mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 24 Nov 2021

164 papers

  1. Needle in a Haystack: Detecting Subtle Malicious Edits to Additive Manufacturing G-code FilesLLM safety and security → Backdoor and data poisoning attacks
  2. Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized CodesDiffusion models → Diffusion foundations and sampling
  3. Conditional Object-Centric Learning from VideoWorld models → Latent predictive world models
  4. EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge DistillationKnowledge distillation → Multimodal distillation
  5. Scaling Up Vision-Language Pre-training for Image CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes
  7. Coarse-To-Fine Incremental Few-Shot Learning
  8. Machine Learning for Real-Time, Automatic, and Early Diagnosis of Parkinson's Disease by Extracting Signs of Micrographia from Handwriting Images
  9. On computable learning of continuous features
  10. Improving Customer Service Chatbots with Attention-based Transfer Learning
  11. TMM-Fast: A Transfer Matrix Computation Package for Multilayer Thin-Film Optimization
  12. Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers
  13. Information Bottleneck-Based Hebbian Learning Rule Naturally Ties Working Memory and Synaptic Updates
  14. Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
  15. Animal Behavior Classification via Accelerometry Data and Recurrent Neural Networks
  16. Explaining machine-learned particle-flow reconstruction
  17. SchemaDB: Structures in Relational Datasets
  18. TSO-DSOs Stable Cost Allocation for the Joint Procurement of Flexibility: A Cooperative Game Approach
  19. Cross Your Body: A Cognitive Assessment System for Children
  20. Fairness for AUC via Feature Augmentation
  21. Application of deep learning to camera trap data for ecologists in planning / engineering -- Can captivity imagery train a model which generalises to the wild?
  22. A Rule-based/BPSO Approach to Produce Low-dimensional Semantic Basis Vectors Set
  23. Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
  24. ReAct: Out-of-distribution Detection With Rectified Activations
  25. Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
  26. Picasso: Model-free Feature Visualization
  27. Improving the Perceptual Quality of 2D Animation Interpolation
  28. Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning
  29. Temporal Effects on Pre-trained Models for Language Processing Tasks
  30. Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator
  31. Differentially Private Nonparametric Regression Under a Growth Condition
  32. For the Purpose of Curry: A UD Treebank for Ashokan Prakrit
  33. Fast mesh denoising with data driven normal filtering using deep variational autoencoders
  34. Transferability Estimation using Bhattacharyya Class Separability
  35. IMBENS: Ensemble Class-imbalanced Learning in Python
  36. JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
  37. Towards an Efficient Semantic Segmentation Method of ID Cards for Verification Systems
  38. Sparse is Enough in Scaling Transformers
  39. Lensless multicore-fiber microendoscope for real-time tailored light field generation with phase encoder neural network (CoreNet)
  40. ACNet: Approaching-and-Centralizing Network for Zero-Shot Sketch-Based Image Retrieval
  41. FCMpy: A Python Module for Constructing and Analyzing Fuzzy Cognitive Maps
  42. Layered Controllable Video Generation
  43. Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering
  44. Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
  45. Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets
  46. PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
  47. MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
  48. MixSyn: Learning Composition and Style for Multi-Source Image Synthesis
  49. Investigating Tradeoffs in Real-World Video Super-Resolution
  50. Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
  51. Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling
  52. A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
  53. A stacked deep convolutional neural network to predict the remaining useful life of a turbofan engine
  54. EgoRenderer: Rendering Human Avatars from Egocentric Camera Images
  55. VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
  56. An XGBoost-Based Forecasting Framework for Product Cannibalization
  57. On the (In)Tractability of Reinforcement Learning for LTL Objectives
  58. Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning
  59. Finite-Time Error Bounds for Distributed Linear Stochastic Approximation
  60. MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning
  61. Analysing Statistical methods for Automatic Detection of Image Forgery
  62. SM3D: Simultaneous Monocular Mapping and 3D Detection
  63. Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approaches
  64. Efficient Decompositional Rule Extraction for Deep Neural Networks
  65. Self-slimmed Vision Transformer
  66. Accelerating Deep Learning with Dynamic Data Pruning
  67. GreedyNASv2: Greedier Search with a Greedy Path Filter
  68. Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
  69. Deep metric learning improves lab of origin prediction of genetically engineered plasmids
  70. State-space deep Gaussian processes with applications
  71. Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
  72. Learning State Representations via Retracing in Reinforcement Learning
  73. Lepard: Learning partial point cloud matching in rigid and deformable scenes
  74. Towards Cross-Cultural Analysis using Music Information Dynamics
  75. Optimizing Latent Space Directions For GAN-based Local Image Editing
  76. UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
  77. Water Care: Water Surface Cleaning Bot and Water Body Surveillance System
  78. A Method for Evaluating Deep Generative Models of Images via Assessing the Reproduction of High-order Spatial Context
  79. ModelPred: A Framework for Predicting Trained Model from Training Data
  80. LDDMM meets GANs: Generative Adversarial Networks for diffeomorphic registration
  81. Autonomous bot with ML-based reactive navigation for indoor environment
  82. Rethinking the modeling of the instrumental response of telescopes with a differentiable optical model
  83. Knowledge Enhanced Sports Game Summarization
  84. Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations
  85. MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
  86. Mining Meta-indicators of University Ranking: A Machine Learning Approach Based on SHAP
  87. Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
  88. LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation
  89. Generalized Normalizing Flows via Markov Chains
  90. Extracting Triangular 3D Models, Materials, and Lighting From Images
  91. TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation
  92. Meta Mask Correction for Nuclei Segmentation in Histopathological Image
  93. Altering Backward Pass Gradients improves Convergence
  94. Efficient semidefinite bounds for multi-label discrete graphical models
  95. Matching Learned Causal Effects of Neural Networks with Domain Priors
  96. Intuitive Shape Editing in Latent Space
  97. Understanding the Dynamics of DNNs Using Graph Modularity
  98. LDP-Net: An Unsupervised Pansharpening Network Based on Learnable Degradation Processes
  99. One More Step Towards Reality: Cooperative Bandits with Imperfect Communication
  100. Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences
All 164
  1. Selection of pseudo-annotated data for adverse drug reaction classification across drug groups
  2. Hierarchical Modular Network for Video Captioning
  3. Introduction to Presentation Attack Detection in Iris Biometrics and Recent Advances
  4. ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment
  5. Exploring Business Process Deviance with Sequential and Declarative Patterns
  6. Background-Click Supervision for Temporal Action Localization
  7. 3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces
  8. Revisiting Contextual Toxicity Detection in Conversations
  9. Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
  10. tsflex: flexible time series processing & feature extraction
  11. Challenges of Adversarial Image Augmentations
  12. Few-shot Named Entity Recognition with Cloze Questions
  13. NAM: Normalization-based Attention Module
  14. N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion
  15. Auto robust relative radiometric normalization via latent change noise modelling
  16. An Attack on Facial Soft-biometric Privacy Enhancement
  17. Dictionary-based Low-Rank Approximations and the Mixed Sparse Coding problem
  18. Track Boosting and Synthetic Data Aided Drone Detection
  19. One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
  20. Space-Partitioning RANSAC
  21. Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks
  22. Human Activity Recognition Using 3D Orthogonally-projected EfficientNet on Radar Time-Range-Doppler Signature
  23. MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing
  24. Uniform Convergence Rates for Lipschitz Learning on Graphs
  25. SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning
  26. Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
  27. Supervised Neural Discrete Universal Denoiser for Adaptive Denoising
  28. Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing
  29. How does AI play football? An analysis of RL and real-world football strategies
  30. Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
  31. MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images
  32. Consistency Regularization for Deep Face Anti-Spoofing
  33. Handling tree-structured text: parsing directory pages
  34. A note on stabilizing reinforcement learning
  35. Dynamic Texture Recognition using PDV Hashing and Dictionary Learning on Multi-scale Volume Local Binary Pattern
  36. RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
  37. Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability
  38. Thundernna: a white box adversarial attack
  39. Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction
  40. EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
  41. Spatial-context-aware deep neural network for multi-class image classification
  42. Animal behavior classification via deep learning on embedded systems
  43. An Image Patch is a Wave: Phase-Aware Vision MLP
  44. PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization
  45. Improved Fine-Tuning by Better Leveraging Pre-Training Data
  46. Attention-based Dual-stream Vision Transformer for Radar Gait Recognition
  47. Real-time smart vehicle surveillance system
  48. A Self-Supervised Automatic Post-Editing Data Generation Tool
  49. Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages
  50. Sharpness-aware Quantization for Deep Neural Networks
  51. Causal Analysis and Prediction of Human Mobility in the U.S. during the COVID-19 Pandemic
  52. Distribution Estimation to Automate Transformation Policies for Self-Supervision
  53. Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
  54. APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
  55. Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation
  56. PU-Transformer: Point Cloud Upsampling Transformer
  57. PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering
  58. Universal Deep Network for Steganalysis of Color Image based on Channel Representation
  59. Subspace Adversarial Training
  60. Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation
  61. Flexible Pattern Discovery and Analysis
  62. Explainable multiple abnormality classification of chest CT volumes
  63. From Kepler to Newton: Explainable AI for Science
  64. Combinations of Jaccard with Numerical Measures for Collaborative Filtering Enhancement: Current Work and Future Proposal