mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 2 Jun 2021

217 papers

  1. Not All Knowledge Is Created Equal: Mutual Distillation of Confident KnowledgeKnowledge distillation → General knowledge distillation methods
  2. Decision Transformer: Reinforcement Learning via Sequence ModelingOffline RL and imitation learning from data → Decision transformers and sequence modeling
  3. One Teacher is Enough? Pre-trained Language Model Distillation from Multiple TeachersKnowledge distillation → Knowledge distillation for LLMs
  4. Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive TranslationKnowledge distillation → Knowledge distillation for LLMs
  5. Steerable 3D Spherical Neurons
  6. Deep Learning for Network Traffic Classification
  7. Teaching Machine Learning in K-12 Computing Education: Potential and Pitfalls
  8. GemNet: Universal Directional Graph Neural Networks for Molecules
  9. Artificial Perceptual Learning: Image Categorization with Weak Supervision
  10. Long Term Object Detection and Tracking in Collaborative Learning Environments
  11. A Cognitive Science perspective for learning how to design meaningful user experiences and human-centered technology
  12. Posthoc Verification and the Fallibility of the Ground Truth
  13. MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network
  14. MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education
  15. Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
  16. Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
  17. General Rough Modeling of Cluster Analysis
  18. Random Forest classifier for EEG-based seizure prediction
  19. Federated Neural Collaborative Filtering
  20. The Struggle with Academic Plagiarism: Approaches based on Semantic Similarity
  21. Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial network
  22. Heterogeneous Noisy Short Signal Camouflage in Multi-Domain Environment Decision-Making
  23. DNA-GCN: Graph convolutional networks for predicting DNA-protein binding
  24. Deep Learning Based Analysis of Prostate Cancer from MP-MRI
  25. Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
  26. Barbershop: GAN-based Image Compositing using Segmentation Masks
  27. DeepCompress: Efficient Point Cloud Geometry Compression
  28. Towards an Explanation Space to Align Humans and Explainable-AI Teamwork
  29. Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
  30. Personalizing Pre-trained Models
  31. IoT Solutions with Multi-Sensor Fusion and Signal-Image Encoding for Secure Data Transfer and Decision Making
  32. Knowing More About Questions Can Help: Improving Calibration in Question Answering
  33. MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain
  34. Minimax Optimization with Smooth Algorithmic Adversaries
  35. LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
  36. Weakly Supervised Learning Creates a Fusion of Modeling Cultures
  37. Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection
  38. Quantifying language changes surrounding mental health on Twitter
  39. Evaluating the Efficacy of Summarization Evaluation across Languages
  40. Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning
  41. Domain Adaptation for Facial Expression Classifier via Domain Discrimination and Gradient Reversal
  42. Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
  43. Lightweight Adapter Tuning for Multilingual Speech Translation
  44. BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks
  45. Attention-based Contextual Language Model Adaptation for Speech Recognition
  46. Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes
  47. SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis
  48. Optimization of Heterogeneous Systems with AI Planning Heuristics and Machine Learning: A Performance and Energy Aware Approach
  49. NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results
  50. Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour
  51. SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
  52. Smooth Bilevel Programming for Sparse Regularization
  53. Unsharp Mask Guided Filtering
  54. GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
  55. Learning to Select: A Fully Attentive Approach for Novel Object Captioning
  56. One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
  57. Parallelizing Thompson Sampling
  58. Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
  59. A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
  60. Rectangular Flows for Manifold Learning
  61. Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
  62. Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning
  63. Container: Context Aggregation Network
  64. Dual Script E2E framework for Multilingual and Code-Switching ASR
  65. Automatic Assessment of the Design Quality of Python Programs with Personalized Feedback
  66. Single-component gradient rules for variational quantum algorithms
  67. From Undecidability of Non-Triviality and Finiteness to Undecidability of Learnability
  68. q-RBFNN:A Quantum Calculus-based RBF Neural Network
  69. The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop
  70. multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning
  71. NeRP: Neural Rearrangement Planning for Unknown Objects
  72. On Efficiently Explaining Graph-Based Classifiers
  73. SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
  74. Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
  75. On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers
  76. Addressing the Long-term Impact of ML Decisions via Policy Regret
  77. Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
  78. Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence
  79. Spectral embedding for dynamic networks with stability guarantees
  80. Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection
  81. Deep learning-based multi-output quantile forecasting of PV generation
  82. More Identifiable yet Equally Performant Transformers for Text Classification
  83. Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
  84. Matrix factorisation and the interpretation of geodesic distance
  85. Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles
  86. Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
  87. Principled Evaluation with Human Labels: One Rater at a Time and Rater Equivalence
  88. Multilingual Medical Question Answering and Information Retrieval for Rural Health Intelligence Access
  89. A Privacy-Preserving and Trustable Multi-agent Learning Framework
  90. Lower Perplexity is Not Always Human-Like
  91. Metaphor Generation with Conceptual Mappings
  92. Improving low-resource ASR performance with untranscribed out-of-domain data
  93. Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
  94. A Unified Generative Framework for Various NER Subtasks
  95. Differential Privacy for Text Analytics via Natural Text Sanitization
  96. DFGC 2021: A DeepFake Game Competition
  97. Evidential Turing Processes
  98. Cross-document Coreference Resolution over Predicted Mentions
  99. Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning
  100. Framing RNN as a kernel method: A neural ODE approach
All 217
  1. IrEne: Interpretable Energy Prediction for Transformers
  2. Figurative Language in Recognizing Textual Entailment
  3. Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verification
  4. Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference
  5. A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space
  6. ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
  7. Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck
  8. Hybrid Ensemble optimized algorithm based on Genetic Programming for imbalanced data classification
  9. Digital homotopy relations and digital homology theories
  10. Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions
  11. End-to-End NLP Knowledge Graph Construction
  12. Online and Real-Time Tracking in a Surveillance Scenario
  13. Towards Deeper Deep Reinforcement Learning with Spectral Normalization
  14. Towards Emotional Support Dialog Systems
  15. Accurate and Robust Deep Learning Framework for Solving Wave-Based Inverse Problems in the Super-Resolution Regime
  16. Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
  17. MNL-Bandit with Knapsacks: a near-optimal algorithm
  18. Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity
  19. Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
  20. Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
  21. Towards Robust Classification Model by Counterfactual and Invariant Data Generation
  22. Opening the Black Box of Deep Neural Networks in Physical Layer Communication
  23. Connections and Equivalences between the Nystr"om Method and Sparse Variational Gaussian Processes
  24. Design and Comparison of Reward Functions in Reinforcement Learning for Energy Management of Sensor Nodes
  25. DynaEval: Unifying Turn and Dialogue Level Evaluation
  26. Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
  27. Improvement over Pinball Loss Support Vector Machine
  28. Use of Formal Ethical Reviews in NLP Literature: Historical Trends and Current Practices
  29. Learning a Single Neuron with Bias Using Gradient Descent
  30. Prediction of the Position of External Markers Using a Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer Radiotherapy
  31. Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
  32. T-BERT -- Model for Sentiment Analysis of Micro-blogs Integrating Topic Model and BERT
  33. Learning to Rehearse in Long Sequence Memorization
  34. LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
  35. Statistical optimality conditions for compressive ensembles
  36. belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification
  37. TSI: Temporal Saliency Integration for Video Action Recognition
  38. Is Sparse Attention more Interpretable?
  39. Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning
  40. Online Coreset Selection for Rehearsal-based Continual Learning
  41. Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations
  42. SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics
  43. Database Reasoning Over Text
  44. Evidence-based Factual Error Correction
  45. Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection
  46. Testing Group Fairness via Optimal Transport Projections
  47. Towards Robustness of Text-to-SQL Models against Synonym Substitution
  48. Generating Informative Conclusions for Argumentative Texts
  49. Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
  50. John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs
  51. A Novel Edge Detection Operator for Identifying Buildings in Augmented Reality Applications
  52. Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
  53. Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making
  54. Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
  55. Examining the Inductive Bias of Neural Language Models with Artificial Languages
  56. Causal Discovery in Knowledge Graphs by Exploiting Asymmetric Properties of Non-Gaussian Distributions
  57. Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling
  58. Towards Unified Surgical Skill Assessment
  59. Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text
  60. Why Machine Reading Comprehension Models Learn Shortcuts?
  61. Decision-making Oriented Clustering: Application to Pricing and Power Consumption Scheduling
  62. Deep Reinforcement Learning-based UAV Navigation and Control: A Soft Actor-Critic with Hindsight Experience Replay Approach
  63. FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare
  64. SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
  65. Warming up recurrent neural networks to maximise reachable multistability greatly improves learning
  66. Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation
  67. Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey
  68. Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels
  69. On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction
  70. NVC-Net: End-to-End Adversarial Voice Conversion
  71. Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
  72. OctoPath: An OcTree Based Self-Supervised Learning Approach to Local Trajectory Planning for Mobile Robots
  73. Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation
  74. Few-Shot Partial-Label Learning
  75. End-to-End Hierarchical Relation Extraction for Generic Form Understanding
  76. A Span Extraction Approach for Information Extraction on Visually-Rich Documents
  77. Exploring Discourse Structures for Argument Impact Classification
  78. COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences
  79. Multiresolution Equivariant Graph Variational Autoencoder
  80. A Generalizable Approach to Learning Optimizers
  81. RevCore: Review-augmented Conversational Recommendation
  82. Answer Generation for Retrieval-based Question Answering Systems
  83. When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis
  84. End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net
  85. A Multi-Level Attention Model for Evidence-Based Fact Checking
  86. Unsupervised Out-of-Domain Detection via Pre-trained Transformers
  87. JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data
  88. Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
  89. Discrete Cosine Transform as Universal Sentence Encoder
  90. OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres
  91. An Extendible, Graph-Neural-Network-Based Approach for Accurate Force Field Development of Large Flexible Organic Molecules
  92. Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
  93. An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task
  94. DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
  95. Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
  96. Consumer Image Quality Prediction using Recurrent Neural Networks for Spatial Pooling
  97. Translational Symmetry-Aware Facade Parsing for 3D Building Reconstruction
  98. Concurrent Learning Based Tracking Control of Nonlinear Systems using Gaussian Process
  99. The Generalized Mean Densest Subgraph Problem
  100. TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
  101. Operator Splitting for Learning to Predict Equilibria in Convex Games
  102. Low-cost Stereovision system (disparity map) for few dollars
  103. A Differentiable Point Process with Its Application to Spiking Neural Networks
  104. Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
  105. Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text
  106. High-Quality Diversification for Task-Oriented Dialogue Systems
  107. Exploiting Global Contextual Information for Document-level Named Entity Recognition
  108. Partial Wasserstein Covering
  109. Robustifying Algorithms of Learning Latent Trees with Vector Variables
  110. Deep Personalized Glucose Level Forecasting Using Attention-based Recurrent Neural Networks
  111. Efficient Passage Retrieval with Hashing for Open-domain Question Answering
  112. Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks
  113. Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
  114. Evaluating Word Embeddings with Categorical Modularity
  115. Conversational Question Answering: A Survey
  116. Coverage-based Scene Fuzzing for Virtual Autonomous Driving Testing
  117. On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study