mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 8 Jan 2022

58 papers

  1. A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  2. Two-Pass End-to-End ASR Model CompressionKnowledge distillation → Speech and audio distillation
  3. Beyond modeling: NLP Pipeline for efficient environmental policy analysis
  4. A Machine Learning Based Algorithm for Joint Improvement of Power Control, link adaptation, and Capacity in Beyond 5G Communication systems
  5. Forecasting Loss of Signal in Optical Networks with Machine Learning
  6. Knowledge Tracing: A Survey
  7. Impact of Stop Sets on Stopping Active Learning for Text Classification
  8. Multi-View Non-negative Matrix Factorization Discriminant Learning via Cross Entropy Loss
  9. VGAER: Graph Neural Network Reconstruction based Community Detection
  10. Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists
  11. Lazy Lagrangians with Predictions for Online Learning
  12. Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision
  13. Attention-based Random Forest and Contamination Model
  14. Defocus Deblur Microscopy via Head-to-Tail Cross-scale Fusion
  15. Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture
  16. LoMar: A Local Defense Against Poisoning Attack on Federated Learning
  17. Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy
  18. PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++
  19. Decoupling Makes Weakly Supervised Local Feature Better
  20. Effect of Toxic Review Content on Overall Product Sentiment
  21. Fake Hilsa Fish Detection Using Machine Vision
  22. Image-based Automatic Dial Meter Reading in Unconstrained Scenarios
  23. Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
  24. Learning Sample Importance for Cross-Scenario Video Temporal Grounding
  25. Coherence-Based Distributed Document Representation Learning for Scientific Documents
  26. Mushrooms Detection, Localization and 3D Pose Estimation using RGB-D Sensor for Robotic-picking Applications
  27. Self-aligned Spatial Feature Extraction Network for UAV Vehicle Re-identification
  28. Reconfigurable Intelligent Surface Enabled Spatial Multiplexing with Fully Convolutional Network
  29. Weighted Encoding Optimization for Dynamic Single-pixel Imaging and Sensing
  30. SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception
  31. CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
  32. Optimal 1-Wasserstein Distance for WGANs
  33. AnomMAN: Detect Anomaly on Multi-view Attributed Networks
  34. Classification of Hyperspectral Images by Using Spectral Data and Fully Connected Neural Network
  35. Clustering Text Using Attention
  36. Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization
  37. A fall alert system with prior-fall activity identification
  38. Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence
  39. RARA: Zero-shot Sim2Real Visual Navigation with Following Foreground Cues
  40. A Unified Review of Deep Learning for Automated Medical Coding
  41. Defining maximum acceptable latency of AI-enhanced CAI tools
  42. Scaling Knowledge Graph Embedding Models
  43. Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
  44. A Fair and Efficient Hybrid Federated Learning Framework based on XGBoost for Distributed Power Prediction
  45. A Baseline Statistical Method For Robust User-Assisted Multiple Segmentation
  46. ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems
  47. A Sneak Attack on Segmentation of Medical Images Using Deep Neural Network Classifiers
  48. QuadTree Attention for Vision Transformers
  49. Global Convergence Analysis of Deep Linear Networks with A One-neuron Layer
  50. Modeling Human-AI Team Decision Making
  51. DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks
  52. Machine Learning-Based Disease Diagnosis:A Bibliometric Analysis
  53. Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand
  54. Expert Knowledge-guided Geometric Representation Learning for Magnetic Resonance Imaging-based Glioma Grading
  55. Provable Clustering of a Union of Linear Manifolds Using Optimal Directions
  56. Real-time Rail Recognition Based on 3D Point Clouds
  57. Low-Rank Constraints for Fast Inference in Structured Models
  58. Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment