mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 15 Mar 2025

170 papers

  1. VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation MetricLLM agents and tool use → Software engineering coding agents
  2. Token-Level Uncertainty-Aware Objective for Language Model Post-TrainingKnowledge distillation → Knowledge distillation for LLMs
  3. ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video SynthesisVision-language-action models → Generalist VLA models and benchmarks
  4. From Demonstrations to Rewards: Alignment Without Explicit Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  5. Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning MechanismsLLM reasoning → Reasoning benchmarks and evaluation
  6. Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical NotesLLM reasoning → Clinical and biomedical applications +1
  7. Towards Optimal Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  8. Exploration of VLMs for Driver Monitoring Systems ApplicationsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  9. Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context ReflectionLLM reasoning → Diffusion reasoning and test-time scaling +1
  10. Agentic Search Engine for Real-Time IoT DataLLM agents and tool use → Web, search, and research agents
  11. RISE: Robust Imitation through Stochastic EncodingOffline RL and imitation learning from data → Imitation learning methods
  12. Transition Uncertainties in Constrained Markov Decision Models: A Robust Optimization ApproachDeep reinforcement learning methods → RL theory and sample complexity
  13. Evaluation-Time Policy Switching for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  14. TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code GenerationLLM agents and tool use → Agent threats, guardrails and governance
  15. STAY Diffusion: Styled Layout Diffusion Model for Diverse Layout-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  16. PredicateFix: Repairing Static Analysis Alerts with Bridging PredicatesRetrieval-augmented generation → RAG for code
  17. D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised DeformationsDiffusion models → Diffusion and flow policies for robotics
  18. S2IL: Structurally Stable Incremental LearningKnowledge distillation → Distillation for continual learning
  19. Multi-Agent Systems Execute Arbitrary Malicious CodeLLM agents and tool use → Agent threats, guardrails and governance
  20. DiffAD: A Unified Diffusion Modeling Approach for Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  21. Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  22. Hyperbolic Safety-Aware Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  23. MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward ModelingLLM reasoning → Reinforcement learning for reasoning +1
  24. Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  25. O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  26. A Comprehensive Survey on Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  27. TACO: Taming Diffusion for in-the-wild Video Amodal CompletionDiffusion models → Video generation
  28. Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion EstimationDeep reinforcement learning methods → Safe and constrained RL
  29. Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop TrainingEnd-to-end autonomous driving → End-to-end system architecture
  30. Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding TasksLLM agents and tool use → Social simulation and multi-agent debate
  31. CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of ArtDiffusion models → Image generation, text-to-image and editing
  32. QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  33. UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  34. Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data SynthesisDiffusion models → Robustness, privacy and adversarial aspects +1
  35. WiFi-Diffusion: Achieving Fine-Grained WiFi Radio Map Estimation With Ultra-Low Sampling Rate by Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  36. Diffusion Dynamics Models with Generative State Estimation for Cloth ManipulationDiffusion models → Diffusion and flow policies for robotics
  37. Automation and Feature Selection Enhancement with Reinforcement Learning (RL)Deep reinforcement learning methods → Deep RL algorithms and representations
  38. Applications of Large Language Model Reasoning in Feature GenerationLLM reasoning → Reasoning benchmarks and evaluation
  39. SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. Your Text Encoder Can Be An Object-Level Watermarking ControllerLLM safety and security → Watermarking generated content and models
  41. Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational AutoencoderDiffusion models → Image generation, text-to-image and editing
  42. The Strategic Imperative for Healthcare Organizations to Build Proprietary Foundation Models
  43. LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks
  44. PIPO: Pipelined Offloading for Efficient Inference on Consumer Devices
  45. Brain2Text Decoding Model Reveals the Neural Mechanisms of Visual Semantic Processing
  46. Toward a Human-Centered AI-assisted Colonoscopy System in Australia
  47. Medifact at PerAnsSumm 2025: Leveraging Lightweight Models for Perspective-Specific Summarization of Clinical Q&A Forums
  48. A Logic of Uncertain Interpretation
  49. Threefold model for AI Readiness: A Case Study with Finnish Healthcare SMEs
  50. Spline refinement with differentiable rendering
  51. Salient Temporal Encoding for Dynamic Scene Graph Generation
  52. FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learning
  53. Unlocking Learning Potentials: The Transformative Effect of Generative AI in Education Across Grade Levels
  54. Multi-output Classification for Compound Fault Diagnosis in Motor under Partially Labeled Target Domain
  55. The Status Quo and Future of AI-TPACK for Mathematics Teacher Education Students: A Case Study in Chinese Universities
  56. Context-aware Multimodal AI Reveals Hidden Pathways in Five Centuries of Art Evolution
  57. Internet of Things-Based Smart Precision Farming in Soilless Agriculture: Opportunities and Challenges for Global Food Security
  58. Towards Learning High-Precision Least Squares Algorithms with Sequence Models
  59. The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation
  60. Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models
  61. A Resilience Framework for Bi-Criteria Combinatorial Optimization with Bandit Feedback
  62. REdiSplats: Ray Tracing for Editable Gaussian Splatting
  63. Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study
  64. Probabilistic Forecasting for Dynamical Systems with Missing or Imperfect Data
  65. Cracking the PUMA Challenge in 24 Hours with CellViT++ and nnU-Net
  66. An Efficient Deep Learning-Based Approach to Automating Invoice Document Validation
  67. Support Collapse of Deep Gaussian Processes with Polynomial Kernels for a Wide Regime of Hyperparameters
  68. United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space
  69. Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge
  70. Minuscule Cell Detection in AS-OCT Images with Progressive Field-of-View Focusing
  71. RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance
  72. A Novel Double Pruning method for Imbalanced Data using Information Entropy and Roulette Wheel Selection for Breast Cancer Diagnosis
  73. From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
  74. LIAM: Multimodal Transformer for Language Instructions, Images, Actions and Semantic Maps
  75. Shadow Art Kanji: Inverse Rendering Application
  76. Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments
  77. Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning
  78. Interpretation Gaps in LLM-Assisted Comprehension of Privacy Documents
  79. PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data
  80. Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labels
  81. Gun Detection Using Combined Human Pose and Weapon Appearance
  82. Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment
  83. Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs
  84. TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
  85. Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
  86. Action-Gradient Monte Carlo Tree Search for Non-Parametric Continuous (PO)MDPs
  87. Bench2FreeAD: A Benchmark for Vision-based End-to-end Navigation in Unstructured Robotic Environments
  88. DPCS: Path Tracing-Based Differentiable Projector-Camera Systems
  89. LAPIG: Language Guided Projector Image Generation with Surface Adaptation and Stylization
  90. SEAL: Semantic Aware Image Watermarking
  91. Learning Extremely High Density Crowds as Active Matters
  92. PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing
  93. VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction
  94. Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphs
  95. Aristotle's Original Idea: For and Against Logic in the era of AI
  96. Weighted Graph Structure Learning with Attention Denoising for Node Classification
  97. Efficient and Privacy-Preserved Link Prediction via Condensed Graphs
  98. Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusion
  99. Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
  100. Language Models for Automated Classification of Brain MRI Reports and Growth Chart Generation
All 170
  1. Enhanced Sentiment Analysis of Iranian Restaurant Reviews Utilizing Sentiment Intensity Analyzer & Fuzzy Logic
  2. A State Alignment-Centric Approach to Federated System Identification: The FedAlign Framework
  3. DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap
  4. Robust Isolation Forest using Soft Sparse Random Projection and Valley Emphasis Method
  5. Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
  6. ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control
  7. Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations
  8. RECSIP: REpeated Clustering of Scores Improving the Precision
  9. ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
  10. A Speech-to-Video Synthesis Approach Using Spatio-Temporal Diffusion for Vocal Tract MRI
  11. Large Language Models in Legislative Content Analysis: A Dataset from the Polish Parliament
  12. Towards Vision Zero: The TUM Traffic Accid3nD Dataset
  13. E-SAM: Training-Free Segment Every Entity Model
  14. SFMNet: Sparse Focal Modulation for 3D Object Detection
  15. Temporally Consistent Mitral Annulus Measurements from Sparse Annotations in Echocardiographic Videos
  16. FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields
  17. Automating the loop in traffic incident management on highway
  18. PICID: Proof-Driven Clause Learning in Neural Network Verification
  19. Comparing Human Expertise and Large Language Models Embeddings in Content Validity Assessment of Personality Tests
  20. V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
  21. Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
  22. Robust Dataset Distillation by Matching Adversarial Trajectories
  23. Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation
  24. Dataset Properties Shape the Success of Neuroimaging-Based Patient Stratification: A Benchmarking Analysis Across Clustering Algorithms
  25. Maritime Mission Planning for Unmanned Surface Vessel using Large Language Model
  26. DLA-Count: Dynamic Label Assignment Network for Dense Cell Distribution Counting
  27. EHNet: An Efficient Hybrid Network for Crowd Counting and Localization
  28. Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
  29. Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
  30. A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments
  31. TLUE: A Tibetan Language Understanding Evaluation Benchmark
  32. PSGait: Gait Recognition using Parsing Skeleton
  33. Auditing Differential Privacy in the Black-Box Setting
  34. An LLM-Integrated Framework for Completion, Management, and Tracing of STPA
  35. Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
  36. Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning
  37. MOS: Modeling Object-Scene Associations in Generalized Category Discovery
  38. Real-Time Manipulation Action Recognition with a Factorized Graph Sequence Encoder
  39. Challenges in Plane Symmetry: From Theory to Perception
  40. Leveraging Motion Information for Better Self-Supervised Video Correspondence Learning
  41. SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
  42. Variance-Dependent Regret Lower Bounds for Contextual Bandits
  43. A Survey on Federated Fine-tuning of Large Language Models
  44. Learning Dual-Domain Multi-Scale Representations for Single Image Deraining
  45. Mixed-feature Logistic Regression Robust to Distribution Shifts
  46. ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object
  47. 3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
  48. Fraesormer: Learning Adaptive Sparse Transformer for Efficient Food Recognition
  49. No LLM is Free From Bias: A Comprehensive Study of Bias Evaluation in Large Language Models
  50. DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
  51. DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes
  52. Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
  53. Machine Learning-Based Model for Postoperative Stroke Prediction in Coronary Artery Disease
  54. Evaluation of Intra-operative Patient-specific Methods for Point Cloud Completion for Minimally Invasive Liver Interventions
  55. Revisiting Gradient Descent: A Dual-Weight Method for Improved Learning
  56. Entropy-regularized Gradient Estimators for Approximate Bayesian Inference
  57. Effective and Efficient Cross-City Traffic Knowledge Transfer: A Privacy-Preserving Perspective
  58. HInter: Exposing Hidden Intersectional Bias in Large Language Models
  59. CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts
  60. Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification
  61. SPOC: Spatially-Progressing Object State Change Segmentation in Video
  62. Privacy Ethics Alignment in AI: A Stakeholder-Centric Framework for Ethical AI
  63. Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis
  64. Ethical AI for Young Digital Citizens: A Call to Action on Privacy Governance
  65. Human Digital Twins in Personalized Healthcare: An Overview and Future Perspectives
  66. Integrating Product Coefficients for Improved 3D LiDAR Data Classification
  67. Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusion
  68. End-to-End Edge AI Service Provisioning Framework in 6G ORAN
  69. SPRINT: Script-agnostic Structure Recognition in Tables
  70. Generating a Biometrically Unique and Realistic Iris Database