mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 20 Jul 2025

156 papers

  1. Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAGMultimodal LLMs / vision-language models → Medical vision-language models
  2. MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  3. StaAgent: An Agentic Framework for Testing Static AnalyzersLLM agents and tool use → Software engineering coding agents
  4. Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform RepairingSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  5. Distributional Machine Unlearning via Selective Data RemovalLLM safety and security → Machine unlearning
  6. From Kicking to Causality: Simulating Infant Agency Detection with a Robust Intrinsic RewardDeep reinforcement learning methods → Deep RL algorithms and representations
  7. Robust Control with Gradient UncertaintyDeep reinforcement learning methods → RL for games and combinatorial optimization
  8. PET Image Reconstruction Using Deep Diffusion Image PriorDiffusion models → Medical imaging and segmentation
  9. Reinforcement Learning for Flow-Matching PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  10. StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image AnimationDiffusion models → Video generation
  11. DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt InjectionRetrieval-augmented generation → Privacy and security of RAG +1
  12. OmniVTON: Training-Free Universal Virtual Try-OnDiffusion models → 3D, point cloud and scene generation
  13. Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and UnderstandingLLM reasoning → Multimodal reasoning
  14. RefCritic: Training Long Chain-of-Thought Critic Models with Refinement FeedbackLLM reasoning → Reinforcement learning for reasoning
  15. MetaCrit: A Critical Thinking Framework for Self-Regulated LLM ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  16. The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software EngineeringLLM agents and tool use → Software engineering coding agents
  17. Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based RegressionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy TradingLLM agents and tool use → Financial trading and forecasting agents
  19. DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech SynthesisDiffusion models → Audio, speech and music
  20. AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement LearningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  21. Hierarchical Cross-modal Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  22. Complexity of Faceted Explanations in Propositional AbductionLLM reasoning → Reasoning benchmarks and evaluation
  23. MUR: Momentum Uncertainty guided Reasoning for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  24. Byzantine-Robust Decentralized Coordination of LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  25. Redefining Elderly Care with Agentic AI: Challenges and OpportunitiesLLM agents and tool use → Medical and scientific domain agents
  26. CoMoCAVs: Cohesive Decision-Guided Motion Planning for Connected and Autonomous Vehicles with Multi-Policy Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving +1
  27. Learning Nonlinear Causal Reductions to Explain Reinforcement Learning PoliciesDeep reinforcement learning methods → Deep RL algorithms and representations
  28. AgentFly: Extensible and Scalable Reinforcement Learning for LM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  29. SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMsMechanistic interpretability → SAE features and their applications
  30. MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair ExtractionLLM reasoning → Audio-language model reasoning
  31. Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context UnderstandingLLM reasoning → Reasoning benchmarks and evaluation +1
  32. Paired Image Generation with Diffusion-Guided Diffusion ModelsDiffusion models → Medical imaging and segmentation
  33. FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  34. SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  35. Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility TreeLLM agents and tool use → Agent threats, guardrails and governance +1
  36. Distilling Parallel Gradients for Fast ODE Solvers of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  37. Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task SchedulingLLM reasoning → Reinforcement learning for reasoning
  38. Rethinking Memorization Measures and their Implications in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  39. Piano: A Multi-Constraint Pin Assignment-Aware Floorplanner
  40. Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack Perspective
  41. Morphlux: Transforming Torus Fabrics for Efficient Multi-tenant ML
  42. From Propagator to Oscillator: The Dual Role of Symmetric Differential Equations in Neural Systems
  43. Theoretical Foundations and Mitigation of Hallucination in Large Language Models
  44. Full Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphs
  45. Research on the application of graph data structure and graph neural network in node classification/clustering tasks
  46. Quantizing Text-attributed Graphs for Semantic-Structural Integration
  47. MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation
  48. Enhancing Lung Disease Diagnosis via Semi-Supervised Machine Learning
  49. TD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning
  50. Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems
  51. Integrating Reason-Based Moral Decision-Making in the Reinforcement Learning Architecture
  52. Systole-Conditioned Generative Cardiac Motion
  53. Designing User-Centric Metrics for Evaluation of Counterfactual Explanations
  54. Resonant-Tunnelling Diode Reservoir Computing System for Image Recognition
  55. Can LLMs Generate User Stories and Assess Their Quality?
  56. Constraint-aware Learning of Probabilistic Sequential Models for Multi-Label Classification
  57. What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction
  58. Performance Analysis of Post-Training Quantization for CNN-based Conjunctival Pallor Anemia Detection
  59. Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection
  60. Design of an Edge-based Portable EHR System for Anemia Screening in Remote Health Applications
  61. Quantum Machine Learning for Secure Cooperative Multi-Layer Edge AI with Proportional Fairness
  62. NaviGNN: Multi-Agent Reinforcement Learning and Graph Neural Network for Sustainable Mobility in Futuristic Smart Cities
  63. A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
  64. Clinical Semantic Intelligence (CSI): Emulating the Cognitive Framework of the Expert Clinician for Comprehensive Oral Disease Diagnosis
  65. Transforming Datasets to Requested Complexity with Projection-based Many-Objective Genetic Algorithm
  66. Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction
  67. Automated planning with ontologies under coherence update semantics (Extended Version)
  68. U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecasting
  69. Graph Attention Networks for Detecting Epilepsy from EEG Signals Using Accessible Hardware in Low-Resource Settings
  70. From Disagreement to Understanding: The Case for Ambiguity Detection in NLI
  71. LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM
  72. AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI
  73. Commonsense on Demand: Generating and Selectively Integrating Commonsense Knowledge for Natural Language Inference
  74. Learning under Latent Group Sparsity via Diffusion on Networks
  75. BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking
  76. A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations
  77. Visual Place Recognition for Large-Scale UAV Applications
  78. Evaluation of Coding Schemes for Transformer-based Gene Sequence Modeling
  79. OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities
  80. Simulation-Prior Independent Neural Unfolding Procedure
  81. Isotonic Quantile Regression Averaging for uncertainty quantification of electricity price forecasts
  82. NavVI: A Telerobotic Simulation with Multimodal Feedback for Visually Impaired Navigation in Warehouse Environments
  83. ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model
  84. Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
  85. Quantum Annealing for Machine Learning: Applications in Feature Selection, Instance Selection, and Clustering
  86. Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper
  87. WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
  88. Rethinking Pan-sharpening: A New Training Process for Full-Resolution Generalization
  89. LibLMFuzz: LLM-Augmented Fuzz Target Generation for Black-box Libraries
  90. EBA-AI: Ethics-Guided Bias-Aware AI for Efficient Underwater Image Enhancement and Coral Reef Monitoring
  91. OpenBreastUS: Benchmarking Neural Operators for Wave Imaging Using Breast Ultrasound Computed Tomography
  92. The hunt for new pulsating ultraluminous X-ray sources: a clustering approach
  93. Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
  94. Integrating Newton's Laws with deep learning for enhanced physics-informed compound flood modelling
  95. A Forced-Choice Neural Cognitive Diagnostic Model of Personality Testing
  96. FastSmoothSAM: A Fast Smooth Method For Segment Anything Model
  97. Hear Your Code Fail, Voice-Assisted Debugging for Python
  98. Axis-Aligned Document Dewarping
  99. Clustered Federated Learning for Generalizable FDIA Detection in Smart Grids with Heterogeneous Data
  100. FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios
All 156
  1. FCRF: Flexible Constructivism Reflection for Long-Horizon Robotic Task Planning with Large Language Models
  2. Decision PCR: Decision version of the Point Cloud Registration task
  3. A Comparative Analysis of Statistical and Machine Learning Models for Outlier Detection in Bitcoin Limit Order Books
  4. Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
  5. Probing EFX via PMMS: (Non-)Existence Results in Discrete Fair Division
  6. FullRecall: A Semantic Search-Based Ranking Approach for Maximizing Recall in Patent Retrieval
  7. Open-set Cross Modal Generalization via Multimodal Unified Representation
  8. Probabilistic smooth attention for deep multiple instance learning in medical imaging
  9. 3-Dimensional CryoEM Pose Estimation and Shift Correction Pipeline
  10. Synthia: Scalable Grounded Persona Generation from Social Media Data
  11. Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction
  12. Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning
  13. Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification
  14. One Step Beyond: Feedthrough & Placement-Aware Rectilinear Floorplanner
  15. PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
  16. The Endless Tuning. An Artificial Intelligence Design To Avoid Human Replacement and Trace Back Responsibilities
  17. Feedback-Induced Performance Decline in LLM-Based Decision-Making
  18. TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
  19. U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs
  20. From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment
  21. InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis
  22. BeatFormer: Efficient motion-robust remote heart rate estimation through unsupervised spectral zoomed attention filters
  23. Application-Specific Component-Aware Structured Pruning of Deep Neural Networks in Control via Soft Coefficient Optimization
  24. Region-aware Depth Scale Adaptation with Sparse Measurements
  25. The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs
  26. Tiny language models
  27. Hybrid-supervised Hypergraph-enhanced Transformer for Micro-gesture Based Emotion Recognition
  28. An Uncertainty-aware DETR Enhancement Framework for Object Detection
  29. A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption
  30. Grounding Degradations in Natural Language for All-In-One Video Restoration
  31. Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
  32. Time-Aware Attention for Enhanced Electronic Health Records Modeling
  33. Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Image
  34. The Invisible Leash: Why RLVR May or May Not Escape Its Origin
  35. Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization
  36. Differentially Private Synthetic Graphs Preserving Triangle-Motif Cuts
  37. eMargin: Revisiting Contrastive Learning with Margin-Based Separation
  38. PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing
  39. Benchmarking Foundation Models with Multimodal Public Electronic Health Records
  40. Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents
  41. FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
  42. Light Future: Multimodal Action Frame Prediction via InstructPix2Pix
  43. Decoding RWA Tokenized U.S. Treasuries: Functional Dissection and Address Role Inference
  44. Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection
  45. Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
  46. ACME: Adaptive Customization of Large Models via Distributed Systems
  47. Exploring Scalable Unified Modeling for General Low-Level Vision
  48. Large Language Model as An Operator: An Experience-Driven Solution for Distribution Network Voltage Control
  49. An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks
  50. A DPI-PAC-Bayesian Framework for Generalization Bounds
  51. Flow Equivariant Recurrent Neural Networks
  52. A Novel Downsampling Strategy Based on Information Complementarity for Medical Image Segmentation
  53. FOCUS: Fused Observation of Channels for Unveiling Spectra
  54. Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs
  55. LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering
  56. Uncertainty Quantification for Machine Learning-Based Prediction: A Polynomial Chaos Expansion Approach for Joint Model and Input Uncertainty Propagation