mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 4 Jan 2025

95 papers

  1. Benchmarking Large and Small MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  2. LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot ArenaLLM safety and security → Safety alignment, refusal and guardrails
  3. Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive DeploymentLLM reasoning → Reasoning for agents, planning and code +1
  4. REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage NormalizationLLM reasoning → Reinforcement learning for reasoning +1
  5. Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt VariationsMultimodal LLMs / vision-language models → Medical vision-language models
  6. Origin Identification for Text-Guided Image-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  7. BADTV: Unveiling Backdoor Threats in Third-Party Task VectorsLLM safety and security → Backdoor and data poisoning attacks
  8. CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  9. Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-SolvingLLM reasoning → Reasoning for agents, planning and code
  10. Optimizing Small Language Models for In-Vehicle Function-CallingLLM agents and tool use → Tool learning and function calling
  11. UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude MobilityLLM agents and tool use → Multimodal and embodied agents
  12. SR-Reward: Taking The Path More TraveledOffline RL and imitation learning from data → Inverse reinforcement learning
  13. DiffGraph: Heterogeneous Graph Diffusion ModelDiffusion models → Flow matching, time series and science
  14. Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distanceDiffusion models → Diffusion foundations and sampling
  15. Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-ReflectionLLM reasoning → Reasoning benchmarks and evaluation
  16. TDM: Temporally-Consistent Diffusion Model for All-in-One Real-World Video RestorationDiffusion models → Inverse problems and image restoration
  17. What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of GraphMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  18. Unsupervised Class Generation to Expand Semantic Segmentation DatasetsDiffusion models → Medical imaging and segmentation
  19. MagicFace: High-Fidelity Facial Expression Editing with Action-Unit ControlDiffusion models → Image generation, text-to-image and editing
  20. Distillation-Enhanced Physical Adversarial AttacksKnowledge distillation → Federated, robust and private distillation
  21. Knowledge Graph Retrieval-Augmented Generation for LLM-based RecommendationRetrieval-augmented generation → RAG for recommendation
  22. CORD: Generalizable Cooperation via Role DiversityDeep reinforcement learning methods → Multi-agent reinforcement learning
  23. Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised LearningDiffusion models → Robustness, privacy and adversarial aspects
  24. Digital Twin Calibration with Model-Based Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  25. Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual LearningMixture-of-experts → Mixture of LoRA experts
  26. A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and ChallengesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +2
  27. AdaMixup: A Dynamic Defense Framework for Membership Inference Attack MitigationLLM safety and security → Membership inference attacks
  28. The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early ExitEfficient LLM inference and serving → Prompt and context compression
  29. Table as Thought: Exploring Structured Thoughts in LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  30. Robust Uplift Modeling with Large-Scale Contexts for Real-time Marketing
  31. ED-Filter: Dynamic Feature Filtering for Eating Disorder Classification
  32. DeServe: Towards Affordable Offline LLM Inference via Decentralization
  33. Path Space Partitioning and Guided Image Sampling for MCMC
  34. Guiding Treatment Strategies: The Role of Adjuvant Anti-Her2 Neu Therapy and Skin/Nipple Involvement in Local Recurrence-Free Survival in Breast Cancer Patients
  35. Heterogeneous Graph Pre-training Based Model for Secure and Efficient Prediction of Default Risk Propagation among Bond Issuers
  36. Bridge the Inference Gaps of Neural Processes via Expectation Maximization
  37. A Training-free Method for LLM Text Attribution
  38. iTARGET: Interpretable Tailored Age Regression for Grouped Epigenetic Traits
  39. Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers
  40. Syntactic Evolution in Language Usage
  41. TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training
  42. A ghost mechanism: An analytical model of abrupt learning in recurrent networks
  43. Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison
  44. Predicting two-dimensional spatiotemporal chaotic patterns with optimized high-dimensional hybrid reservoir computing
  45. Enhancing Workplace Productivity and Well-being Using AI Agent
  46. Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension
  47. V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detection
  48. Easing Optimization Paths: a Circuit Perspective
  49. Context Aware Lemmatization and Morphological Tagging Method in Turkish
  50. When is the Computation of a Feature Attribution Method Tractable?
  51. Reweighting Improves Conditional Risk Bounds
  52. GNSS/GPS Spoofing and Jamming Identification Using Machine Learning and Deep Learning
  53. Revelio: A Real-World Screen-Camera Communication System with Visually Imperceptible Data Embedding
  54. Exploring the Capabilities and Limitations of Large Language Models for Radiation Oncology Decision Support
  55. Accurate Crop Yield Estimation of Blueberries using Deep Learning and Smart Drones
  56. Evaluation of the Code Generation Capabilities of ChatGPT 4: A Comparative Analysis in 19 Programming Languages
  57. AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
  58. Validity Arguments For Constructed Response Scoring Using Generative Artificial Intelligence Applications
  59. On The Causal Network Of Face-selective Regions In Human Brain During Movie Watching
  60. Revisiting Compactness for District Plans
  61. RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radar
  62. Analysis of Fluorescence Telescope Data Using Machine Learning Methods
  63. Diabetic Retinopathy Detection Using CNN with Residual Block with DCGAN
  64. Deep Learning-Driven Segmentation of Ischemic Stroke Lesions Using Multi-Channel MRI
  65. Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding
  66. Efficient Video-Based ALPR System Using YOLO and Visual Rhythm
  67. Towards a constructive framework for control theory
  68. LLMzSzL: a comprehensive LLM benchmark for Polish
  69. Interpretable Load Forecasting via Representation Learning of Geo-distributed Meteorological Factors
  70. Financial Named Entity Recognition: How Far Can LLM Go?
  71. Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends
  72. tCURLoRA: Tensor CUR Decomposition Based Low-Rank Parameter Adaptation and Its Application in Medical Image Segmentation
  73. How Robust Is Homogeneity Bias in LLMs? Evidence Across Models, Decoding Settings, and Identity Signals
  74. Robust Multi-Dimensional Scaling via Accelerated Alternating Projections
  75. Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies
  76. Acknowledging Focus Ambiguity in Visual Questions
  77. Learning Evolution via Optimization Knowledge Adaptation
  78. Can ChatGPT implement finite element models for geotechnical engineering applications?
  79. Majorization-Minimization Dual Stagewise Algorithm for Generalized Lasso
  80. CPTuning: Contrastive Prompt Tuning for Generative Relation Extraction
  81. On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing
  82. SMDP-Based Dynamic Batching for Improving Responsiveness and Energy Efficiency of Batch Services
  83. Quaternionic Reweighted Amplitude Flow for Phase Retrieval in Image Reconstruction
  84. Molecule-dynamic-based Aging Clock and Aging Roadmap Forecast with Sundial
  85. The Integration of Blockchain and Artificial Intelligence for Secure Healthcare Systems
  86. Generating Multimodal Images with GAN: Integrating Text, Image, and Style
  87. ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle
  88. Joint Optimization for 4D Human-Scene Reconstruction in the Wild
  89. Personalized Graph-Based Retrieval for Large Language Models
  90. The Race to Efficiency: A New Perspective on AI Scaling Laws
  91. From Images to Detection: Machine Learning for Blood Pattern Classification
  92. Attribute-Based Robotic Grasping with Data-Efficient Adaptation
  93. Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50
  94. Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN
  95. Establishing baselines for generative discovery of inorganic crystals