mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 17 Mar 2022

213 papers

  1. Delta Distillation for Efficient Video ProcessingKnowledge distillation → Detection and dense prediction distillation
  2. Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycleKnowledge distillation → General knowledge distillation methods
  3. When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data AugmentationKnowledge distillation → General knowledge distillation methods
  4. Semi-Markov Offline Reinforcement Learning for HealthcareOffline RL and imitation learning from data → Safe offline RL
  5. Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated LearningKnowledge distillation → Federated, robust and private distillation
  6. RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet ExtractionSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  7. UNIMO-2: End-to-End Unified Vision-Language Grounded LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
  9. Towards a New Science of Disinformation
  10. Encryption and encoding of facial images into quick response and high capacity color 2d code for biometric passport security system
  11. Decouple-and-Sample: Protecting sensitive information in task agnostic data release
  12. A Novel Exploration of Diffusion Process based on Multi-types Galton-Watson Forests
  13. GAM(L)A: An econometric model for interpretable Machine Learning
  14. Short Text Topic Modeling: Application to tweets about Bitcoin
  15. Label conditioned segmentation
  16. Neural Enhanced Belief Propagation for Data Association in Multiobject Tracking
  17. 3DAC: Learning Attribute Compression for Point Clouds
  18. Revealing Reliable Signatures by Learning Top-Rank Pairs
  19. Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach
  20. Low-degree learning and the metric entropy of polynomials
  21. Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation
  22. MatchFormer: Interleaving Attention in Transformers for Feature Matching
  23. Deep Reinforcement Agent for Efficient Instant Search
  24. Cascade Transformers for End-to-End Person Search
  25. Generating unrepresented proportions of geological facies using Generative Adversarial Networks
  26. Unified Line and Paragraph Detection by Graph Convolutional Networks
  27. Investigating Compounding Prediction Errors in Learned Dynamics Models
  28. A Density Evolution framework for Preferential Recovery of Covariance and Causal Graphs from Compressed Measurements
  29. Predicate Invention for Bilevel Planning
  30. Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages
  31. A Learning Framework for Bandwidth-Efficient Distributed Inference in Wireless IoT
  32. Monotonic Differentiable Sorting Networks
  33. HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information
  34. On the Importance of Data Size in Probing Fine-tuned Models
  35. The Analysis of Online Event Streams: Predicting the Next Activity for Anomaly Detection
  36. DeepLSS: breaking parameter degeneracies in large scale structure with deep learning analysis of combined probes
  37. STICC: A multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity
  38. Developing a Successful Bomberman Agent
  39. Learning Distributionally Robust Models at Scale via Composite Optimization
  40. Overview of Test Coverage Criteria for Test Case Generation from Finite State Machines Modelled as Directed Graphs
  41. Robotic Speech Synthesis: Perspectives on Interactions, Scenarios, and Ethics
  42. DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection
  43. Towards Responsible Natural Language Annotation for the Varieties of Arabic
  44. Prioritized Variable-length Test Cases Generation for Finite State Machines
  45. ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations
  46. Video-based Formative and Summative Assessment of Surgical Tasks using Deep Learning
  47. SepTr: Separable Transformer for Audio Spectrogram Processing
  48. Surface Defect Detection and Evaluation for Marine Vessels using Multi-Stage Deep Learning
  49. GAC: A Deep Reinforcement Learning Model Toward User Incentivization in Unknown Social Networks
  50. Triangle and Four Cycle Counting with Predictions in Graph Streams
  51. Leveraging Adversarial Examples to Quantify Membership Information Leakage
  52. Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination
  53. Outcome Assumptions and Duality Theory for Balancing Weights
  54. On the expressive power of message-passing neural networks as global feature map transformers
  55. CoGS: Controllable Generation and Search from Sketch and Style
  56. Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
  57. Multi-similarity based Hyperrelation Network for few-shot segmentation
  58. Human Gait Analysis using Gait Energy Image
  59. SemTUI: a Framework for the Interactive Semantic Enrichment of Tabular Data
  60. TensoRF: Tensorial Radiance Fields
  61. AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation
  62. On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
  63. DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection
  64. ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
  65. Towards Data-Efficient Detection Transformers
  66. Visualizing Global Explanations of Point Cloud DNNs
  67. The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents
  68. Transframer: Arbitrary Frame Prediction with Generative Models
  69. An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models
  70. Electronic excited states in deep variational Monte Carlo
  71. FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos
  72. Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image
  73. Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation
  74. Continual Learning Based on OOD Detection and Task Masking
  75. Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks
  76. Image Super-Resolution With Deep Variational Autoencoders
  77. Learning of Structurally Unambiguous Probabilistic Grammars
  78. TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes
  79. An Explainable Stacked Ensemble Model for Static Route-Free Estimation of Time of Arrival
  80. Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions
  81. Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation
  82. elBERto: Self-supervised Commonsense Learning for Question Answering
  83. Deep Unsupervised Hashing with Latent Semantic Components
  84. ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
  85. Bi-directional Object-context Prioritization Learning for Saliency Ranking
  86. Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images
  87. Stability and Risk Bounds of Iterative Hard Thresholding
  88. A Framework and Benchmark for Deep Batch Active Learning for Regression
  89. Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models
  90. A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
  91. One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning
  92. Euler State Networks: Non-dissipative Reservoir Computing
  93. Identifiability of Sparse Causal Effects using Instrumental Variables
  94. Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits
  95. Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans
  96. Using the Order of Tomographic Slices as a Prior for Neural Networks Pre-Training
  97. Transforming Gait: Video-Based Spatiotemporal Gait Analysis
  98. Interacting Attention Graph for Single Image Two-Hand Reconstruction
  99. Fine Detailed Texture Learning for 3D Meshes with Generative Models
  100. Expressivity of Planning with Horn Description Logic Ontologies (Technical Report)
All 213
  1. Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models
  2. POSTER: Diagnosis of COVID-19 through Transfer Learning Techniques on CT Scans: A Comparison of Deep Learning Models
  3. Dimensionality Reduction and Wasserstein Stability for Kernel Regression
  4. Error estimates for physics informed neural networks approximating the Navier-Stokes equations
  5. CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation
  6. Object Localization under Single Coarse Point Supervision
  7. Modulated Contrast for Versatile Image Synthesis
  8. Machine Learning for Encrypted Malicious Traffic Detection: Approaches, Datasets and Comparative Study
  9. Combining Static and Contextualised Multilingual Embeddings
  10. Localizing Visual Sounds the Easy Way
  11. EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
  12. Few-Shot Learning on Graphs
  13. Finding Structural Knowledge in Multimodal-BERT
  14. MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks
  15. One-Shot Adaptation of GAN in Just One CLIP
  16. A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
  17. PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer
  18. PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks
  19. HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions
  20. PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation
  21. Ranking of Communities in Multiplex Spatiotemporal Models of Brain Dynamics
  22. Knowledge Graph Embedding Methods for Entity Alignment: An Experimental Review
  23. Transfer learning for cross-modal demand prediction of bike-share and public transit
  24. Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss
  25. Stochastic and Private Nonconvex Outlier-Robust PCA
  26. ART-SS: An Adaptive Rejection Technique for Semi-Supervised restoration for adverse weather-affected images
  27. Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
  28. Progressive Subsampling for Oversampled Data - Application to Quantitative MRI
  29. Explainability in Graph Neural Networks: An Experimental Survey
  30. Contrastive Learning for Cross-Domain Open World Recognition
  31. On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
  32. Visualizing Riemannian data with Rie-SNE
  33. Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs
  34. Symmetry-Based Representations for Artificial and Biological General Intelligence
  35. On the Properties of Adversarially-Trained CNNs
  36. Depth-aware Neural Style Transfer using Instance Normalization
  37. Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study
  38. HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR
  39. Universal Conditional Masked Language Pre-training for Neural Machine Translation
  40. Neural Compression-Based Feature Learning for Video Restoration
  41. Simulation-Driven Training of Vision Transformers Enabling Metal Segmentation in X-Ray Images
  42. SoK: Differential Privacy on Graph-Structured Data
  43. Investigation of Physics-Informed Deep Learning for the Prediction of Parametric, Three-Dimensional Flow Based on Boundary Data
  44. Novel Consistency Check For Fast Recursive Reconstruction Of Non-Regularly Sampled Video Data
  45. Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
  46. Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
  47. Abstract Interpretation on E-Graphs
  48. RoMe: A Robust Metric for Evaluating Natural Language Generation
  49. An Interactive Explanatory AI System for Industrial Quality Control
  50. A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected Layers
  51. Maximum Likelihood Estimation in Gaussian Process Regression is Ill-Posed
  52. Multilingual Detection of Personal Employment Status on Twitter
  53. ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
  54. Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding
  55. Nearest Neighbor Classifier with Margin Penalty for Active Learning
  56. On Vision Features in Multimodal Machine Translation
  57. Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
  58. On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
  59. Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion
  60. Modeling Dual Read/Write Paths for Simultaneous Machine Translation
  61. How Many Data Samples is an Additional Instruction Worth?
  62. Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation
  63. Optimal Rejection Function Meets Character Recognition Tasks
  64. Active Visuo-Haptic Object Shape Completion
  65. Prediction of speech intelligibility with DNN-based performance measures
  66. Covid19 Reproduction Number: Credibility Intervals by Blockwise Proximal Monte Carlo Samplers
  67. Graph Representation Learning with Individualization and Refinement
  68. MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering
  69. Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
  70. Type-Driven Multi-Turn Corrections for Grammatical Error Correction
  71. Co-visual pattern augmented generative transformer learning for automobile geo-localization
  72. Contrastive Learning with Positive-Negative Frame Mask for Music Representation
  73. Time Dependency, Data Flow, and Competitive Advantage
  74. ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps
  75. Conversational Recommendation: A Grand AI Challenge
  76. Are Vision Transformers Robust to Spurious Correlations?
  77. Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
  78. DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection
  79. Time and the Value of Data
  80. MotionAug: Augmentation with Physical Correction for Human Motion Prediction
  81. Causal Robot Communication Inspired by Observational Learning Insights
  82. Community-Driven Comprehensive Scientific Paper Summarization: Insight from cvpaper.challenge
  83. Knowledge Graph-Enabled Text-Based Automatic Personality Prediction
  84. PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
  85. TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding
  86. DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications
  87. Automating Code Review Activities by Large-Scale Pre-training
  88. Semantic-aligned Fusion Transformer for One-shot Object Detection
  89. deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques
  90. Deep Point Cloud Simplification for High-quality Surface Reconstruction
  91. Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation
  92. Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
  93. Ask to Understand: Question Generation for Multi-hop Question Answering
  94. Gaussian Multi-head Attention for Simultaneous Machine Translation
  95. STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
  96. Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
  97. Robust Table Detection and Structure Recognition from Heterogeneous Document Images
  98. Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT
  99. Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework
  100. DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
  101. Convert, compress, correct: Three steps toward communication-efficient DNN training
  102. Latent Image Animator: Learning to Animate Images via Latent Space Navigation
  103. DATA: Domain-Aware and Task-Aware Self-supervised Learning
  104. An Active Contour Model with Local Variance Force Term and Its Efficient Minimization Solver for Multi-phase Image Segmentation
  105. HybridNets: End-to-End Perception Network
  106. GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis
  107. Phased Flight Trajectory Prediction with Deep Learning
  108. Triangular Transfer: Freezing the Pivot for Triangular Machine Translation
  109. Graph Augmentation Learning
  110. Kan Extensions in Data Science and Machine Learning
  111. Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector
  112. Natural Language Communication with a Teachable Agent
  113. AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation