mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 21 Jun 2025

144 papers

  1. Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  2. Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and ExperienceLLM reasoning → Reasoning for agents, planning and code
  3. Reflective Verbal Reward Design for Pluralistic AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  4. Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize ApproachLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  6. Reimagining Parameter Space Exploration with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  7. AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent PredictionLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Expanding Relevance Judgments for Medical Case-based Retrieval Task with Multimodal LLMsMultimodal LLMs / vision-language models → Medical vision-language models
  9. Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding ModelsRetrieval-augmented generation → Generation and context integration
  10. PAGENT: Learning to Patch Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  11. CARTS: Collaborative Agents for Recommendation Textual SummarizationLLM agents and tool use → Agentic recommender systems
  12. Towards a Unified Textual Graph Framework for Spectral Reasoning via Physical and Chemical Information FusionLLM reasoning → Clinical and biomedical applications
  13. Physics-informed mixture of experts network for interpretable battery degradation trajectory computation amid second-life complexitiesMixture-of-experts → MoE for time series and graphs
  14. KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  15. Distributed Butterfly Analysis using Mobile AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. DreamJourney: Perpetual View Generation with Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  17. Beyond Syntax: Action Semantics Learning for App AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate LevelLLM reasoning → Spatial and embodied reasoning
  19. MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  20. Histopathology Image Report Generation by Vision Language Model with Multimodal In-Context LearningMultimodal LLMs / vision-language models → Medical vision-language models
  21. RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  22. Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured ValidationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  23. Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  24. CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual ReasoningLLM reasoning → Spatial and embodied reasoning
  25. Imitation Learning for Active Neck Motion Enabling Robot Manipulation beyond the Field of ViewOffline RL and imitation learning from data → Robot manipulation imitation learning
  26. Synthetic Perception: Can Generated Images Unlock Latent Visual Prior for Text-Centric Reasoning?LLM reasoning → Multimodal reasoning
  27. JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching AgentLLM agents and tool use → Multimodal and embodied agents
  28. HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An OptionDiffusion models → Diffusion and flow policies for robotics
  30. DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For DrivingLLM reasoning → Chain-of-thought reasoning for driving +1
  31. Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the UnknownLLM reasoning → Multimodal reasoning
  32. HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language ModelsLLM reasoning → Hallucination detection and mitigation +1
  33. VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  34. Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D AnnotationsLLM reasoning → Spatial and embodied reasoning
  35. Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature TestingLLM agents and tool use → GUI and mobile agents
  36. DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  37. Regulation Compliant AI for Fusion: Real-Time Image Analysis-Based Control of Divertor Detachment in Tokamaks
  38. Systemic Constraints of Undecidability
  39. Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems
  40. An Interpretable Transformer-Based Foundation Model for Cross-Procedural Skill Assessment Using Raw fNIRS Signals
  41. LastingBench: Defend Benchmarks Against Knowledge Leakage
  42. ChildGuard: A Specialized Dataset for Combatting Child-Targeted Hate Speech
  43. AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning
  44. Secure Energy Transactions Using Blockchain Leveraging AI for Fraud Detection and Energy Market Stability
  45. AI Safety vs. AI Security: Demystifying the Distinction and Boundaries
  46. Dynamic Exploration on Segment-Proposal Graphs for Tubular Centerline Tracking
  47. From Tiny Machine Learning to Tiny Deep Learning: A Survey
  48. In-Context Learning Strategies Emerge Rationally
  49. Fetuses Made Simple: Modeling and Tracking of Fetal Shape and Pose
  50. AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
  51. Bayesian Inference for Left-Truncated Log-Logistic Distributions for Time-to-event Data Analysis
  52. Pathway-based Progressive Inference (PaPI) for Energy-Efficient Continual Learning
  53. A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity
  54. Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
  55. THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction
  56. Generative Grasp Detection and Estimation with Concept Learning-based Safety Criteria
  57. Causal Spherical Hypergraph Networks for Modelling Social Uncertainty
  58. Robust Foreground-Background Separation for Severely-Degraded Videos Using Convolutional Sparse Representation Modeling
  59. Time-Contrastive Pretraining for In-Context Image and Video Segmentation
  60. Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
  61. Actionable Interpretability via Causal Hypergraphs: Unravelling Batch Size Effects in Deep Learning
  62. Quantum-Hybrid Support Vector Machines for Anomaly Detection in Industrial Control Systems
  63. Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking
  64. CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
  65. Flatness After All?
  66. AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator
  67. SING: SDE Inference via Natural Gradients
  68. Accelerating Policy Synthesis in Large-Scale MDPs via Hierarchical Adaptive Refinement
  69. Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
  70. Bayesian Social Deduction with Graph-Informed Language Models
  71. Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert
  72. Toward Autonomous UI Exploration: The UIExplorer Benchmark
  73. Machine Learning Model Integration with Open World Temporal Logic for Process Automation
  74. PhysiX: A Foundation Model for Physics Simulations
  75. Collaborative Texture Filtering
  76. Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks
  77. A Locally Differential Private Coding-Assisted Succinct Histogram Protocol
  78. Derandomizing Simultaneous Confidence Regions for Band-Limited Functions by Improved Norm Bounds and Majority-Voting Schemes
  79. LoLA-SpecViT: Local Attention SwiGLU Vision Transformer with LoRA for Hyperspectral Imaging
  80. Residual Connection-Enhanced ConvLSTM for Lithium Dendrite Growth Prediction
  81. HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
  82. Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation
  83. PhysID: Physics-based Interactive Dynamics from a Single-view Image
  84. Rethinking the Role of Operating Conditions for Learning-based Multi-condition Fault Diagnosis
  85. YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception
  86. Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
  87. Clarifying the Ti-V Phase Diagram Using First-Principles Calculations and Bayesian Learning
  88. Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains
  89. Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages
  90. PDC-Net: Pattern Divide-and-Conquer Network for Pelvic Radiation Injury Segmentation
  91. CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
  92. Aged to Perfection: Machine-Learning Maps of Age in Conversational English
  93. Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
  94. The Evolution of Natural Language Processing: How Prompt Optimization and Language Models are Shaping the Future
  95. Regular Tree Search for Simulation Optimization
  96. SSAVSV: Towards Unified Model for Self-Supervised Audio-Visual Speaker Verification
  97. Zero-Shot Conversational Stance Detection: Dataset and Approaches
  98. Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering
  99. Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models
  100. Domain Generalization using Action Sequences for Egocentric Action Recognition
All 144
  1. Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems
  2. Enhancing Stress-Strain Predictions with Seq2Seq and Cross-Attention based on Small Punch Test
  3. CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection
  4. FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
  5. Learning Personalized Utility Functions for Drivers in Ride-hailing Systems Using Ensemble Hypernetworks
  6. TPTT: Transforming Pretrained Transformers into Titans
  7. Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution
  8. Advanced Modeling for Exoplanet Detection and Characterization
  9. Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges
  10. 3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene
  11. Scalable Machine Learning Algorithms using Path Signatures
  12. Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
  13. Pixel-Optimization-Free Patch Attack on Stereo Depth Estimation
  14. Time-Prompt: Integrated Heterogeneous Prompts for Unlocking LLMs in Time Series Forecasting
  15. Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
  16. Trustworthy Chronic Disease Risk Prediction For Self-Directed Preventive Care via Medical Literature Validation
  17. EQuARX: Efficient Quantized AllReduce in XLA for Distributed Machine Learning Acceleration
  18. OpusLM: A Family of Open Unified Speech Language Models
  19. TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecasting
  20. Towards Fundamental Limits for Active Multi-distribution Learning
  21. Mind the Gap: Assessing Wiktionary's Crowd-Sourced Linguistic Knowledge on Morphological Gaps in Two Related Languages
  22. OpenMAP-BrainAge: Generalizable and Interpretable Brain Age Predictor
  23. A Multimodal In Vitro Diagnostic Method for Parkinson's Disease Combining Facial Expressions and Behavioral Gait Data
  24. SELFI: Selective Fusion of Identity for Generalizable Deepfake Detection
  25. Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
  26. LFR-PINO: A Layered Fourier Reduced Physics-Informed Neural Operator for Parametric PDEs
  27. Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models
  28. AgriCHN: A Comprehensive Cross-domain Resource for Chinese Agricultural Named Entity Recognition
  29. Optimizing Mastery Learning by Fast-Forwarding Over-Practice Steps
  30. Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning
  31. Accelerating Residual Reinforcement Learning with Uncertainty Estimation
  32. LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learning
  33. Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework
  34. SynDaCaTE: A Synthetic Dataset For Evaluating Part-Whole Hierarchical Inference
  35. Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nystr"om Method
  36. DRIMV_TSK: An Interpretable Surgical Evaluation Model for Incomplete Multi-View Rectal Cancer Data
  37. Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems
  38. Predicting Stock Market Crash with Bayesian Generalised Pareto Regression
  39. Predicting E-commerce Purchase Behavior using a DQN-Inspired Deep Learning Model for enhanced adaptability
  40. Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception
  41. MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
  42. ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
  43. Exploring Strategies for Personalized Radiation Therapy Part I Unlocking Response-Related Tumor Subregions with Class Activation Mapping
  44. Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning