mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 28 Mar 2026

199 papers

  1. Safety in Embodied AI: A Survey of Risks, Attacks, and DefensesLLM safety and security → Prompt injection and agent security
  2. A Reference Architecture for Agentic Hybrid Retrieval in Dataset SearchLLM agents and tool use → Web, search, and research agents
  3. Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systemsLLM reasoning → Reasoning for agents, planning and code
  4. Listen, Correct, and Feed Back: Spoken Pedagogical Feedback GenerationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  5. Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD SurrogatesMechanistic interpretability → Sparse autoencoder training and evaluation
  6. 3D-IDE: 3D Implicit Depth EmergentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  7. GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language ModelsLLM safety and security → Jailbreaking
  8. The impact of multi-agent debate protocols on debate quality: a controlled case studyLLM agents and tool use → Social simulation and multi-agent debate
  9. SafeClaw-R: Towards Safe and Secure Multi-Agent Personal AssistantsLLM agents and tool use → Agent threats, guardrails and governance +1
  10. LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World ModelWorld models → Embodied and robot world models
  11. From Tool to Teammate: LLM Coding Agents as Collaborative Partners for Behavioral Labeling in Educational Dialogue AnalysisLLM agents and tool use → Educational agents and math problem solving
  12. SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  13. Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  14. Greedy Is a Strong Default: Agents as Iterative OptimizersLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual StreamsLLM safety and security → Safety alignment, refusal and guardrails
  16. Rainbow-DemoRL: Combining Improvements in Demonstration-Augmented Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  17. Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  18. Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  19. HMPDM: A Diffusion Model for Driving Video Prediction with Historical Motion PriorsDiffusion models → Diffusion and flow policies for robotics
  20. Inference-Time Structural Reasoning for Compositional Vision-Language UnderstandingLLM reasoning → Multimodal reasoning +1
  21. D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learning in Robotic ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  22. PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question AnsweringLLM reasoning → Clinical and biomedical applications
  23. Supporting Reflection and Forward-Looking Reasoning With Data-Driven QuestionsLLM reasoning → Reasoning benchmarks and evaluation
  24. Where-to-Learn: Analytical Policy Gradient Directed Exploration for On-Policy Robotic Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  25. EpochX: Building the Infrastructure for an Emergent Agent CivilizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer VerificationLLM agents and tool use → Agent threats, guardrails and governance +1
  27. Uni-World VLA: Interleaved World Modeling and Planning for Autonomous DrivingWorld models → World models for autonomous driving +1
  28. HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  29. Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCPLLM agents and tool use → Software engineering coding agents
  30. From Foundation ECG Models to NISQ Learners: Distilling ECGFounder into a VQC StudentKnowledge distillation → Distillation for medical imaging
  31. Mitigating Hallucination on Hallucination in RAG via Ensemble VotingRetrieval-augmented generation → Hallucination detection in RAG
  32. Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace ProjectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  33. Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  34. LightMover: Generative Light Movement with Color and Intensity ControlsDiffusion models → 3D, point cloud and scene generation
  35. Autonomous overtaking trajectory optimization using reinforcement learning and opponent pose estimationDeep reinforcement learning methods → RL for autonomous driving and traffic
  36. MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  37. Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought ModelsLLM reasoning → Hallucination detection and mitigation
  38. Let Triggers Control: Frequency-Aware Dropout for Effective Token ControlDiffusion models → Image generation, text-to-image and editing
  39. AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure DesignLLM agents and tool use → Medical and scientific domain agents
  40. Incentivizing Temporal-Awareness in Egocentric Video Understanding ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  41. Reasoning-Driven Anomaly Detection and Localization with Image-Level SupervisionLLM reasoning → Chain-of-thought reasoning for driving +1
  42. MEDIC-AD: Towards Medical Vision-Language Model's Clinical IntelligenceMultimodal LLMs / vision-language models → Medical vision-language models
  43. MediHive: A Decentralized Agent Collective for Medical ReasoningLLM reasoning → Clinical and biomedical applications +1
  44. SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually DoLLM agents and tool use → Agent threats, guardrails and governance
  45. Routing Sensitivity Without Controllability: A Diagnostic Study of Fairness in MoE Language ModelsMixture-of-experts → Expert routing strategies
  46. The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  47. ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM InferenceEfficient LLM inference and serving → KV cache optimization
  48. Red-MIRROR: Agentic LLM-based Autonomous Penetration Testing with Reflective Verification and Knowledge-augmented InteractionLLM agents and tool use → Agent threats, guardrails and governance
  49. EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution FlowDiffusion models → Video generation
  50. LightCtrl: Training-free Controllable Video RelightingDiffusion models → 3D, point cloud and scene generation
  51. When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof TutoringLLM agents and tool use → Educational agents and math problem solving
  52. Mind The Gap: How The Technical Mechanism Of Agentic AI Outpace Global Legal FrameworksLLM agents and tool use → Agent threats, guardrails and governance
  53. Structural Graph Probing of Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  54. Dynamic resource matching in manufacturing using deep reinforcement learningDeep reinforcement learning methods → RL for energy, networks and operations
  55. ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  56. VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal SegmentationLLM reasoning → Multimodal reasoning
  57. Liquid Networks with Mixture Density Heads for Efficient Imitation LearningDiffusion models → Diffusion and flow policies for robotics +1
  58. Towards High-Quality Machine Translation for Kokborok: A Low-Resource Tibeto-Burman Language of Northeast India
  59. Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
  60. Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa
  61. RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)
  62. SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills
  63. Selectivity and Shape in the Design of Forward-Forward Goodness Functions
  64. Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power Side-Channel Data
  65. Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
  66. On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment
  67. Structured Exploration and Exploitation of Label Functions for Automated Data Annotation
  68. Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition
  69. Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets
  70. Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild
  71. ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
  72. XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation
  73. ASTRA: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering
  74. SkillTester: Benchmarking Utility and Security of Agent Skills
  75. Data-Driven Estimation of the interfacial Dzyaloshinskii-Moriya Interaction with Machine Learning
  76. WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression
  77. GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback
  78. Interpretable Physics Extraction from Data for Linear Dynamical Systems using Lie Generator Networks
  79. Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly
  80. The Novelty Bottleneck: A Framework for Understanding Human Effort Scaling in AI-Assisted Work
  81. Improving Attributed Long-form Question Answering with Intent Awareness
  82. The Geometric Cost of Normalization: Affine Bounds on the Bayesian Complexity of Neural Networks
  83. Mind the Shape Gap: A Benchmark and Baseline for Deformation-Aware 6D Pose Estimation of Agricultural Produce
  84. AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases
  85. CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing
  86. Kempe Swap K-Means: A Scalable Near-Optimal Solution for Semi-Supervised Clustering
  87. Multiple-Prediction-Powered Inference
  88. The Hidden Costs of AI-Mediated Political Outreach: Persuasion and AI Penalties in the US and UK
  89. Grounding Social Perception in Intuitive Physics
  90. On the Relationship between Bayesian Networks and Probabilistic Structural Causal Models
  91. Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring
  92. Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
  93. Topological Detection of Hopf Bifurcations via Persistent Homology: A Functional Criterion from Time Series
  94. K-Means Based TinyML Anomaly Detection and Distributed Model Reuse via the Distributed Internet of Learning (DIoL)
  95. Active In-Context Learning for Tabular Foundation Models
  96. Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
  97. Where Does AI Leave a Footprint? Children's Reasoning About AI's Environmental Costs
  98. The Risk Quadrangle in Optimization: An Overview with Recent Results and Extensions
  99. Falcon Perception
  100. Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance
All 199
  1. Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation
  2. Guided Lensless Polarization Imaging
  3. Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach
  4. LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications
  5. Embedding Provenance in Computer Vision Datasets with JSON-LD
  6. TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR
  7. WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking
  8. A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling
  9. EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
  10. CounterMoral: Editing Morals in Language Models
  11. ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair
  12. Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models
  13. SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality
  14. Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification
  15. Multimodal Forecasting for Commodity Prices Using Spectrogram-Based and Time Series Representations
  16. Retrospective Counterfactual Prediction by Conditioning on the Factual Outcome: A Cross-World Approach
  17. TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba
  18. Scalable Maximum Entropy Population Synthesis via Persistent Contrastive Divergence
  19. MeshTailor: Cutting Seams via Generative Mesh Traversal
  20. GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
  21. Self-evolving AI agents for protein discovery and directed evolution
  22. Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution
  23. Complet4R: Geometric Complete 4D Reconstruction
  24. A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX
  25. Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes
  26. Class-Distribution Guided Active Learning for 3D Occupancy Prediction in Autonomous Driving
  27. Human-Centric Perception for Child Sexual Abuse Imagery
  28. StretchCast: Global-Regional AI Weather Forecasting on Stretched Cubed-Sphere Mesh
  29. Robust Global-Local Behavior Arbitration via Continuous Command Fusion Under LiDAR Errors
  30. Quantification of Credal Uncertainty: A Distance-Based Approach
  31. TrackMAE: Video Representation Learning via Track Mask and Predict
  32. TrendGen: An Outfit Recommendation and Display System
  33. MD-RWKV-UNet: Scale-Aware Anatomical Encoding with Cross-Stage Fusion for Multi-Organ Segmentation
  34. Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
  35. Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism
  36. Zero-shot Vision-Language Reranking for Cross-View Geolocalization
  37. IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment
  38. SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration
  39. SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track
  40. An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
  41. Can pre-trained Deep Learning models predict groove ratings?
  42. Structural Stress and Learned Helplessness in Afghanistan: A Multi-Layer Analysis of the AFSTRESS Dari Corpus
  43. NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather
  44. EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams
  45. HD-VGGT: High-Resolution Visual Geometry Transformer
  46. Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis
  47. Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentation
  48. KαLOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks
  49. Multi-AUV Ad-hoc Networks-Based Multi-Target Tracking Based on Scene-Adaptive Embodied Intelligence
  50. Conformal Prediction Assessment: A Framework for Conditional Coverage Evaluation and Selection
  51. Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention
  52. Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries
  53. MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation
  54. Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
  55. An End-to-end Flight Control Network for High-speed UAV Obstacle Avoidance based on Event-Depth Fusion
  56. MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization
  57. Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization
  58. RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation
  59. daVinci-LLM:Towards the Science of Pretraining
  60. Online Learning of Kalman Filtering: From Output to State Estimation
  61. Weakly Convex Ridge Regularization for 3D Non-Cartesian MRI Reconstruction
  62. GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph
  63. A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management
  64. Preconditioned Attention: Enhancing Efficiency in Transformers
  65. DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
  66. Learning to Predict Future-Aligned Research Proposals with Language Models
  67. Pan-Cancer Mapping of the Tumor Immune Landscape through Metagene Clustering and Predictive Modeling
  68. Follow Your Heart: Landmark-Guided Transducer Pose Scoring for Point-of-Care Echocardiography
  69. tBayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data
  70. A Mean Field Games Perspective on Evolutionary Clustering
  71. Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data
  72. Factorization Regret mediates compositional generalization in latent space
  73. Bayesian-Symbolic Integration for Uncertainty-Aware Parking Prediction
  74. Quantitative measurements of biological/chemical concentrations using smartphone cameras
  75. Gender-Based Heterogeneity in Youth Privacy-Protective Behavior for Smart Voice Assistants: Evidence from Multigroup PLS-SEM
  76. The Price of Meaning: Why Every Semantic Memory System Forgets
  77. SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation
  78. Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes
  79. Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation
  80. RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation
  81. MotiMem: Motion-Aware Approximate Memory for Energy-Efficient Neural Perception in Autonomous Vehicles
  82. UniDAC: Universal Metric Depth Estimation for Any Camera
  83. Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders
  84. LLM Enhanced Action Recognition via Hierarchical Global-Local Skeleton-Language Model
  85. PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
  86. Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models
  87. RDEx-MOP: Indicator-Guided Reconstructed Differential Evolution for Fixed-Budget Multiobjective Optimization
  88. RDEx-CSOP: Feasibility-Aware Reconstructed Differential Evolution with Adaptive epsilon-Constraint Ranking
  89. RDEx-SOP: Exploitation-Biased Reconstructed Differential Evolution for Fixed-Budget Bound-Constrained Single-Objective Optimization
  90. SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion
  91. Forecastability as an Information-Theoretic Limit on Prediction
  92. Voice-based debate with an AI adversary is associated with increased divergent ideation
  93. On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
  94. Story2Proposal: A Scaffold for Structured Scientific Paper Writing
  95. Conformalized Signal Temporal Logic Inference under Covariate Shift
  96. Towards Intrinsic-Aware Monocular 3D Object Detection
  97. Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning
  98. Persona-Based Simulation of Human Opinion at Population Scale
  99. Text Data Integration