mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 16 Dec 2021

234 papers

  1. Multi-task UNet architecture for end-to-end autonomous drivingEnd-to-end autonomous driving → End-to-end system architecture
  2. Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  3. Knowledge Distillation Leveraging Alternative Soft Targets from Non-Parallel Qualified Speech DataKnowledge distillation → Speech and audio distillation
  4. AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language ModelsSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
  5. Evidentiality-guided Generation for Knowledge-Intensive NLP TasksRetrieval-augmented generation → RAG robustness and adaptive retrieval
  6. Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identificationMixture-of-experts → Vision mixture-of-experts
  7. Feature Distillation Interaction Weighting Network for Lightweight Image Super-ResolutionKnowledge distillation → General knowledge distillation methods
  8. Maximum Entropy of Random Permutation Set
  9. Using Particle Swarm Optimization as Pathfinding Strategy in a Space with Obstacles
  10. Differentially Describing Groups of Graphs
  11. Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark
  12. Two Stream Network for Stroke Detection in Table Tennis
  13. Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization
  14. Activity-based and agent-based Transport model of Melbourne (AToM): an open multi-modal transport simulation model for Greater Melbourne
  15. ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification
  16. Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees
  17. Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021
  18. Predicting Defects in Laser Powder Bed Fusion using in-situ Thermal Imaging Data and Machine Learning
  19. There is an elephant in the room: Towards a critique on the use of fairness in biometrics
  20. Intelligent Online Selling Point Extraction for E-Commerce Recommendation
  21. Context-Based Music Recommendation Algorithm Evaluation
  22. Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation
  23. Exact Shapley Values for Local and Model-True Explanations of Decision Tree Ensembles
  24. CGAN-EB: A Non-parametric Empirical Bayes Method for Crash Hotspot Identification Using Conditional Generative Adversarial Networks: A Real-world Crash Data Study
  25. Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic
  26. Deep Surrogate for Direct Time Fluid Dynamics
  27. Improving Ethical Outcomes with Machine-in-the-Loop: Broadening Human Understanding of Data Annotations
  28. Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
  29. Explanation as Question Answering based on Design Knowledge
  30. How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation
  31. A Novel Image Denoising Algorithm Using Concepts of Quantum Many-Body Theory
  32. Logically at Factify 2022: Multimodal Fact Verification
  33. The Wanderings of Odysseus in 3D Scenes
  34. Automated Deep Learning: Neural Architecture Search Is Not the End
  35. PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers
  36. Two-view Graph Neural Networks for Knowledge Graph Completion
  37. Sim2Real Docs: Domain Randomization for Documents in Natural Scenes using Ray-traced Rendering
  38. All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines
  39. High-Dimensional Inference in Bayesian Networks
  40. A Deep-Learning Framework for Improving COVID-19 CT Image Quality and Diagnostic Accuracy
  41. Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction
  42. Sparse Coding with Multi-Layer Decoders using Variance Regularization
  43. AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds
  44. Semantic-Based Few-Shot Learning by Interactive Psychometric Testing
  45. Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes
  46. Benchmarking Uncertainty Quantification on Biosignal Classification Tasks under Dataset Shift
  47. Mitigating the Bias of Centered Objects in Common Datasets
  48. Analysis of Generalized Bregman Surrogate Algorithms for Nonsmooth Nonconvex Statistical Learning
  49. Monitoring crop phenology with street-level imagery using computer vision
  50. Predicting Shallow Water Dynamics using Echo-State Networks with Transfer Learning
  51. Approximation of functions with one-bit neural networks
  52. Coherence Learning using Keypoint-based Pooling Network for Accurately Assessing Radiographic Knee Osteoarthritis
  53. Effective prevention of semantic drift as angular distance in memory-less continual deep neural networks
  54. Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations
  55. An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification
  56. Causal Modeling With Infinitely Many Variables
  57. On Optimizing Interventions in Shared Autonomy
  58. ALEBk: Feasibility Study of Attention Level Estimation via Blink Detection applied to e-Learning
  59. High Fidelity Visualization of What Your Self-Supervised Representation Knows About
  60. Constraint-based graph network simulator
  61. Implementation of a Binary Neural Network on a Passive Array of Magnetic Tunnel Junctions
  62. An Empirical Investigation of the Role of Pre-training in Lifelong Learning
  63. TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations
  64. ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network
  65. Masked Feature Prediction for Self-Supervised Visual Pre-Training
  66. HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
  67. Ensembling Off-the-shelf Models for GAN Training
  68. Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
  69. ICON: Implicit Clothed humans Obtained from Normals
  70. IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling
  71. Human Hands as Probes for Interactive Object Understanding
  72. Unsupervised Dense Information Retrieval with Contrastive Learning
  73. Machine Learning Kreuzer--Skarke Calabi--Yau Threefolds
  74. RegionCLIP: Region-based Language-Image Pretraining
  75. Non-Gaussian Component Analysis via Lattice Basis Reduction
  76. Learning and Analyzing Generation Order for Undirected Sequence Models
  77. A new locally linear embedding scheme in light of Hessian eigenmap
  78. CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
  79. Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants
  80. Solving Inverse Problems with NerfGANs
  81. Towards Robust Real-time Audio-Visual Speech Enhancement
  82. Hierarchical Clustering: O(1)-Approximation for Well-Clustered Graphs
  83. Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability
  84. Simultaneous Multivariate Forecast of Space Weather Indices using Deep Neural Network Ensembles
  85. Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach
  86. The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
  87. Neural Style Transfer and Unpaired Image-to-Image Translation to deal with the Domain Shift Problem on Spheroid Segmentation
  88. A Static Analyzer for Detecting Tensor Shape Errors in Deep Neural Network Training Code
  89. The Dual PC Algorithm and the Role of Gaussianity for Structure Learning of Bayesian Networks
  90. Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
  91. Classification of diffraction patterns using a convolutional neural network in single particle imaging experiments performed at X-ray free-electron lasers
  92. Multivariate Realized Volatility Forecasting with Graph Neural Network
  93. Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation
  94. Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation
  95. Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer
  96. Interference Suppression Using Deep Learning: Current Approaches and Open Challenges
  97. A Heterogeneous Graph Learning Model for Cyber-Attack Detection
  98. Quality monitoring of federated Covid-19 lesion segmentation
  99. Automated segmentation of 3-D body composition on computed tomography
  100. Objective hearing threshold identification from auditory brainstem response measurements using supervised and self-supervised approaches
All 234
  1. A molecular generative model with genetic algorithm and tree search for cancer samples
  2. Stable Long-Term Recurrent Video Super-Resolution
  3. Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
  4. MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
  5. Intelli-Paint: Towards Developing Human-like Painting Agents
  6. Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
  7. Khmer Word Search: Challenges, Solutions, and Semantic-Aware Search
  8. GOSH: Task Scheduling Using Deep Surrogate Models in Fog Computing Environments
  9. Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
  10. Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
  11. Degendering Resumes for Fair Algorithmic Resume Screening
  12. CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learning
  13. Inherently Explainable Reinforcement Learning in Natural Language
  14. On the Uncertain Single-View Depths in Colonoscopies
  15. Graph Structure Learning with Variational Information Bottleneck
  16. Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection
  17. Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds
  18. GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation
  19. Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks
  20. Multi-Camera LiDAR Inertial Extension to the Newer College Dataset
  21. Classification Under Ambiguity: When Is Average-K Better Than Top-K?
  22. Multiple Instance Learning for Brain Tumor Detection from Magnetic Resonance Spectroscopy Data
  23. Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model
  24. A CNN based method for Sub-pixel Urban Land Cover Classification using Landsat-5 TM and Resourcesat-1 LISS-IV Imagery
  25. Improving Unsupervised Stain-To-Stain Translation using Self-Supervision and Meta-Learning
  26. Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN
  27. Self-supervised Enhancement of Latent Discovery in GANs
  28. Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network
  29. Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning
  30. Search for temporal cell segmentation robustness in phase-contrast microscopy videos
  31. Deep Hash Distillation for Image Retrieval
  32. An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks
  33. Ditch the Gold Standard: Re-evaluating Conversational Question Answering
  34. Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
  35. Simple Questions Generate Named Entity Recognition Datasets
  36. Correlation inference attacks against machine learning models
  37. CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs
  38. UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
  39. Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation
  40. Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
  41. Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages
  42. Efficient Hierarchical Domain Adaptation for Pretrained Language Models
  43. Improved YOLOv5 network for real-time multi-scale traffic sign detection
  44. Self-Supervised Learning for speech recognition with Intermediate layer supervision
  45. Long Context Question Answering via Supervised Contrastive Learning
  46. Unsupervised Matching of Data and Text
  47. DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation
  48. BoGraph: Structured Bayesian Optimization From Logs for Expensive Systems with Many Parameters
  49. Sharpness-Aware Minimization with Dynamic Reweighting
  50. Proposition-Level Clustering for Multi-Document Summarization
  51. Adaptation and Attention for Neural Video Coding
  52. CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
  53. Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching
  54. DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems
  55. Constrained multi-objective optimization of process design parameters in settings with scarce data: an application to adhesive bonding
  56. KnAC: an approach for enhancing cluster analysis with background knowledge and explanations
  57. CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain
  58. Unsupervised Reinforcement Learning in Multiple Environments
  59. Radio-Assisted Human Detection
  60. Feature Erasing and Diffusion Network for Occluded Person Re-Identification
  61. Forensic Analysis of Synthetically Generated Western Blot Images
  62. Learning to Minimize Cost-to-Serve for Multi-Node Multi-Product Order Fulfilment in Electronic Commerce
  63. Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQL
  64. Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast
  65. NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
  66. Distilled Dual-Encoder Model for Vision-Language Understanding
  67. Prompt Tuning GPT-2 language model for parameter-efficient domain adaptation of ASR systems
  68. GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation
  69. CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
  70. DOCmT5: Document-Level Pretraining of Multilingual Language Models
  71. Forecasting sales with Bayesian networks: a case study of a supermarket product in the presence of promotions
  72. Learning to Share in Multi-Agent Reinforcement Learning
  73. Few-Shot Semantic Parsing with Language Models Trained On Code
  74. Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
  75. Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
  76. Isometric MT: Neural Machine Translation for Automatic Dubbing
  77. Machine Learning-Accelerated Computational Solid Mechanics: Application to Linear Elasticity
  78. Reframing Human-AI Collaboration for Generating Free-Text Explanations
  79. Intelligent Bearing Fault Diagnosis Method Combining Mixed Input and Hybrid CNN-MLP model
  80. Amortized Noisy Channel Neural Machine Translation
  81. MAVE: A Product Dataset for Multi-source Attribute Value Extraction
  82. Taming Repetition in Dialogue Generation
  83. DREAM: Improving Situational QA by First Elaborating the Situation
  84. Learning to Prompt for Continual Learning
  85. Reconsidering the Past: Optimizing Hidden States in Language Models
  86. Extreme Zero-Shot Learning for Extreme Text Classification
  87. QAHOI: Query-Based Anchors for Human-Object Interaction Detection
  88. Learning Interpretable Models Through Multi-Objective Neural Architecture Search
  89. A comparative study of paired versus unpaired deep learning methods for physically enhancing digital rock image resolution
  90. TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning
  91. Analyzing the Limits of Self-Supervision in Handling Bias in Language
  92. Road-aware Monocular Structure from Motion and Homography Estimation
  93. FRUIT: Faithfully Reflecting Updated Information in Text
  94. Learning To Retrieve Prompts for In-Context Learning
  95. Explainable Natural Language Processing with Matrix Product States
  96. Analysis and Evaluation of Kinect-based Action Recognition Algorithms
  97. Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge
  98. A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling
  99. Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context
  100. Knowledge-Augmented Language Models for Cause-Effect Relation Classification
  101. KAT: A Knowledge Augmented Transformer for Vision-and-Language
  102. DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
  103. QuALITY: Question Answering with Long Input Texts, Yes!
  104. Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection
  105. Use Image Clustering to Facilitate Technology Assisted Review
  106. FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
  107. Guiding Neural Story Generation with Reader Models
  108. Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
  109. Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning
  110. Idiomatic Expression Paraphrasing without Strong Supervision
  111. Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules
  112. Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
  113. SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning
  114. Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge
  115. Mathematical Runtime Analysis for the Non-Dominated Sorting Genetic Algorithm II (NSGA-II)
  116. CLICKER: A Computational LInguistics Classification Scheme for Educational Resources
  117. Predictive Price-Performance Optimization for Serverless Query Processing
  118. Can Multilinguality benefit Non-autoregressive Machine Translation?
  119. HampDTI: a heterogeneous graph automatic meta-path learning method for drug-target interaction prediction
  120. Block-Skim: Efficient Question Answering for Transformer
  121. CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
  122. A Deep Learning Approach for Ontology Enrichment from Unstructured Text
  123. UMAD: Universal Model Adaptation under Domain and Category Shift
  124. Neural Content Extraction for Poster Generation of Scientific Papers
  125. A prediction-based approach for online dynamic patient scheduling: a case study in radiotherapy treatment
  126. Isochrony-Aware Neural Machine Translation for Automatic Dubbing
  127. Learning Rich Representation of Keyphrases from Text
  128. NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge
  129. QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization
  130. BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing
  131. Integrated Guidance and Control for Lunar Landing using a Stabilized Seeker
  132. Implicit Neural Representations for Deconvolving SAS Images
  133. Visualizing the Loss Landscape of Winning Lottery Tickets
  134. Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture