mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 20 Jul 2024

118 papers

  1. Diffusion Models as Data Mining ToolsDiffusion models → Diffusion foundations and sampling
  2. Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge BaseRetrieval-augmented generation → Agentic RAG, agents and memory +1
  3. EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task ClassificationState-space sequence models (S4, Mamba) → Physiological signal modeling
  4. Improving EEG Classification Through Randomly Reassembling Original and Generated Data with Transformer-based Diffusion ModelsDiffusion models → Medical imaging and segmentation
  5. Intelligence Analysis of Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  6. Is Behavior Cloning All You Need? Understanding Horizon in Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  7. Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  8. Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)LLM safety and security → Prompt injection and agent security
  9. Improving Context-Aware Preference Modeling for Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  10. AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image EnhancementDiffusion models → Inverse problems and image restoration
  11. Text-based Talking Video Editing with Cascaded Conditional DiffusionDiffusion models → Audio, speech and music
  12. Retrieval Augmented Generation Integrated Large Language Models in Smart Contract Vulnerability DetectionRetrieval-augmented generation → Privacy and security of RAG
  13. Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning CoordinatorsLLM reasoning → Multimodal reasoning +1
  14. FMamba: Mamba based on Fast-attention for Multivariate Time-series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  15. PASSION: Towards Effective Incomplete Multi-Modal Medical Image Segmentation with Imbalanced Missing RatesKnowledge distillation → Distillation for medical imaging
  16. Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?LLM reasoning → Mathematical reasoning
  17. VisFly: An Efficient and Versatile Simulator for Training Vision-based FlightDeep reinforcement learning methods → RL for robot navigation and UAV control
  18. Phase Re-service in Reinforcement Learning Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  19. Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge DistillationKnowledge distillation → Graph neural network distillation
  20. Difflare: Removing Image Lens Flare with Latent Diffusion ModelDiffusion models → Inverse problems and image restoration
  21. Flatness-aware Sequential Learning Generates Resilient BackdoorsLLM safety and security → Backdoor and data poisoning attacks
  22. Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RLDeep reinforcement learning methods → RL training of language and agent models
  23. FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  24. Provable Differentially Private Computation of the Cross-Attention MechanismDiffusion models → Robustness, privacy and adversarial aspects
  25. Unveiling the Decision-Making Process in Reinforcement Learning with Genetic ProgrammingDeep reinforcement learning methods → Interpretable and logic-guided RL
  26. ∞-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite DimensionsDiffusion models → Diffusion foundations and sampling
  27. Mapping Patient Trajectories: Understanding and Visualizing Sepsis Prognostic Pathways from Patients Clinical Narratives
  28. Mapping the Technological Future: A Topic, Sentiment, and Emotion Analysis in Social Media Discourse
  29. CORT: Class-Oriented Real-time Tracking for Embedded Systems
  30. Ensemble quantile-based deep learning framework for streamflow and flood prediction in Australian catchments
  31. Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
  32. Diff4VS: HIV-inhibiting Molecules Generation with Classifier Guidance Diffusion for Virtual Screening
  33. Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach
  34. Enhancing Wildfire Forecasting Through Multisource Spatio-Temporal Data, Deep Learning, Ensemble Models and Transfer Learning
  35. Improving Citation Text Generation: Overcoming Limitations in Length Control
  36. All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks
  37. Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs
  38. Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
  39. Enhancing Microgrid Performance Prediction with Attention-based Deep Learning Models
  40. Deep Learning CT Image Restoration using System Blur and Noise Models
  41. GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
  42. RGB2Point: 3D Point Cloud Generation from Single RGB Images
  43. A Measure for Level of Autonomy Based on Observable System Behavior
  44. Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
  45. ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition
  46. Technical report: Improving the properties of molecules generated by LIMO
  47. Base and Exponent Prediction in Mathematical Expressions using Multi-Output CNN
  48. Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives
  49. Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models
  50. Temporal Residual Jacobians For Rig-free Motion Transfer
  51. Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces
  52. CoCoG-2: Controllable generation of visual stimuli for understanding human concept representation
  53. Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
  54. Conversational Rubert for Detecting Competitive Interruptions in ASR-Transcribed Dialogues
  55. Consent in Crisis: The Rapid Decline of the AI Data Commons
  56. POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
  57. TraveLLM: Could you plan my new public transit route in face of a network disruption?
  58. RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies
  59. RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddings
  60. PolyR-CNN: R-CNN for end-to-end polygonal building outline extraction
  61. Self-supervised transformer-based pre-training method with General Plant Infection dataset
  62. Visual Geo-Localization from images
  63. Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
  64. Automated Patient Positioning with Learned 3D Hand Gestures
  65. Hyperspectral Unmixing Under Endmember Variability: A Variational Inference Framework
  66. Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis
  67. Falcon2-11B Technical Report
  68. Inferring Ingrained Remote Information in AC Power Flows Using Neuromorphic Modality Regime
  69. Reduced Effectiveness of Kolmogorov-Arnold Networks on Functions with Noise
  70. A New Dataset and Framework for Real-World Blurred Images Super-Resolution
  71. Thompson Sampling Itself is Differentially Private
  72. Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
  73. Preictal Period Optimization for Deep Learning-Based Epileptic Seizure Prediction
  74. Seal: Advancing Speech Language Models to be Few-Shot Learners
  75. Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts
  76. Dual High-Order Total Variation Model for Underwater Image Restoration
  77. An Explainable Fast Deep Neural Network for Emotion Recognition
  78. Improving Bias Correction Standards by Quantifying its Effects on Treatment Outcomes
  79. Enhancing High-Energy Particle Physics Collision Analysis through Graph Data Attribution Techniques
  80. CBCTLiTS: A Synthetic, Paired CBCT/CT Dataset For Segmentation And Style Transfer
  81. A Tale of Single-channel Electroencephalogram: Devices, Datasets, Signal Processing, Applications, and Future Directions
  82. Integrated BIM and Machine Learning System for Circularity Prediction of Construction Demolition Waste
  83. Realistic Surgical Image Dataset Generation Based On 3D Gaussian Splatting
  84. Prompting the Unknown: Understanding Response Uncertainty in Large Language Models
  85. Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns
  86. Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks
  87. Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyond
  88. Text Style Transfer: An Introductory Overview
  89. Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding
  90. GaitMA: Pose-guided Multi-modal Feature Fusion for Gait Recognition
  91. Decoupled Prompt-Adapter Tuning for Continual Activity Recognition
  92. FairViT: Fair Vision Transformer via Adaptive Masking
  93. Automatic Real-word Error Correction in Persian Text
  94. FedPartWhole: Federated domain generalization via consistent part-whole hierarchies
  95. PERCORE: A Deep Learning-Based Framework for Persian Spelling Correction with Phonetic Analysis
  96. Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights
  97. MedMAE: A Self-Supervised Backbone for Medical Imaging Tasks
  98. Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach
  99. Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation
  100. Subgraph Clustering and Atom Learning for Improved Image Classification
All 118
  1. I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation
  2. Fairness Interventions in Classification: A Study on AI Explainability
  3. Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs
  4. DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control
  5. Enhancing Skin Disease Classification Leveraging Transformer-based Deep Learning Architectures and Explainable AI
  6. Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures
  7. A Comprehensive Review of Few-shot Action Recognition
  8. Denoising Long- and Short-term Interests for Sequential Recommendation
  9. Orthogonal Hyper-category Guided Multi-interest Elicitation for Micro-video Matching
  10. Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
  11. ECRTime: Ensemble Integration of Classification and Retrieval for Time Series Classification
  12. Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
  13. Economy Watchers Survey Provides Datasets and Tasks for Japanese Financial Domain
  14. MetaAug: Meta-Data Augmentation for Post-Training Quantization
  15. CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting
  16. Downstream-Pretext Domain Knowledge Traceback for Active Learning
  17. Universal Medical Imaging Model for Domain Generalization with Data Privacy
  18. Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence