mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 29 Mar 2026

190 papers

  1. LUMEN: Cost-Transparent Multi-Agent Pipeline for Automated Systematic Review and Meta-AnalysisLLM agents and tool use → Web, search, and research agents
  2. Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offsLLM safety and security → Prompt injection and agent security
  3. Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language LearningLLM agents and tool use → Social simulation and multi-agent debate
  4. Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMsLLM reasoning → Test-time compute and efficient thinking
  5. ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score PredictionRetrieval-augmented generation → Legal and financial RAG
  6. QU-NLP at QIAS 2026: Multi-Stage QLoRA Fine-Tuning for Arabic Islamic Inheritance ReasoningLLM reasoning → Reasoning for agents, planning and code
  7. Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)Efficient LLM inference and serving → Serving systems and request scheduling
  8. Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  9. GAAMA: Graph Augmented Associative Memory for AgentsLLM agents and tool use → Agent memory systems
  10. ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime ControlLLM agents and tool use → Software engineering coding agents
  11. R'enyi Entropy: A New Token Pruning Metric for Vision TransformersEfficient LLM inference and serving → Visual token pruning in multimodal models
  12. SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  13. Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial RewardsDeep reinforcement learning methods → RL theory and sample complexity
  14. Wan-R1: Verifiable-Reinforcement Learning for Video ReasoningLLM reasoning → Multimodal reasoning
  15. EffiSkill: Agent Skill Based Automated Code Efficiency OptimizationLLM agents and tool use → Software engineering coding agents
  16. Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3LLM reasoning → Test-time compute and efficient thinking
  17. Improving Clinical Diagnosis with Counterfactual Multi-Agent ReasoningLLM reasoning → Clinical and biomedical applications +1
  18. KVSculpt: KV Cache Compression as DistillationEfficient LLM inference and serving → KV cache optimization
  19. MuSEAgent: A Multimodal Reasoning Agent with Stateful ExperiencesLLM reasoning → Multimodal reasoning +1
  20. Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive ScienceLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
  22. TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail EntitiesRetrieval-augmented generation → RAG pipeline design and evaluation
  23. AutoStan: Autonomous Bayesian Model Improvement via Predictive FeedbackLLM agents and tool use → Web, search, and research agents
  24. Let the Agent Steer: Closed-Loop Ranking Optimization via Influence ExchangeLLM agents and tool use → Agentic recommender systems
  25. When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  26. Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAGRetrieval-augmented generation → Hallucination detection in RAG
  27. SkyNet: Belief-Aware Planning for Partially-Observable Stochastic GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  28. Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository EditsLLM agents and tool use → Software engineering coding agents
  29. Data Organization Matters in Multimodal Instruction Tuning: A Controlled Study of Capability Trade-offsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  30. TIR-Agent: Training an Explorative and Efficient Agent for Image RestorationLLM agents and tool use → Multimodal and embodied agents
  31. Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
  32. KAT-Coder-V2 Technical ReportLLM agents and tool use → Software engineering coding agents
  33. Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz CompositionDeep reinforcement learning methods → RL training of language and agent models
  34. Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?LLM reasoning → Reasoning benchmarks and evaluation
  35. LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and GenerationLLM reasoning → Multimodal reasoning +1
  36. Customized Visual Storytelling with Unified Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  37. ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic ManipulationVision-language-action models → Efficient VLA inference and adaptation +1
  38. V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  39. PRBench: End-to-end Paper Reproduction in Physics ResearchLLM reasoning → Spatial and embodied reasoning
  40. OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image GenerationDiffusion models → Image generation, text-to-image and editing
  41. Umwelt Engineering: Designing the Cognitive Worlds of Linguistic AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory SchedulingMixture-of-experts → Efficient MoE training and inference systems
  43. You Only Erase Once: Erasing Anything without Bringing Unexpected ContentDiffusion models → Robustness, privacy and adversarial aspects
  44. STRIDE: When to Speak Meets Sequence Denoising for Streaming Video UnderstandingLLM reasoning → Multimodal reasoning
  45. Fundamental Limits of Man-in-the-Middle Attack Detection in Model-Free Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  46. LLM-Enabled Low-Altitude UAV Natural Language Navigation via Signal Temporal Logic Specification Translation and RepairLLM reasoning → Spatial and embodied reasoning
  47. RAGent: Physics-Aware Agentic Reasoning for Training-Free mmWave Human Activity RecognitionLLM reasoning → Spatial and embodied reasoning
  48. InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for IntrospectionLLM agents and tool use → Social simulation and multi-agent debate
  49. Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  50. Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost AwarenessLLM agents and tool use → Financial trading and forecasting agents
  51. Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRsLLM agents and tool use → Software engineering coding agents
  52. Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  53. TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial SpaceDiffusion models → Video generation
  54. Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  55. A Security Analysis of the OpenClaw AI Agent FrameworkLLM reasoning → Reasoning for agents, planning and code +1
  56. Match or Replay: Self Imitating Proximal Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  57. Understanding Semantic Perturbations on In-Processing Generative Image WatermarksLLM safety and security → Watermarking generated content and models
  58. Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLMMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMsLLM reasoning → Multimodal reasoning +1
  60. AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web AgentsLLM agents and tool use → Agent memory systems
  61. Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement LearningLLM reasoning → Multimodal reasoning
  62. On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  63. Driving Condition-Aware Multi-Agent Integrated Power and Thermal Management for Hybrid Electric VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving
  64. KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical StudyEfficient LLM inference and serving → Fast autoregressive visual generation
  65. TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle QuantizationEfficient LLM inference and serving → KV cache quantization
  66. Multi-Agent Dialectical Refinement for Enhanced Argument ClassificationLLM agents and tool use → Social simulation and multi-agent debate
  67. FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  68. RAINO: Anchoring Agents in Reality, A Systematic Review and Conceptual Framework for Realism in Agent-Based Modelling
  69. The Randomness Floor: Measuring Intrinsic Non-Randomness in Language Model Token Distributions
  70. The Root Theorem of Context Engineering
  71. Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment
  72. Instructor-Created Custom GPTs as Pedagogical Partners Fostering Immersion in Online Higher Education: Two Case Studies
  73. Dynamic Forecasting and Temporal Feature Evolution of Stock Repurchases in Listed Companies Using Attention-Based Deep Temporal Networks
  74. WearBCI Dataset: Understanding and Benchmarking Real-World Wearable Brain-Computer Interfaces Signals
  75. Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation
  76. Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
  77. AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System
  78. MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement
  79. Computational Foundations for Strategic Coopetition: Formalizing Sequential Interaction and Reciprocity
  80. Large Language Models for Analyzing Enterprise Architecture Debt in Unstructured Documentation
  81. DriftScript: A Domain-Specific Language for Programming Non-Axiomatic Reasoning Agents
  82. Incentives, Equilibria, and the Limits of Healthcare AI: A Game-Theoretic Perspective
  83. SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
  84. Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs
  85. Spatial Orthogonal Refinement for Robust RGB-Event Visual Object Tracking
  86. An Empirical Markov Chain Car-Following (MC-CF) Model
  87. BINO: Encoder Centric Self Supervised Stereo With Native Pair Input
  88. Persistence diagrams of random matrices via Morse theory: universality and a new spectral diagnostic
  89. Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimation
  90. Article and Comment Frames Shape the Quality of Online Comments
  91. AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D
  92. Spectral Signatures of Data Quality: Eigenvalue Tail Index as a Diagnostic for Label Noise in Neural Networks
  93. Kernel Dynamics under Path Entropy Maximization
  94. HumMusQA: A Human-written Music Understanding QA Benchmark Dataset
  95. Stability and Sensitivity Analysis of Relative Temporal-Difference Learning: Extended Version
  96. Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences
  97. A Revealed Preference Framework for AI Alignment
  98. Vertical Consensus Inference for High-Dimensional Random Partition
  99. ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
  100. KazByte: Adapting Qwen models to Kazakh via Byte-level Adapter
All 190
  1. CARGO: Carbon-Aware Gossip Orchestration in Smart Shipping
  2. What can LLMs tell us about the mechanisms behind polarity illusions in humans? Experiments across model scales and training steps
  3. ProText: A benchmark dataset for measuring (mis)gendering in long-form texts
  4. Q-Bridge: Code Translation for Quantum Machine Learning via LLMs
  5. 3-D Representations for Hyperspectral Flame Tomography
  6. jaxsgp4: GPU-accelerated mega-constellation propagation with batch parallelism
  7. Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras
  8. Towards Context-Aware Image Anonymization with Multi-Agent Reasoning
  9. RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series
  10. Tracking without Seeing: Geospatial Inference using Encrypted Traffic from Distributed Nodes
  11. Understanding Teacher Revisions of Large Language Model-Generated Feedback
  12. Distributed Online Submodular Maximization under Communication Delays: A Simultaneous Decision-Making Approach
  13. Engineering Mythology: A Digital-Physical Framework for Culturally-Inspired Public Art
  14. Towards Emotion Recognition with 3D Pointclouds Obtained from Facial Expression Images
  15. What-If Explanations Over Time: Counterfactuals for Time Series Classification
  16. Inference-time Trajectory Optimization for Structure-Preserving Manga Image Editing
  17. GS3LAM: Gaussian Semantic Splatting SLAM
  18. Exploring Student Perception on Gen AI Adoption in Higher Education: A Descriptive Study
  19. RINO: Rotation-Invariant Non-Rigid Correspondences
  20. Emergent Risks in Generative Multi-Agent Systems
  21. RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
  22. E-TIDE: Fast, Structure-Preserving Motion Forecasting from Event Sequences
  23. Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control
  24. AI-Powered Facial Mask Removal Is Not Suitable For Identification
  25. Empirical Likelihood for Nonsmooth Functionals
  26. Segmenting Superbubbles in a Simulated Multiphase Interstellar Medium using Computer Vision
  27. TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric science
  28. Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training
  29. Suppression of 14C photon hits in large liquid scintillator detectors via spatiotemporal deep learning
  30. TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution
  31. Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting
  32. The role of neuromorphic principles in the future of biomedicine and healthcare
  33. Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes
  34. RAP: Retrieve, Adapt, and Prompt-Fit for Training-Free Few-Shot Medical Image Segmentation
  35. Ink Detection from Surface Topography of the Herculaneum Papyri
  36. Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?
  37. CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning
  38. Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization
  39. Energy Score-Guided Neural Gaussian Mixture Model for Predictive Uncertainty Quantification
  40. EvA: An Evidence-First Audio Understanding Paradigm for LALMs
  41. Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
  42. Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling
  43. Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMs
  44. LiDAR for Crowd Management: Applications, Benefits, and Future Directions
  45. A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos
  46. Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection
  47. The Degree of Language Diacriticity and Its Effect on Tasks
  48. Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African Languages
  49. OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
  50. ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation
  51. On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry
  52. RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning
  53. DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Flexible Job Shop with LLM-Evolved Heuristic Portfolios
  54. Clore: Interactive Pathology Image Segmentation with Click-based Local Refinement
  55. What Does a System Modify When It Modifies Itself?
  56. Calibration and transfer in indicator-based assessments of artificial consciousness
  57. An Energy-Efficient Spiking Neural Network Architecture for Predictive Insulin Delivery
  58. A Robust Low-Rank Prior Model for Structured Cartoon-Texture Image Decomposition with Heavy-Tailed Noise
  59. Structured Observation Language for Efficient and Generalizable Vision-Language Navigation
  60. A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators
  61. Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
  62. PANDORA: Pixel-wise Attention Dissolution and Latent Guidance for Zero-Shot Object Removal
  63. Annotation-Free Detection of Drivable Areas and Curbs Leveraging LiDAR Point Cloud Maps
  64. BLOSSOM: Block-wise Federated Learning Over Shared and Sparse Observed Modalities
  65. Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs
  66. MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction
  67. A Novel Immune Algorithm for Multiparty Multiobjective Optimization
  68. LongCat-Next: Lexicalizing Modalities as Discrete Tokens
  69. Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance
  70. Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation
  71. OmniColor: A Unified Framework for Multi-modal Lineart Colorization
  72. A gentle tutorial on Bock's algorithm for minimum directed spanning trees with a structured reformulation
  73. Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
  74. Visualization of Machine Learning Models through Their Spatial and Temporal Listeners
  75. Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization
  76. SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotyping
  77. SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering
  78. Decomposing Discrimination: Causal Mediation Analysis for AI-Driven Credit Decisions
  79. Transferring Physical Priors into Remote Sensing Segmentation via Large Language Models
  80. Streamlined Open-Vocabulary Human-Object Interaction Detection
  81. STATrack: A Target-Aware Fully Spiking Neural Network for Efficient UAV Tracking
  82. Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding
  83. Variational Learning of Fractional Posteriors
  84. Estimating the Impact of COVID-19 on Travel Demand in Houston Area Using Deep Learning and Satellite Imagery
  85. PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded Verification
  86. RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication
  87. Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development
  88. A tree interpretation of arc standard dependency derivation
  89. Optimal Demixing of Nonparametric Densities
  90. From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis