mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 5 Mar 2023

83 papers

  1. A Formal Metareasoning Model of Concurrent Planning and ExecutionLLM reasoning → Reasoning for agents, planning and code
  2. Seq2Seq Imitation Learning for Tactile Feedback-based ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  3. Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution MatchingOffline RL and imitation learning from data → Imitation learning methods
  4. Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forums
  5. Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation
  6. Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild
  7. How to Construct Energy for Images? Denoising Autoencoder Can Be Energy Based Model
  8. A Provably Secure Strong PUF based on LWE: Construction and Implementation
  9. Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification
  10. CoRTX: Contrastive Framework for Real-time Explanation
  11. Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning
  12. Robustness, Evaluation and Adaptation of Machine Learning Models in the Wild
  13. A Low-Cost Portable Apparatus to Analyze Oral Fluid Droplets and Quantify the Efficacy of Masks
  14. Universal distribution of the empirical coverage in split conformal prediction
  15. A Study of Augmentation Methods for Handwritten Stenography Recognition
  16. Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes
  17. WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks
  18. Frequency-domain Blind Quality Assessment of Blurred and Blocking-artefact Images using Gaussian Process Regression model
  19. Revisiting the Noise Model of Stochastic Gradient Descent
  20. IDA: Informed Domain Adaptive Semantic Segmentation
  21. Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback
  22. SePaint: Semantic Map Inpainting via Multinomial Diffusion
  23. Scalable Object Detection on Embedded Devices Using Weight Pruning and Singular Value Decomposition
  24. Reparameterization through Spatial Gradient Scaling
  25. Iterative Approximate Cross-Validation
  26. Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality
  27. Local Environment Poisoning Attacks on Federated Reinforcement Learning
  28. Active learning using region-based sampling
  29. A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS
  30. Learning to Localize in Unseen Scenes with Relative Pose Regressors
  31. Deep Learning in the Field of Biometric Template Protection: An Overview
  32. Industry Risk Assessment via Hierarchical Financial Data Using Stock Market Sentiment Indicators
  33. HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling
  34. Robust affine point matching via quadratic assignment on Grassmannians
  35. Understanding Bugs in Multi-Language Deep Learning Frameworks
  36. Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
  37. Revisiting Weighted Strategy for Non-stationary Parametric Bandits
  38. Text2Face: A Multi-Modal 3D Face Model
  39. Mining both Commonality and Specificity from Multiple Documents for Multi-Document Summarization
  40. Continuous-Time Gaussian Process Motion-Compensation for Event-vision Pattern Tracking with Distance Fields
  41. Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models
  42. Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT
  43. Learned Lossless Compression for JPEG via Frequency-Domain Prediction
  44. Heterogeneous Graph Learning for Acoustic Event Classification
  45. SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data
  46. On the Capacity Limits of Privileged ERM
  47. Sparsity-Aware Intelligent Massive Random Access Control in Open RAN: A Reinforcement Learning Based Approach
  48. On Modifying a Neural Network's Perception
  49. Comparative study of Transformer and LSTM Network with attention mechanism on Image Captioning
  50. Expectation consistency for calibration of neural networks
  51. CueCAn: Cue Driven Contextual Attention For Identifying Missing Traffic Signs on Unconstrained Roads
  52. Swim: A General-Purpose, High-Performing, and Efficient Activation Function for Locomotion Control Tasks
  53. A Semi-Bayesian Nonparametric Estimator of the Maximum Mean Discrepancy Measure: Applications in Goodness-of-Fit Testing and Generative Adversarial Networks
  54. VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning
  55. Deep-Learning-based Counting Methods, Datasets, and Applications in Agriculture -- A Review
  56. Ensemble Reinforcement Learning: A Survey
  57. Estimating Extreme 3D Image Rotation with Transformer Cross-Attention
  58. HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
  59. Event-based Camera Simulation using Monte Carlo Path Tracing with Adaptive Denoising
  60. DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detection
  61. Knowledge-Based Counterfactual Queries for Visual Question Answering
  62. Hybrid Y-Net Architecture for Singing Voice Separation
  63. PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow
  64. Super-Resolution Neural Operator
  65. Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data
  66. MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition
  67. Learning Decentralized Power Control in Cell-Free Massive MIMO Networks
  68. Time Associated Meta Learning for Clinical Prediction
  69. Unlearnable Graph: Protecting Graphs from Unauthorized Exploitation
  70. MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Information
  71. FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis
  72. The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences
  73. CAMEL: Curvature-Augmented Manifold Embedding and Learning
  74. Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation
  75. Bounding the Optimal Value Function in Compositional Reinforcement Learning
  76. Self-reinforced polynomial approximation methods for concentrated probability densities
  77. An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry
  78. Discrepancies among Pre-trained Deep Neural Networks: A New Threat to Model Zoo Reliability
  79. Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
  80. Streaming Active Learning with Deep Neural Networks
  81. Semi-parametric inference based on adaptively collected data
  82. PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities
  83. DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network