mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 25 Apr 2025

240 papers

  1. Human-In-The-Loop Software Development Agents: Challenges and Future DirectionsLLM agents and tool use → Software engineering coding agents
  2. A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1LLM reasoning → Clinical and biomedical applications
  3. Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  4. VideoMultiAgents: A Multi-Agent Framework for Video Question AnsweringLLM reasoning → Multimodal reasoning
  5. Understanding and Mitigating Risks of Generative AI in Financial ServicesLLM safety and security → Prompt injection and agent security
  6. Evolution of AI in Education: Agentic WorkflowsLLM agents and tool use → Educational agents and math problem solving
  7. Dream-Box: Object-wise Outlier Generation for Out-of-Distribution DetectionDiffusion models → Medical imaging and segmentation
  8. From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive StepsizesDeep reinforcement learning methods → RL theory and sample complexity
  9. A Review of 3D Object Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  10. Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data AssimilationDiffusion models → Flow matching, time series and science
  11. SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  12. Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) PredictionLLM reasoning → Clinical and biomedical applications +1
  13. Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: √T-RegretDeep reinforcement learning methods → Safe and constrained RL
  14. Generalization Capability for Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  15. TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language GenerationLLM reasoning → Test-time compute and efficient thinking
  16. Scaling Laws For Scalable OversightLLM safety and security → Prompt injection and agent security
  17. Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup FunctionalDiffusion models → Flow matching, time series and science
  18. Instrumentation for Better Demonstrations: A Case StudyOffline RL and imitation learning from data → Robot learning from demonstration
  19. Action Flow Matching for Continual Robot LearningDiffusion models → Diffusion and flow policies for robotics
  20. Fast-Slow Thinking GRPO for Large Vision-Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  21. Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report GenerationLLM reasoning → Clinical and biomedical applications
  22. NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and CollaborationWorld models → Video-generation world models and simulators
  23. PolyMath: Evaluating Mathematical Reasoning in Multilingual ContextsLLM reasoning → Mathematical reasoning
  24. HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial ModelsDiffusion models → Medical imaging and segmentation
  25. Unsupervised Visual Chain-of-Thought Reasoning via Preference OptimizationLLM reasoning → Multimodal reasoning +2
  26. Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI ModelsLLM reasoning → Reinforcement learning for reasoning
  27. Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal AssistantLLM agents and tool use → GUI and mobile agents
  28. Revisiting Data Auditing in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  29. Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt InjectionsLLM safety and security → Prompt injection and agent security
  30. STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  31. Towards Adaptive Software Agents for DebuggingLLM agents and tool use → Software engineering coding agents
  32. Deep Reinforcement Learning Based Navigation with Macro Actions and Topological MapsDeep reinforcement learning methods → RL for robot navigation and UAV control
  33. MAGI: Multi-Agent Guided Interview for Psychiatric AssessmentLLM agents and tool use → Medical and scientific domain agents
  34. Depth-Constrained ASV Navigation with Deep RL and Limited SensingDeep reinforcement learning methods → RL for robot navigation and UAV control
  35. One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn ReasoningLLM reasoning → Test-time compute and efficient thinking
  36. Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model FamilyLLM reasoning → Knowledge- and tool-augmented reasoning +1
  37. Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference UnderstandingDiffusion models → Diffusion and flow policies for robotics
  38. Aligning Language Models for Icelandic Legal Text SummarizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  39. Offline Learning of Controllable Diverse BehaviorsOffline RL and imitation learning from data → Imitation learning methods
  40. ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  41. Think, Prune, Train, Improve: Scaling Reasoning without Scaling ModelsLLM reasoning → Test-time compute and efficient thinking
  42. Learning from Less: SINDy Surrogates in RLDeep reinforcement learning methods → RL for robot navigation and UAV control
  43. Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait GenerationDiffusion models → Audio, speech and music
  44. RL-Driven Data Generation for Robust Vision-Based Dexterous GraspingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  45. Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference OptimizationLLM reasoning → Clinical and biomedical applications +1
  46. PropRAG: Guiding Retrieval with Beam Search over Proposition PathsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  47. S3MOT: Monocular 3D Object Tracking with Selective State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  48. DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  49. RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language ModelsRetrieval-augmented generation → Privacy and security of RAG +1
  50. MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of MindLLM reasoning → Reasoning for agents, planning and code +1
  51. Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  52. A Large Vision-Language Model based Environment Perception System for Visually Impaired PeopleMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  53. Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  54. SMARTFinRAG: Interactive Modularized Financial RAG BenchmarkRetrieval-augmented generation → Legal and financial RAG
  55. Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future TransportationEnd-to-end autonomous driving → Cooperative and V2X driving +1
  56. Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  57. Back to Fundamentals: Low-Level Visual Features Guided Progressive Token PruningEfficient LLM inference and serving → Token pruning and merging for ViTs
  58. Human Creativity and AI
  59. Data Science: a Natural Ecosystem
  60. Anti-adversarial Learning: Desensitizing Prompts for Large Language Models
  61. CORG: Generating Answers from Complex, Interrelated Contexts
  62. Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings
  63. Self-Healing Software Systems: Lessons from Nature, Powered by AI
  64. An Integrated Framework for Contextual Personalized LLM-Based Food Recommendation
  65. Spark: A System for Scientifically Creative Idea Generation
  66. Deep Learning vs. Black-Scholes: Option Pricing Performance on Brazilian Petrobras Stocks
  67. AI Awareness
  68. A model and package for German ColBERT
  69. DNAD: Differentiable Neural Architecture Distillation
  70. FX-DARTS: Designing Topology-unconstrained Architectures with Differentiable Architecture Search and Entropy-based Super-network Shrinking
  71. Low-Rank Matrix Approximation for Neural Network Compression
  72. Edge-Based Learning for Improved Classification Under Adversarial Noise
  73. EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Papers
  74. TLoRA: Tri-Matrix Low-Rank Adaptation of Large Language Models
  75. Multimodal graph representation learning for website generation based on visual sketch
  76. World Food Atlas Project
  77. MODP: Multi Objective Directional Prompting
  78. Building UD Cairo for Old English in the Classroom
  79. Spatial Speech Translation: Translating Across Space With Binaural Hearables
  80. Explicit neural network classifiers for non-separable data
  81. Active Few-Shot Learning for Vertex Classification Starting from an Unlabeled Dataset
  82. Local Polynomial Lp-norm Regression
  83. Technical Challenges in Maintaining Tax Prep Software with Large Language Models
  84. From Prompts to Propositions: A Logic-Based Lens on Student-LLM Interactions
  85. HierSum: A Global and Local Attention Mechanism for Video Summarization
  86. Transformational Creativity in Science: A Graphical Theory
  87. A Unified MDL-based Binning and Tensor Factorization Framework for PDF Estimation
  88. Can Third-parties Read Our Emotions?
  89. Exploring the Potential of Latent Embeddings for Sea Ice Characterization using ICESat-2 Data
  90. Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning
  91. M2R2: MultiModal Robotic Representation for Temporal Action Segmentation
  92. The Big Send-off: Scalable and Performant Collectives for Deep Learning
  93. Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development
  94. Unsupervised outlier detection to improve bird audio dataset labels
  95. Span-Level Hallucination Detection for LLM-Generated Answers
  96. A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection
  97. Statistical Inference for Clustering-based Anomaly Detection
  98. Research on Personalized Medical Intervention Strategy Generation System based on Group Relative Policy Optimization and Time-Series Data Fusion
  99. Periodic Online Testing for Sparse Systolic Tensor Arrays
  100. Validation and Calibration of Semi-Analytical Models for the Event Horizon Telescope Observations of Sagittarius A*
All 240
  1. Explainable Deep-Learning Based Potentially Hazardous Asteroids Classification Using Graph Neural Networks
  2. A Cognitive-Mechanistic Human Reliability Analysis Framework: A Nuclear Power Plant Case Study
  3. Adapting Probabilistic Risk Assessment for AI
  4. Augmenting Perceptual Super-Resolution via Image Quality Predictors
  5. Extrapolation Guarantees for Perturbation Modeling Under the Additive Latent Shift Assumption
  6. E-VLC: A Real-World Dataset for Event-based Visible Light Communication And Localization
  7. RSFR: A Coarse-to-Fine Reconstruction Framework for Diffusion Tensor Cardiac MRI with Semantic-Aware Refinement
  8. Intelligent Attacks and Defense Methods in Federated Learning-enabled Energy-Efficient Wireless Networks
  9. PODNO: Proper Orthogonal Decomposition Neural Operators
  10. Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
  11. Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
  12. Enhancing Visual Interpretability and Explainability in Functional Survival Trees and Forests
  13. DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statistics
  14. An Improved ResNet50 Model for Predicting Pavement Condition Index (PCI) Directly from Pavement Images
  15. Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues
  16. Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions
  17. RGS-DR: Deferred Reflections and Residual Shading in 2D Gaussian Splatting
  18. Discovering Governing Equations of Geomagnetic Storm Dynamics with Symbolic Regression
  19. Multiview Representation Learning via Distributed Joint Latent Space Structuring
  20. Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
  21. Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning
  22. Iterative Event-based Motion Segmentation by Variational Contrast Maximization
  23. Boosting-Enabled Robust System Identification of Partially Observed LTI Systems Under Heavy-Tailed Noise
  24. Pseudo-Boolean Proof Logging for Optimal Classical Planning
  25. Imaging Biomarkers for Neurodegenerative Diseases from Detailed Segmentation of Medial Temporal Lobe Subregions on in vivo Brain MRI Using Upsampling Strategy Guided by High-resolution ex vivo MRI
  26. Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
  27. An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
  28. Kimi-Audio Technical Report
  29. LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
  30. LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection
  31. A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detection
  32. BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
  33. Online learning to accelerate nonlinear PDE solvers: applied to multiphase porous media flow
  34. Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers
  35. HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?
  36. Paradigm shift on Coding Productivity Using GenAI
  37. A Multimodal Deep Learning Approach for White Matter Shape Prediction in Diffusion MRI Tractography
  38. Partition Map-Based Fast Block Partitioning for VVC Inter Coding
  39. Three Types of Calibration with Properties and their Semantic and Formal Relationships
  40. Machine Learning and Statistical Insights into Hospital Stay Durations: The Italian EHR Case
  41. A UD Treebank for Bohairic Coptic
  42. Model Evaluation in the Dark: Robust Classifier Metrics with Missing Labels
  43. Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation
  44. Spatial Reasoner: A 3D Inference Pipeline for XR Applications
  45. Explainable AI for UAV Mobility Management: A Deep Q-Network Approach for Handover Minimization
  46. A Novel 4-D Dataset Paradigm for Studying Complete Ligand-Protein Dissociation Dynamics
  47. COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations
  48. Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes
  49. Testing Individual Fairness in Graph Neural Networks
  50. TSCL:Multi-party loss Balancing scheme for deep learning Image steganography based on Curriculum learning
  51. Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review
  52. NUDF: Neural Unsigned Distance Fields for high resolution 3D medical image segmentation
  53. SSD-Poser: Avatar Pose Estimation with State Space Duality from Sparse Observations
  54. PHEATPRUNER: Interpretable Data-centric Feature Selection for Multivariate Time Series Classification through Persistent Homology
  55. Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation
  56. Outlier-aware Tensor Robust Principal Component Analysis with Self-guided Data Augmentation
  57. Task-Oriented Semantic Compression for Localization at the Network Edge
  58. How much does context affect the accuracy of AI health advice?
  59. SSA-UNet: Advanced Precipitation Nowcasting via Channel Shuffling
  60. Enhancing Long-Term Re-Identification Robustness Using Synthetic Data: A Comparative Analysis
  61. Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator
  62. A comprehensive review of classifier probability calibration metrics
  63. Structural Inference: Interpreting Small Language Models with Susceptibilities
  64. Efficient Learning on Large Graphs using a Densifying Regularity Lemma
  65. Large Language Model-Based Intelligent Antenna Design System
  66. TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation
  67. Towards a deep learning approach for classifying treatment response in glioblastomas
  68. Neural operators struggle to learn complex PDEs in pedestrian mobility: Hughes model case study
  69. Local Statistical Parity for the Estimation of Fair Decision Trees
  70. SSL4Eco: A Global Seasonal Dataset for Geospatial Foundation Models in Ecology
  71. Event-Based Eye Tracking. 2025 Event-based Vision Workshop
  72. DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering
  73. Switch-Based Multi-Part Neural Network
  74. BiasBench: A reproducible benchmark for tuning the biases of event cameras
  75. Dense Geometry Supervision for Underwater Depth Estimation
  76. Time and Frequency Domain-based Anomaly Detection in Smart Meter Data for Distribution Network Studies
  77. Learning to fuse: dynamic integration of multi-source data for accurate battery lifespan prediction
  78. Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish
  79. Unify3D: An Augmented Holistic End-to-end Monocular 3D Human Reconstruction via Anatomy Shaping and Twins Negotiating
  80. A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenes
  81. Post-Transfer Learning Statistical Inference in High-Dimensional Regression
  82. Numerical Generalized Randomized Hamiltonian Monte Carlo for piecewise smooth target densities
  83. Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
  84. Gradient Descent as a Shrinkage Operator for Spectral Bias
  85. A Machine Learning Approach For Bitcoin Forecasting
  86. LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring
  87. Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition
  88. What is the Added Value of UDA in the VFM Era?
  89. An Open-Source and Reproducible Implementation of LSTM and GRU Networks for Time Series Forecasting
  90. Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
  91. Unveiling 3D Ocean Biogeochemical Provinces in the North Atlantic: A Systematic Comparison and Validation of Clustering Methods
  92. Label-independent hyperparameter-free self-supervised single-view deep subspace clustering
  93. Fast approximate estimation of conditional Shapley values when using a linear explainer
  94. PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models
  95. E-InMeMo: Enhanced Prompting for Visual In-Context Learning
  96. A Generative Graph Contrastive Learning Model with Global Signal
  97. NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
  98. EDU-NER-2025: Named Entity Recognition in Urdu Educational Texts using XLM-RoBERTa with X (formerly Twitter)
  99. MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View
  100. Tree Boosting Methods for Balanced andImbalanced Classification and their Robustness Over Time in Risk Assessment
  101. Score-based deterministic density sampling
  102. Temporal Entailment Pretraining for Clinical Language Models over EHR Data
  103. Towards Arbitrary-Scale Spacecraft Image Super-Resolution via Salient Region-Guidance
  104. Lecture Notes on Normalizing Flows for Lattice Quantum Field Theories
  105. Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
  106. Study on Real-Time Road Surface Reconstruction Using Stereo Vision
  107. Comparative Study on the Discourse Meaning of Chinese and English Media in the Paris Olympics Based on LDA Topic Modeling Technology and LLM Prompt Engineering
  108. Temperature Estimation in Induction Motors using Machine Learning
  109. Application and Optimization of Large Models Based on Prompt Tuning for Fact-Check-Worthiness Estimation
  110. Bayesian Quantum Orthogonal Neural Networks for Anomaly Detection
  111. Tracking Articulatory Dynamics in Speech with a Fixed-Weight BiLSTM-CNN Architecture
  112. Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation
  113. Subject-independent Classification of Meditative State from the Resting State using EEG
  114. Reliable and efficient inverse analysis using physics-informed neural networks with normalized distance functions and adaptive weight tuning
  115. Random-Set Large Language Models
  116. Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
  117. Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity
  118. A Model Zoo on Phase Transitions in Neural Networks
  119. Physics-Driven Neural Compensation For Electrical Impedance Tomography
  120. LLM-hRIC: LLM-empowered Hierarchical RAN Intelligent Control for O-RAN
  121. POET: Prompt Offset Tuning for Continual Human Action Adaptation
  122. Exploring Personality-Aware Interactions in Salesperson Dialogue Agents
  123. Opportunistic Collaborative Planning with Large Vision Model Guided Control and Joint Query-Service Optimization
  124. Validating Network Protocol Parsers with Traceable RFC Document Interpretation
  125. A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images
  126. Modes of Sequence Models and Learning Coefficients
  127. DMS-Net:Dual-Modal Multi-Scale Siamese Network for Binocular Fundus Image Classification
  128. AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How
  129. Cabbage: A Differential Growth Framework for Open Surfaces
  130. ShapeSpeak: Body Shape-Aware Textual Alignment for Visible-Infrared Person Re-Identification
  131. Federated Client-tailored Adapter for Medical Image Segmentation
  132. Non-identifiability distinguishes Neural Networks among Parametric Models
  133. DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
  134. Memory Reviving, Continuing Learning and Beyond: Evaluation of Pre-trained Encoders and Decoders for Multimodal Machine Translation
  135. TGDT: A Temporal Graph-based Digital Twin for Urban Traffic Corridors
  136. Differential Privacy-Driven Framework for Enhancing Heart Disease Prediction
  137. Self-Balancing, Memory Efficient, Dynamic Metric Space Data Maintenance, for Rapid Multi-Kernel Estimation
  138. Improving Language Model Personas via Rationalization with Psychological Scaffolds
  139. RSRNav: Reasoning Spatial Relationship for Image-Goal Navigation
  140. From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval