mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 11 Aug 2024

93 papers

  1. GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person PerspectiveLLM reasoning → Audio-language model reasoning
  2. Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree SearchLLM safety and security → Prompt injection and agent security
  3. LaWa: Using Latent Space for In-Generation Image WatermarkingLLM safety and security → Watermarking generated content and models
  4. Egocentric Vision Language PlanningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  5. CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
  6. Efficient Test-Time Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  7. Reference-free Hallucination Detection for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  8. Low-Dimensional Federated Knowledge Graph Embedding via Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
  9. Parallel Distributional Deep Reinforcement Learning for Mapless Navigation of Terrestrial Mobile RobotsDeep reinforcement learning methods → RL for robot navigation and UAV control
  10. Neural Architecture Search based Global-local Vision Mamba for Palm-Vein RecognitionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  11. MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent ImputationDiffusion models → Flow matching, time series and science
  12. SSL: A Self-similarity Loss for Improving Generative Image Super-resolutionDiffusion models → Inverse problems and image restoration
  13. Efficient Diffusion Transformer with Step-wise Dynamic Attention MediatorsDiffusion models → Diffusion foundations and sampling
  14. SMILES-Mamba: Chemical Mamba Foundation Models for Drug ADMET PredictionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  15. The Bandit Whisperer: Communication Learning for Restless BanditsDeep reinforcement learning methods → RL for energy, networks and operations
  16. StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  17. People over trust AI-generated medical responses and view them to be as valid as doctors, despite low accuracy
  18. Multitask Fine-Tuning and Generative Adversarial Learning for Improved Auxiliary Classification
  19. S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation
  20. Exploiting Formal Concept Analysis for Data Modeling in Data Lakes
  21. Post-Training Sparse Attention with Double Sparsity
  22. Autoregressive Enzyme Function Prediction with Multi-scale Multi-modality Fusion
  23. Approximate ADCs for In-Memory Computing
  24. LLM-Based Robust Product Classification in Commerce and Compliance
  25. Recognizing Limits: Investigating Infeasibility in Large Language Models
  26. SABER-6D: Shape Representation Based Implicit Object Pose Estimation
  27. Temporal Knowledge-Graph Memory in a Partially Observable Environment
  28. Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning
  29. The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms
  30. Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends
  31. Using Retriever Augmented Large Language Models for Attack Graph Generation
  32. On the Robustness of Kernel Goodness-of-Fit Tests
  33. An End-to-End Model for Time Series Classification In the Presence of Missing Values
  34. Online Matrix Completion: A Collaborative Approach with Hott Items
  35. Open Role-Playing with Delta-Engines
  36. Iterative Improvement of an Additively Regularized Topic Model
  37. Deep Learning in Medical Image Registration: Magic or Mirage?
  38. Real-Time Drowsiness Detection Using Eye Aspect Ratio and Facial Landmark Detection
  39. Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
  40. Robust Domain Generalization for Multi-modal Object Recognition
  41. Sampling Foundational Transformer: A Theoretical Perspective
  42. Fast convergence of a Federated Expectation-Maximization Algorithm
  43. HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training
  44. Kernel Density Estimators in Large Dimensions
  45. A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
  46. Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI
  47. Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
  48. A Comparative Study of Convolutional and Recurrent Neural Networks for Storm Surge Prediction in Tampa Bay
  49. A Meta-Engine Framework for Interleaved Task and Motion Planning using Topological Refinements
  50. HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes
  51. SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events
  52. Continual Learning of Nonlinear Independent Representations
  53. On zero-shot learning in neural state estimation of power distribution systems
  54. HiLight: A Hierarchy-aware Light Global Model with Hierarchical Local ConTrastive Learning
  55. U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training
  56. Pareto Front Shape-Agnostic Pareto Set Learning in Multi-Objective Optimization
  57. Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task
  58. Neurosymbolic Methods for Rule Mining
  59. An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set
  60. LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
  61. Scalable and Adaptive Spectral Embedding for Attributed Graph Clustering
  62. Personalized Federated Learning for improving radar based precipitation nowcasting on heterogeneous areas
  63. VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing
  64. PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data Settings
  65. RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
  66. Advancing Re-Ranking with Multimodal Fusion and Target-Oriented Auxiliary Tasks in E-Commerce Search
  67. FADE: A Dataset for Detecting Falling Objects around Buildings in Video
  68. Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
  69. Improving Adversarial Transferability with Neighbourhood Gradient Information
  70. Language-Informed Beam Search Decoding for Multilingual Machine Translation
  71. A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
  72. Deep Learning with Data Privacy via Residual Perturbation
  73. Deformable Image Registration with Multi-scale Feature Fusion from Shared Encoder, Auxiliary and Pyramid Decoders
  74. Top Pass: Improve Code Generation by Pass@k-Maximized Code Ranking
  75. DeepAir: A Multi-Agent Deep Reinforcement Learning Based Scheme for an Unknown User Location Problem
  76. Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval
  77. Fast and Scalable Semi-Supervised Learning for Multi-View Subspace Clustering
  78. Decoder Pre-Training with only Text for Scene Text Recognition
  79. TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature Scaling
  80. Predicting Chaotic System Behavior using Machine Learning Techniques
  81. MacFormer: Semantic Segmentation with Fine Object Boundaries
  82. Evaluating BM3D and NBNet: A Comprehensive Study of Image Denoising Across Multiple Datasets
  83. A Novel Momentum-Based Deep Learning Techniques for Medical Image Classification and Segmentation
  84. Strong denoising of financial time-series
  85. Single Image Dehazing Using Scene Depth Ordering
  86. Decoupling Generation and Evaluation for Parallel Greedy Best-First Search(extended version)
  87. SRTFD: Scalable Real-Time Fault Diagnosis through Online Continual Learning
  88. Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data
  89. Tensor Decomposition Meets RKHS: Efficient Algorithms for Smooth and Misaligned Data
  90. PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection
  91. PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT
  92. Training an NLP Scholar at a Small Liberal Arts College: A Backwards Designed Course Proposal
  93. Performance Evaluation of YOLOv8 Model Configurations, for Instance Segmentation of Strawberry Fruit Development Stages in an Open Field Environment