mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 25 Dec 2023

100 papers

  1. ShiftKD: Benchmarking Knowledge Distillation under Distribution ShiftKnowledge distillation → General knowledge distillation methods
  2. Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided DiffusionDiffusion models → Robustness, privacy and adversarial aspects
  3. Audiobox: Unified Audio Generation with Natural Language PromptsDiffusion models → Audio, speech and music
  4. TEILP: Time Prediction over Knowledge Graphs via Logical ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  5. A Recipe for Scaling up Text-to-Video Generation with Text-free VideosDiffusion models → Video generation
  6. Towards Real-World Blind Face Restoration with Generative Diffusion PriorDiffusion models → Inverse problems and image restoration
  7. High-Fidelity Diffusion-based Image EditingDiffusion models → Image generation, text-to-image and editing
  8. What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction TuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide GenerationDiffusion models → Flow matching, time series and science
  10. Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis GenerationLLM reasoning → Reasoning benchmarks and evaluation
  11. Balanced SNR-Aware Distillation for Guided Text-to-Audio GenerationDiffusion models → Audio, speech and music
  12. Choosing the Right Path for AI Integration in Engineering Companies: A Strategic Guide
  13. Active headrest combined with a depth camera-based ear-positioning system
  14. SAiD: Speech-driven Blendshape Facial Animation with Diffusion
  15. VAE for Modified 1-Hot Generative Materials Modeling, A Step Towards Inverse Material Design
  16. μ-Net: ConvNext-Based U-Nets for Cosmic Muon Tomography
  17. ESGReveal: An LLM-based approach for extracting structured data from ESG reports
  18. TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification
  19. MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks
  20. A Comprehensive Study of Object Tracking in Low-Light Environments
  21. XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
  22. Toward Accurate and Temporally Consistent Video Restoration from Raw Data
  23. Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
  24. iKUN: Speak to Trackers without Retraining
  25. Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks
  26. Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
  27. Merging Vision Transformers from Different Tasks and Domains
  28. Chatbot is Not All You Need: Information-rich Prompting for More Realistic Responses
  29. Navigating Decision Landscapes: The Impact of Principals on Decision-Making Dynamics
  30. Comparative Analysis of Radiomic Features and Gene Expression Profiles in Histopathology Data Using Graph Neural Networks
  31. Self-Supervised Learning for Few-Shot Bird Sound Classification
  32. A Sequential Detection and Tracking of Very Low SNR Objects
  33. WebVLN: Vision-and-Language Navigation on Websites
  34. Viral Marketing in Social Networks with Competing Products
  35. A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systems
  36. Compositional Generalization in Spoken Language Understanding
  37. Small Effect Sizes in Malware Detection? Make Harder Train/Test Splits!
  38. A Closed-Loop Multi-perspective Visual Servoing Approach with Reinforcement Learning
  39. Efficient Conformal Prediction under Data Heterogeneity
  40. GenCast: Diffusion-based ensemble forecasting for medium-range weather
  41. Robust Stochastically-Descending Unrolled Networks
  42. AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining
  43. Design and Implementation of a Tool for Extracting Uzbek Syllables
  44. Lp-Norm Constrained One-Class Classifier Combination
  45. On Robust Wasserstein Barycenter: The Model and Algorithm
  46. Solving Label Variation in Scientific Information Extraction via Multi-Task Learning
  47. Large Language Models are Not Stable Recommender Systems
  48. DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection
  49. Improving the Accuracy and Interpretability of Neural Networks for Wind Power Forecasting
  50. BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge
  51. Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement
  52. Diversity-Based Recruitment in Crowdsensing By Combinatorial Multi-Armed Bandits
  53. Set Prediction Guided by Semantic Concepts for Diverse Video Captioning
  54. Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos
  55. Spatial-Temporal Interplay in Human Mobility: A Hierarchical Reinforcement Learning Approach with Hypergraph Representation
  56. UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
  57. PersianLLaMA: Towards Building First Persian Large Language Model
  58. Alleviating Hallucinations of Large Language Models through Induced Hallucinations
  59. TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning
  60. Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning
  61. Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
  62. RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair
  63. EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data
  64. Instruction Fusion: Advancing Prompt Evolution through Hybridization
  65. Word length-aware text spotting: Enhancing detection and recognition in dense text image
  66. PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
  67. Stochastic mean-shift clustering
  68. Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers
  69. BDIS-SLAM: A lightweight CPU-based dense stereo SLAM for surgery
  70. 3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
  71. Open-Vocabulary Video Relation Extraction
  72. TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient
  73. IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models
  74. Unlocking the Potential of Large Language Models for Explainable Recommendations
  75. Swap-based Deep Reinforcement Learning for Facility Location Problems in Networks
  76. A graph-based multimodal framework to predict gentrification
  77. Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment
  78. UVAGaze: Unsupervised 1-to-2 Views Adaptation for Gaze Estimation
  79. Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation
  80. MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility
  81. RDF-star2Vec: RDF-star Graph Embeddings for Data Mining
  82. Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Vision
  83. GanFinger: GAN-Based Fingerprint Generation for Deep Neural Network Ownership Verification
  84. Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction
  85. A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks
  86. APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
  87. Inference of Dependency Knowledge Graph for Electronic Health Records
  88. Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks
  89. Federated learning-outcome prediction with multi-layer privacy protection
  90. A Target Detection Algorithm in Traffic Scenes Based on Deep Reinforcement Learning
  91. A Split-and-Privatize Framework for Large Language Model Fine-Tuning
  92. Context-aware Communication for Multi-agent Reinforcement Learning
  93. Zero-Inflated Bandits
  94. DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognition
  95. Privacy-Preserved Neural Graph Databases
  96. Deep Structure and Attention Aware Subspace Clustering
  97. Reducing LLM Hallucinations using Epistemic Neural Networks
  98. Neural Born Series Operator for Biomedical Ultrasound Computed Tomography
  99. Clustered Switchback Designs for Experimentation Under Spatio-temporal Interference
  100. A Survey on Open-Set Image Recognition