain-Specific Generative AI Provocations
  185. Model-Driven Learning-Based Physical Layer Authentication for Mobile Wi-Fi Devices
  186. Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs
  187. 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
  188. Channel Prediction-Based Physical Layer Authentication under Consecutive Spoofing Attacks
  189. Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
  190. Structural Controllability of Large-Scale Hypergraphs
  191. On the Ability of Transformers to Verify Plans
  192. TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+)
  193. Hybrid topic modelling for computational close reading: Mapping narrative themes in Pushkin's Evgenij Onegin
  194. LIORNet: Self-Supervised LiDAR Snow Removal Framework for Autonomous Driving under Adverse Weather Conditions
  195. RAM: Recover Any 3D Human Motion in-the-Wild
  196. SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images
  197. Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitexts
  198. Span-Level Machine Translation Meta-Evaluation
  199. PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms
  200. Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
  201. Infinite-dimensional spherical-radial decomposition for probabilistic functions, with application to constrained optimal control and Gaussian process regression
  202. A Federated Many-to-One Hopfield model for associative Neural Networks
  203. Deep Time-Series Forecasting in 10 Years: A Survey
  204. Revealing Domain-Spatiality Patterns for Configuration Tuning: Domain Knowledge Meets Fitness Landscapes
  205. Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning
  206. Discovery of Decision Synchronization Patterns from Event Logs
  207. Minimax Generalized Cross-Entropy
  208. SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
  209. NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing
  210. FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts
  211. Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
  212. Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue
  213. Probing and Inducing Clinical Modality Grounding in Brain Tumor Segmentation
  214. Overreliance on AI in Information-seeking from Video Content
  215. Modeling subgrid scale production rates on complex meshes using graph neural networks
  216. Explainable cluster analysis: a bagging approach
  217. Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
  218. Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?
  219. FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization
  220. FrameNet Semantic Role Classification by Analogy
  221. GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Prediction
  222. Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study
  223. Two-Time-Scale Learning Dynamics: A Population View of Neural Network Training
  224. Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
  225. Quantifying Gate Contribution in Quantum Feature Maps for Scalable Circuit Optimization
  226. Uncertainty Quantification Via the Posterior Predictive Variance
  227. Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy
  228. Offshore oil and gas platform dynamics in the North Sea, Gulf of Mexico, and Persian Gulf: Exploiting the Sentinel-1 archive
  229. Borderless Long Speech Synthesis
  230. Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
  231. Scalable Learning of Multivariate Distributions via Coresets
  232. Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation
  233. Decoupled Sensitivity-Consistency Learning for Weakly Supervised Video Anomaly Detection
  234. ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection
  235. Evaluating Image Editing with LLMs: A Comprehensive Benchmark and Intermediate-Layer Probing Approach
  236. Template-based Object Detection Using a Foundation Model
  237. Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders
  238. FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision
  239. Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
  240. PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
  241. Growing Networks with Autonomous Pruning
  242. Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation
  243. Regularity of Solutions to Beckmann's Parametric Optimal Transport
  244. ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
  245. PhysNeXt: Next-Generation Dual-Branch Structured Attention Fusion Network for Remote Photoplethysmography Measurement
  246. Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation
  247. MOSS-TTSD: Text to Spoken Dialogue Generation
  248. A two-step sequential approach for hyperparameter selection in finite context models
  249. PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing
  250. FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
  251. BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates
  252. Neuro-Symbolic Proof Generation for Scaling Systems Software Verification
  253. Binary Classification from Coupled Pairwise Labels
  254. TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch
  255. EvoTaxo: Building and Evolving Taxonomy from Social Media Streams
  256. AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation
  257. Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
  258. Regret Analysis of Sleeping Competing Bandits
  259. Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis
  260. Diminishing Returns in Expanding Generative Models and Godel-Tarski-Lob Limits
  261. TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents
  262. Ontology-Based Knowledge Modeling and Uncertainty-Aware Outdoor Air Quality Assessment Using Weighted Interval Type-2 Fuzzy Logic
  263. 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction
  264. Unbiased Dynamic Multimodal Fusion
  265. Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
  266. Structured Prompting for Arabic Essay Proficiency: A Trait-Centric Evaluation Approach
  267. Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding
  268. Semantic Audio-Visual Navigation in Continuous Environments
  269. Model Selection and Parameter Estimation for Multidimensional Gaussian Mixture Models with a Common Covariance Matrix
  270. GravCal: Single-Image Calibration of IMU Gravity Priors with Per-Sample Confidence
  271. Ensembles-based Feature Guided Analysis
  272. UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer
  273. RiboSphere: Learning Unified and Efficient Representations of RNA Structures
  274. MetaCues: Enabling Critical Engagement with Generative AI for Information Seeking and Sensemaking
  275. Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
  276. On the role of memorization in learned priors for geophysical inverse problems
  277. Dual Prompt-Driven Feature Encoding for Nighttime UAV Tracking
  278. IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1
  279. Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance
  280. Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
  281. A Locally Penalized Cross-Estimate Federated Method with Guarantees for Constrained Personalized Learning
  282. UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
  283. CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation
  284. Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL
  285. LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
  286. FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement
  287. Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning
  288. Beyond Quadratic: Linear-Time Change Detection with RWKV
  289. K-GMRF: Kinetic Gauss-Markov Random Field for First-Principles Covariance Tracking on Lie Groups
  290. Physics-Informed Neural Network with Adaptive Clustering Learning Mechanism for Information Popularity Prediction
  291. ARMOR: Adaptive Resilience Against Model Poisoning Attacks in Continual Federated Learning for Mobile Indoor Localization
  292. Data-driven ensemble prediction of the global ocean
  293. HiFiGaze: Improving Eye Tracking Accuracy Using Screen Content Knowledge
  294. Evolving Embodied Intelligence: Graph Neural Network--Driven Co-Design of Morphology and Control in Soft Robotics
  295. AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?
  296. Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation
  297. Efficiency Follows Global-Local Decoupling
  298. PhyUnfold-Net: Advancing Remote Sensing Change Detection with Physics-Guided Deep Unfolding
  299. PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition
  300. Wearable Foundation Models Should Go Beyond Static Encoders
  301. Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search
  302. Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
  303. An Adaptive Machine Learning Framework for Fluid Flow in Dual-Network Porous Media
  304. Optimal Scalar Quantization for Matrix Multiplication: Closed-Form Density and Phase Transition
  305. StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention
  306. Learning to Bet for Horizon-Aware Anytime-Valid Testing
  307. Plagiarism or Productivity? Students Moral Disengagement and Behavioral Intentions to Use ChatGPT in Academic Writing
  308. SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
  309. Subspace Kernel Learning on Tensor Sequences
  310. Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations
  311. Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers
  312. MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane
  313. Behavioral Engagement in VR-Based Sign Language Learning: Visual Attention as a Predictor of Performance and Temporal Dynamics
  314. Pedestrian Crossing Intent Prediction via Psychological Features and Transformer Fusion
  315. EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models