mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 18 Oct 2025

163 papers

  1. TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  2. Reinforcement Learning for Accelerator Beamline Control: a simulation-based approachDeep reinforcement learning methods → RL for energy, networks and operations
  3. Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  4. Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action MemoryLLM reasoning → Reasoning for agents, planning and code +1
  5. CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code GenerationLLM agents and tool use → Software engineering coding agents
  6. TritonRL: Training LLMs to Think and Code Triton Without CheatingLLM reasoning → Reinforcement learning for reasoning
  7. HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applicationsKnowledge distillation → Detection and dense prediction distillation
  8. Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term ConvergenceSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  9. Adversarial Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Model UncertaintyDeep reinforcement learning methods → RL for robot navigation and UAV control
  10. Unleashing Diverse Thinking Modes in LLMs through Multi-Agent CollaborationLLM reasoning → Reasoning for agents, planning and code +1
  11. Structured Interfaces for Automated Reasoning with 3D Scene GraphsLLM reasoning → Spatial and embodied reasoning
  12. MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt OptimizationLLM reasoning → Prompting and chain-of-thought reasoning +1
  13. On the Impossibility of Retrain Equivalence in Machine UnlearningLLM safety and security → Machine unlearning
  14. MoS-VLA: A Vision-Language-Action Model with One-Shot Skill AdaptationVision-language-action models → Reinforcement learning and post-training
  15. Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic RewardsLLM reasoning → Reinforcement learning for reasoning
  16. Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time MethodsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  17. VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  18. SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability DefenseMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  19. Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  20. Ripple Effect Protocol: Coordinating Agent PopulationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. A First Look at the Security Issues in the Model Context Protocol EcosystemLLM agents and tool use → Agent threats, guardrails and governance
  22. Fit for Purpose? Deepfake Detection in the Real WorldDiffusion models → Image generation, text-to-image and editing
  23. LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  24. Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text DescriptionsLLM reasoning → Multimodal reasoning +1
  25. PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal InconsistenciesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  26. Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive BenchmarksEnd-to-end autonomous driving → End-to-end system architecture
  27. Automated Composition of Agents: A Knapsack Approach for Agentic Component SelectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  28. Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent SafetyLLM agents and tool use → Agent threats, guardrails and governance
  29. NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP ProblemsLLM reasoning → Reinforcement learning for reasoning
  30. Buzz, Choose, Forget: A Meta-Bandit Framework for Bee-Like Decision MakingOffline RL and imitation learning from data → Imitation learning methods
  31. RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement ReasoningLLM reasoning → Multimodal reasoning
  32. TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning ModelLLM reasoning → Test-time compute and efficient thinking
  33. Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  34. RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  35. EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model ReasoningLLM reasoning → Multimodal reasoning +1
  36. SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language ReasoningLLM reasoning → Multimodal reasoning +2
  37. Modeling Expert Interactions in Sparse Mixture of Experts via Graph StructuresMixture-of-experts → MoE large language models
  38. REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian SplattingLLM reasoning → Spatial and embodied reasoning +1
  39. RGMem: Renormalization Group-inspired Memory Evolution for Language AgentsLLM agents and tool use → Agent memory systems
  40. ATA: A Neuro-Symbolic Approach to Implement Autonomous and Trustworthy AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than OutcomesLLM reasoning → Reasoning benchmarks and evaluation
  42. Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMsLLM reasoning → Test-time compute and efficient thinking
  43. EditMark: Watermarking Large Language Models based on Model EditingLLM safety and security → Watermarking generated content and models
  44. Integrating LLM and Diffusion-Based Agents for Social SimulationLLM agents and tool use → Social simulation and multi-agent debate
  45. Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive CounterpartsDiffusion models → Robustness, privacy and adversarial aspects
  46. Thinking About Thinking: Evaluating Reasoning in Post-Trained Language ModelsLLM reasoning → Test-time compute and efficient thinking
  47. RL makes MLLMs see better than SFTMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  48. DiffusionX: Efficient Edge-Cloud Collaborative Image Generation with Multi-Round Prompt EvolutionDiffusion models → Diffusion foundations and sampling
  49. UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local AttentionDiffusion models → Diffusion foundations and sampling
  50. MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight VerifierLLM reasoning → Mathematical reasoning
  51. DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QALLM reasoning → Knowledge- and tool-augmented reasoning +1
  52. OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  53. QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  54. Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  55. Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment VerificationLLM reasoning → Spatial and embodied reasoning +1
  56. What Limits Agentic Systems Efficiency?LLM reasoning → Reasoning for agents, planning and code +1
  57. Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees
  58. Multi-Agent Pose Uncertainty: A Differentiable Rendering Cram'er-Rao Bound
  59. Promptable Fire Segmentation: Unleashing SAM2's Potential for Real-Time Mobile Deployment with Strategic Bounding Box Guidance
  60. EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning
  61. Bridging Accuracy and Interpretability: Deep Learning with XAI for Breast Cancer Detection
  62. What Causes Postoperative Aspiration?
  63. Fourier-Based GAN Fingerprint Detection using ResNet50
  64. When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
  65. Small Language Models Offer Significant Potential for Science Community
  66. Advances in Pre-trained Language Models for Domain-Specific Text Classification: A Systematic Review
  67. MIN-Merging: Merge the Important Neurons for Model Merging
  68. Hey Pentti, We Did It!: A Fully Vector-Symbolic Lisp
  69. Shock-Aware Physics-Guided Fusion-DeepONet Operator for Rarefied Micro-Nozzle Flows
  70. Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
  71. Metrics and evaluations for computational and sustainable AI efficiency
  72. When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking
  73. From Flows to Words: Can Zero-/Few-Shot LLMs Detect Network Intrusions? A Grammar-Constrained, Calibrated Evaluation on UNSW-NB15
  74. Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints
  75. Robust Dynamic Staffing with Predictions
  76. Safire: Similarity Framework for Visualization Retrieval
  77. Universal and Transferable Attacks on Pathology Foundation Models
  78. Large-Scale AI and Foundation Models for Neuroscience: A Comprehensive Review
  79. Simulation-free Structure Learning for Stochastic Population Dynamics
  80. ARCO-BO: Adaptive Resource-aware COllaborative Bayesian Optimization for Heterogeneous Multi-Agent Design
  81. MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models
  82. A Versatile Framework for Designing Group-Sparse Adversarial Attacks
  83. A three-step machine learning approach to predict market bubbles with financial news
  84. Self-Supervised Learning to Fly using Efficient Semantic Segmentation and Metric Depth Estimation for Low-Cost Autonomous UAVs
  85. Feedback Lunch: Learned Feedback Codes for Secure Communications
  86. Accelerated Learning on Large Scale Screens using Generative Library Models
  87. A Deep Learning Framework for Real-Time Image Processing in Medical Diagnostics: Enhancing Accuracy and Speed in Clinical Applications
  88. Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules
  89. Fine-tuning of Large Language Models for Constituency Parsing Using a Sequence to Sequence Approach
  90. Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
  91. Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
  92. Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration
  93. Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis
  94. Multi-Marginal Schr"odinger Bridge Matching
  95. Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
  96. AI-Generated Text Detection in Low-Resource Languages: A Case Study on Urdu
  97. Hallucination Benchmark for Speech Foundation Models
  98. Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models
  99. BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction
  100. Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence
All 163
  1. From Reviews to Actionable Insights: An LLM-Based Approach for Attribute and Feature Extraction
  2. ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation
  3. NeurIPT: Foundation Model for Neural Interfaces
  4. Predicting life satisfaction using machine learning and explainable AI
  5. Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition
  6. Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification
  7. Hey Pentti, We Did It Again!: Differentiable vector-symbolic types that prove polynomial termination
  8. Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks
  9. DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation
  10. Image Categorization and Search via a GAT Autoencoder and Representative Models
  11. eDCF: Estimating Intrinsic Dimension using Local Connectivity
  12. Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
  13. A Bayesian Framework for Symmetry Inference in Chaotic Attractors
  14. OOS-DSD: Improving Out-of-stock Detection in Retail Images using Auxiliary Tasks
  15. Edge-Based Speech Transcription and Synthesis for Kinyarwanda and Swahili Languages
  16. SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning
  17. Declarative Techniques for NL Queries over Heterogeneous Data
  18. ReviewSense: Transforming Customer Review Dynamics into Actionable Business Insights
  19. HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars
  20. Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations
  21. NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation
  22. Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
  23. VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
  24. Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance
  25. Colliding with Adversaries at ECML-PKDD 2025 Model Robustness Competition 1st Prize Solution
  26. Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution
  27. FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution
  28. LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
  29. What Questions Should Robots Be Able to Answer? A Dataset of User Questions for Explainable Robotics
  30. A Relative Error-Based Evaluation Framework of Heterogeneous Treatment Effect Estimators
  31. AoI-Aware Task Offloading and Transmission Optimization for Industrial IoT Networks: A Branching Deep Reinforcement Learning Approach
  32. SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
  33. Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades
  34. Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment
  35. Humanoid-inspired Causal Representation Learning for Domain Generalization
  36. Demeter: A Parametric Model of Crop Plant Morphology from the Real World
  37. Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization
  38. iWatchRoadv2: Pothole Detection, Geospatial Mapping, and Intelligent Road Governance
  39. Navigating through the hidden embedding space: steering LLMs to improve mental health assessment
  40. Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis
  41. MIRAD - A comprehensive real-world robust anomaly detection dataset for Mass Individualization
  42. The Burden of Interactive Alignment with Inconsistent Preferences
  43. End-to-End Argument Mining through Autoregressive Argumentative Structure Prediction
  44. Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets
  45. MLCPD: A Unified Multi-Language Code Parsing Dataset with Universal AST Schema
  46. Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with L1 Prior
  47. MGTS-Net: Exploring Graph-Enhanced Multimodal Fusion for Augmented Time Series Forecasting
  48. Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Models
  49. On the Provable Importance of Gradients for Language-Assisted Image Clustering
  50. Investigating the Association Between Text-Based Indications of Foodborne Illness from Yelp Reviews and New York City Health Inspection Outcomes (2023)
  51. TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
  52. Memorizing Long-tail Data Can Help Generalization Through Composition
  53. Time-Embedded Algorithm Unrolling for Computational MRI
  54. Scaling Laws for Deepfake Detection
  55. Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation
  56. Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
  57. Lung Cancer Classification from CT Images Using ResNet
  58. Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screening
  59. Synergizing chemical and AI communities for advancing laboratories of the future
  60. Disentangling Hyperedges through the Lens of Category Theory
  61. Instant Personalized Large Language Model Adaptation via Hypernetwork
  62. MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding
  63. Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch