mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 22 Aug 2021

59 papers

  1. From Two to One: A New Scene Text Recognizer with Visual Language Modeling NetworkMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  2. Evolving Evolutionary Algorithms using Multi Expression Programming
  3. Multilingual Speech Recognition for Low-Resource Indian Languages using Multi-Task conformer
  4. A Dual-Decoder Conformer for Multilingual Speech Recognition
  5. Training and Profiling a Pediatric Emotion Recognition Classifier on Mobile Devices
  6. Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers
  7. Explainable Machine Learning using Real, Synthetic and Augmented Fire Tests to Predict Fire Resistance and Spalling of RC Columns
  8. Convex Latent Effect Logit Model via Sparse and Low-rank Decomposition
  9. Data Augmentation Using Many-To-Many RNNs for Session-Aware Recommender Systems
  10. FRUGAL: Unlocking SSL for Software Analytics
  11. Temporal Network Embedding via Tensor Factorization
  12. All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces
  13. Embodied AI-Driven Operation of Smart Cities: A Concise Review
  14. Electroencephalogram Signal Processing with Independent Component Analysis and Cognitive Stress Classification using Convolutional Neural Networks
  15. UzBERT: pretraining a BERT model for Uzbek
  16. Efficient Algorithms for Learning from Coarse Labels
  17. Wind Power Projection using Weather Forecasts by Novel Deep Neural Networks
  18. Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger
  19. MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
  20. Relating CNNs with brain: Challenges and findings
  21. A Boosting Approach to Reinforcement Learning
  22. Image Inpainting via Conditional Texture and Structure Dual Generation
  23. Graph2Pix: A Graph-Based Image to Image Translation Framework
  24. Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
  25. A Transformer Architecture for Stress Detection from ECG
  26. A universally consistent learning rule with a universally monotone error
  27. EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA
  28. Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbations
  29. FEDI: Few-shot learning based on Earth Mover's Distance algorithm combined with deep residual network to identify diabetic retinopathy
  30. Self-Regulation for Semantic Segmentation
  31. Spatial Transformer Networks for Curriculum Learning
  32. Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads
  33. Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering
  34. Rainfall-runoff prediction using a Gustafson-Kessel clustering based Takagi-Sugeno Fuzzy model
  35. Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification
  36. Efficient Gaussian Neural Processes for Regression
  37. Detection and Localization of Multiple Image Splicing Using MobileNet V1
  38. Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
  39. Learning of Visual Relations: The Devil is in the Tails
  40. Relational Embedding for Few-Shot Classification
  41. New Trends in Quantum Machine Learning
  42. SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation
  43. Evolutionary Ensemble Learning for Multivariate Time Series Prediction
  44. ExamGAN and Twin-ExamGAN for Exam Script Generation
  45. Domain Adaptation for Underwater Image Enhancement
  46. The Exploitation of Distance Distributions for Clustering
  47. A Systematic Review of Automated Query Reformulations in Source Code Search
  48. Improving Mini-batch Optimal Transport via Partial Transportation
  49. Deep survival analysis with longitudinal X-rays for COVID-19
  50. DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
  51. Signed Bipartite Graph Neural Networks
  52. Graph-Convolutional Deep Learning to Identify Optimized Molecular Configurations
  53. StarVQA: Space-Time Attention for Video Quality Assessment
  54. DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
  55. Impact of Evaluation Methodologies on Code Summarization
  56. Personalised Federated Learning: A Combinational Approach
  57. Apache Submarine: A Unified Machine Learning Platform Made Simple
  58. Self-Supervised Delineation of Geological Structures using Orthogonal Latent Space Projection
  59. Tensor Pooling Driven Instance Segmentation Framework for Baggage Threat Recognition