mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 4 Oct 2025

196 papers

  1. Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  2. Towards an Efficient, Customizable, and Accessible AI TutorRetrieval-augmented generation → Agentic RAG, agents and memory
  3. Enhanced Self-Distillation Framework for Efficient Spiking Neural Network TrainingKnowledge distillation → Distillation for spiking neural networks
  4. No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  5. What Can You Do When You Have Zero Rewards During RL?LLM reasoning → Reinforcement learning for reasoning
  6. Self-Speculative Masked DiffusionsDiffusion models → Discrete and text diffusion
  7. PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in PersianLLM reasoning → Clinical and biomedical applications
  8. Generalized Fitted Q-Iteration with Clustered DataDeep reinforcement learning methods → RL theory and sample complexity
  9. From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation PerformanceMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  10. Zero-Shot Fine-Grained Image Classification Using Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-CodeLLM agents and tool use → Software engineering coding agents
  12. GAE: Unleashing Physical Potential of VLM with Generalizable Action ExpertLLM reasoning → Spatial and embodied reasoning +1
  13. NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action InterfacesVision-language-action models → Generalist VLA models and benchmarks
  14. Rare Text Semantics Were Always There in Your Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  15. Seeing the Bigger Picture: 3D Latent Mapping for Mobile Manipulation Policy LearningLLM reasoning → Spatial and embodied reasoning
  16. Exploring Instruction Data Quality for Explainable Image Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  17. Adversarial Agent Collaboration for Correctness Improvements of C to Safe Rust TranslationLLM agents and tool use → Software engineering coding agents
  18. SDAKD: Student Discriminator Assisted Knowledge Distillation for Super-Resolution Generative Adversarial NetworksKnowledge distillation → General knowledge distillation methods
  19. Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning ExplorationLLM reasoning → Reinforcement learning for reasoning
  20. Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine DifferentiationLLM reasoning → Spatial and embodied reasoning +1
  21. Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offsLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  23. HOFLON: Hybrid Offline Learning and Online Optimization for Process Start-Up and Grade-Transition ControlOffline RL and imitation learning from data → Offline RL algorithms
  24. A4FN: an Agentic AI Architecture for Autonomous Flying NetworksLLM agents and tool use → Multimodal and embodied agents
  25. LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond MemorizationVision-language-action models → Failure recovery and robustness
  26. Diverse Text-to-Image Generation via Contrastive Noise OptimizationDiffusion models → Image generation, text-to-image and editing
  27. Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  28. Mechanistic Interpretability of Socio-Political Frames in Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  29. MambaCAFU: Hybrid Multi-Scale and Multi-Attention Model with Mamba-Based Fusion for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  30. OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent SimulationLLM agents and tool use → Social simulation and multi-agent debate
  31. APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  32. Bridging the Gap Between Multimodal Foundation Models and World ModelsWorld models → World models for language agents
  33. Balancing Interpretability and Performance in Reinforcement Learning: An Adaptive Spectral Based Linear ApproachDeep reinforcement learning methods → Interpretable and logic-guided RL
  34. Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  35. EmbodiSwap for Zero-Shot Robot Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  36. Backdoor-Powered Prompt Injection Attacks Nullify Defense MethodsLLM safety and security → Prompt injection and agent security
  37. Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN AgentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  38. Mind the Goal: Data-Efficient Goal-Oriented Evaluation of Conversational Agents and Chatbots using Teacher ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. MedReflect: Teaching Medical LLMs to Self-Improve via Reflective CorrectionSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  40. Group Policy GradientDeep reinforcement learning methods → RL theory and sample complexity
  41. A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation SystemsDiffusion models → Diffusion and flow policies for robotics
  42. Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  43. UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAGRetrieval-augmented generation → Multimodal RAG
  44. Does higher interpretability imply better utility? A Pairwise Analysis on Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  45. Expressive Power of Implicit Models: Rich Equilibria and Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  46. From Theory to Practice: Evaluating Data Poisoning Attacks and Defenses in In-Context Learning on Social Media Health DiscourseLLM safety and security → Safety alignment, refusal and guardrails
  47. MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual InformationLLM reasoning → Test-time compute and efficient thinking
  48. Cross-Modal Content Optimization for Steering Web Agent PreferencesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  49. PentestMCP: A Toolkit for Agentic Penetration TestingLLM agents and tool use → Agent threats, guardrails and governance
  50. Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCILDiffusion models → Image generation, text-to-image and editing
  51. Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random CropsKnowledge distillation → General knowledge distillation methods
  52. Understanding the Role of Training Data in Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  53. Exploring the Hierarchical Reasoning Model for Small Natural-Image Classification Without AugmentationLLM reasoning → Multimodal reasoning
  54. Decoupling Task-Solving and Output Formatting in LLM GenerationLLM reasoning → Test-time compute and efficient thinking
  55. REFINE: Enhancing Program Repair Agents through Context-Aware Patch RefinementLLM agents and tool use → Software engineering coding agents
  56. FrameOracle: Learning What to See and How Much to See in VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  57. Latent Mixture of Symmetries for Sample-Efficient Dynamic LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  58. Beyond Awareness: Investigating How AI and Psychological Factors Shape Human Self-Confidence Calibration
  59. Deep Learning-based Lightweight RGB Object Tracking for Augmented Reality Devices
  60. Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment
  61. AdaptAuth: Multi-Layered Behavioral and Credential Analysis for a Secure and Adaptive Authentication Framework for Password Security
  62. Enhanced Urban Traffic Management Using CCTV Surveillance Videos and Multi-Source Data Current State Prediction and Frequent Episode Mining
  63. Direct Routing Gradient (DRGrad): A Personalized Information Surgery for Multi-Task Learning (MTL) Recommendations
  64. The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
  65. Evolutionary Computation as Natural Generative AI
  66. LLM-Driven Rubric-Based Assessment of Algebraic Competence in Multi-Stage Block Coding Tasks with Design and Field Evaluation
  67. Machine learning for fraud detection in digital banking: a systematic literature review REVIEW
  68. Domain-Adapted Granger Causality for Real-Time Cross-Slice Attack Attribution in 6G Networks
  69. SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
  70. Deep Learning-Based Multi-Factor Authentication: A Survey of Biometric and Smart Card Integration Approaches
  71. Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam
  72. Beyond Softmax: A New Perspective on Gradient Bandits
  73. Use of Quadcopter Wakes to Supplement Strawberry Pollination
  74. Towards Carbon-Aware Container Orchestration: Predicting Workload Energy Consumption with Federated Learning
  75. How Catastrophic is Your LLM? Certifying Risk in Conversation
  76. SPEAR: Soft Prompt Enhanced Anomaly Recognition for Time Series Data
  77. Operational early warning of thunderstorm-driven power outages from open data: a two-stage machine learning approach
  78. Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs
  79. Optimizing Resources for On-the-Fly Label Estimation with Multiple Unknown Medical Experts
  80. Strategy Logic, Imperfect Information, and Hyperproperties
  81. What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis
  82. Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped
  83. On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
  84. Super-resolution image projection over an extended depth of field using a diffractive decoder
  85. LLM Chemistry Estimation for Multi-LLM Recommendation
  86. Sliding Window Attention for Learned Video Compression
  87. On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
  88. Talking Tennis: Language Feedback from 3D Biomechanical Action Recognition
  89. Transductive and Learning-Augmented Online Regression
  90. OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications
  91. Refactoring with LLMs: Bridging Human Expertise and Machine Understanding
  92. THEMIS: Unlocking Pretrained Knowledge with Foundation Model Embeddings for Anomaly Detection in Time Series
  93. Generating Human Motion Videos using a Cascaded Text-to-Video Framework
  94. LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
  95. Optimal Computation from Fluctuation Responses
  96. Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
  97. Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles
  98. BONSAI: Structure-exploiting robust Bayesian optimization for networked black-box systems under uncertainty
  99. Kantian-Utilitarian XAI: Meta-Explained
  100. Multi-Modal Oral Cancer Detection Using Weighted Ensemble Convolutional Neural Networks
All 196
  1. Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion
  2. DHQA-4D: Perceptual Quality Assessment of Dynamic 4D Digital Human
  3. PoseGaze-AHP: A Knowledge-Based 3D Dataset for AI-Driven Ocular and Postural Diagnosis
  4. Optimal Scaling Needs Optimal Norm
  5. Exploring the Challenge and Value of Deep Learning in Automated Skin Disease Diagnosis
  6. AI Adoption Across Mission-Driven Organizations
  7. On Provable Benefits of Muon in Federated Learning
  8. Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework
  9. Adaptive and Explainable AI Agents for Anomaly Detection in Critical IoT Infrastructure using LLM-Enhanced Contextual Reasoning
  10. Cross-View Open-Vocabulary Object Detection in Aerial Imagery
  11. Optimized Minimal 4D Gaussian Splatting
  12. AI-Assisted Pleural Effusion Volume Estimation from Contrast-Enhanced CT Images
  13. UGround: Towards Unified Visual Grounding with Unrolled Transformers
  14. MetaMuse: Algorithm Generation via Creative Ideation
  15. The Hidden Game Problem
  16. On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records
  17. Smart Paste: Automatically Fixing Copy/Paste for Google Developers
  18. Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting
  19. Technical note on Fisher Information for Robust Federated Cross-Validation
  20. Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Models
  21. Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events
  22. Detecting Malicious Pilot Contamination in Multiuser Massive MIMO Using Decision Trees
  23. Proximal Diffusion Neural Sampler
  24. Distributed Area Coverage with High Altitude Balloons Using Multi-Agent Reinforcement Learning
  25. Contrastive-SDE: Guiding Stochastic Differential Equations with Contrastive Learning for Unpaired Image-to-Image Translation
  26. TROLL: Trust Regions improve Reinforcement Learning for Large Language Models
  27. A Trustworthy Industrial Fault Diagnosis Architecture Integrating Probabilistic Models and Large Language Models
  28. Detecting Invariant Manifolds in ReLU-Based RNNs
  29. ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAs
  30. Curriculum-Augmented GFlowNets For mRNA Sequence Generation
  31. Cellular Learning: Scattered Data Regression in High Dimensions via Voronoi Cells
  32. Spectral Thresholds for Identifiability and Stability:Finite-Sample Phase Transitions in High-Dimensional Learning
  33. Annotate Rhetorical Relations with INCEpTION: A Comparison with Automatic Approaches
  34. 6G-Enabled Digital Twin Framework for Real-Time Cyber-Physical Systems: An Experimental Validation with Industrial Bearing Fault Detection
  35. Batched Bandits with Heavy-Tailed Rewards
  36. Road Damage and Manhole Detection using Deep Learning for Smart Cities: A Polygonal Annotation Approach
  37. Investigating LLM Variability in Personalized Conversational Information Retrieval
  38. Lightweight and Data-Efficient MultivariateTime Series Forecasting using Residual-Stacked Gaussian (RS-GLinear) Architecture
  39. Performance-Efficiency Tradeoffs in Transformers: An Approximation Theory Perspective
  40. Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation
  41. Rezwan: Leveraging Large Language Models for Comprehensive Hadith Text Processing: A 1.2M Corpus Development
  42. A Benchmark Study of Deep Learning Methods for Multi-Label Pediatric Electrocardiogram-Based Cardiovascular Disease Classification
  43. GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
  44. Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets
  45. Efficiency vs. Efficacy: Assessing the Compression Ratio-Dice Score Relationship through a Simple Benchmarking Framework for Cerebrovascular 3D Segmentation
  46. CoPA: Hierarchical Concept Prompting and Aggregating Network for Explainable Diagnosis
  47. Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization
  48. Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
  49. You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models
  50. EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
  51. Cross-Lingual Multi-Granularity Framework for Interpretable Parkinson's Disease Diagnosis from Speech
  52. Code4MeV2: a Research-oriented Code-completion Platform
  53. The Overlooked Value of Test-time Reference Sets in Visual Place Recognition
  54. TreePrompt: Leveraging Hierarchical Few-Shot Example Selection for Improved English-Persian and English-German Translation
  55. LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
  56. Neural Low-Discrepancy Sequences
  57. HydroFusion-LMF: Semi-Supervised Multi-Network Fusion with Large-Model Adaptation for Long-Term Daily Runoff Forecasting
  58. Cost Efficient Fairness Audit Under Partial Feedback
  59. Optimizing Fine-Tuning through Advanced Initialization Strategies for Low-Rank Adaptation
  60. Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation
  61. Personalized federated prototype learning in mixed heterogeneous data scenarios
  62. Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks
  63. Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition
  64. Artery-Vein Segmentation from Fundus Images using Deep Learning
  65. Referring Expression Comprehension for Small Objects
  66. H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis
  67. REG: A Regularization Optimizer for Robust Training Dynamics
  68. From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
  69. SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection
  70. The analogy theorem in Hoare logic
  71. Model-Guided Microstimulation Steers Primate Visual Behavior
  72. Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text
  73. Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
  74. Towards Sampling Data Structures for Tensor Products in Turnstile Streams
  75. MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations
  76. Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
  77. Optimising Battery Energy Storage System Trading via Energy Market Operator Price Forecast
  78. LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design
  79. SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
  80. In-Vivo Training for Deep Brain Stimulation
  81. Towards Unsupervised Speech Recognition at the Syllable-Level
  82. PRTree: An R Package for Probabilistic Regression Trees with Built-in Missing Data Handling
  83. Predicting Stock Price Movement with LLM-Enhanced Tweet Emotion Analysis
  84. Transformed ℓ1 Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding
  85. Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications
  86. Neural Bayesian Filtering
  87. Explore the Loss space with Hill-ADAM
  88. Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
  89. Deep Domain Adaptation for Turbofan Engine Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
  90. MECKD: Deep Learning-Based Fall Detection in Multilayer Mobile Edge Computing With Knowledge Distillation
  91. Neon: Negative Extrapolation From Self-Training Improves Image Generation
  92. Deep Reinforcement Learning for Multi-Agent Coordination
  93. A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games
  94. FieldFormer: Locality-Aware Transformers for Spatio-Temporal Modeling on Sparse Sensor Networks
  95. Exact and Approximate MCMC for Doubly-intractable Probabilistic Graphical Models Leveraging the Underlying Independence Model
  96. Deep learning the sources of MJO predictability: a spectral view of learned features