mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 9 Jun 2021

231 papers

  1. Zero Time Waste: Recycling Predictions in Early Exit Neural NetworksEfficient LLM inference and serving → Early exit and edge inference
  2. End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  3. Knowledge distillation: A good teacher is patient and consistentKnowledge distillation → General knowledge distillation methods
  4. Distilling Image Classifiers in Object DetectorsKnowledge distillation → Detection and dense prediction distillation
  5. PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. Offline Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  7. Adaptive Inference through Early-Exit Networks: Design, Challenges and DirectionsEfficient LLM inference and serving → Early exit and edge inference
  8. Instantaneous Grammatical Error Correction with Shallow Aggressive DecodingEfficient LLM inference and serving → Speculative decoding
  9. Reliable Adversarial Distillation with Unreliable TeachersKnowledge distillation → Federated, robust and private distillation
  10. Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  11. Wearable Health Monitoring System for Older Adults in a Smart Home Environment
  12. Meeting the SDGs : Enabling the Goals by Cooperation with Crowd using a Conversational AI Platform
  13. Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures
  14. Key Information Extraction From Documents: Evaluation And Generator
  15. Timestamping Documents and Beliefs
  16. Partial Wasserstein and Maximum Mean Discrepancy distances for bridging the gap between outlier detection and drift detection
  17. Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
  18. Optimized ensemble deep learning framework for scalable forecasting of dynamics containing extreme events
  19. A Direct Slip Ratio Estimation Method based on an Intelligent Tire and Machine Learning
  20. Spot the Difference: Detection of Topological Changes via Geometric Alignment
  21. Meta-Interpretive Learning as Metarule Specialisation
  22. Probabilistic Forecasting of Imbalance Prices in the Belgian Context
  23. Domain Specific Transporter Framework to Detect Fractures in Ultrasound
  24. CoviLearn: A Machine Learning Integrated Smart X-Ray Device in Healthcare Cyber-Physical System for Automatic Initial Screening of COVID-19
  25. Matrix Completion with Model-free Weighting
  26. Large-scale optimal transport map estimation using projection pursuit
  27. HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks
  28. Rare event estimation using stochastic spectral embedding
  29. FedDICE: A ransomware spread detection in a distributed integrated clinical environment using federated learning and SDN based mitigation
  30. Separating Boundary Points via Structural Regularization for Very Compact Clusters
  31. Deep Direct Volume Rendering: Learning Visual Feature Mappings From Exemplary Images
  32. Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses
  33. Fair Disaster Containment via Graph-Cut Problems
  34. A New Notion of Individually Fair Clustering: α-Equitable k-Center
  35. Probing transfer learning with a model of synthetic correlated datasets
  36. A Reputation Game Simulation: Emergent Social Phenomena from Information Theory
  37. DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
  38. Audiovisual transfer learning for audio tagging and sound event detection
  39. Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective
  40. Fine-Grained System Identification of Nonlinear Neural Circuits
  41. From inexact optimization to learning via gradient concentration
  42. Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
  43. Fairness-Aware Node Representation Learning
  44. Optimizing Reusable Knowledge for Continual Learning via Metalearning
  45. Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
  46. Artificial Intelligence in Drug Discovery: Applications and Techniques
  47. Long-time integration of parametric evolution equations with physics-informed DeepONets
  48. Feature and Parameter Selection in Stochastic Linear Bandits
  49. Plan2Scene: Converting Floorplans to 3D Scenes
  50. StreamBrain: An HPC Framework for Brain-like Neural Networks on CPUs, GPUs and FPGAs
  51. Pulling back information geometry
  52. DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions
  53. Public Transit for Special Events: Ridership Prediction and Train Optimization
  54. Generative Feature-driven Image Replay for Continual Learning
  55. SCARI: Separate and Conquer Algorithm for Action Rules and Recommendations Induction
  56. Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud
  57. Online Learning for Stochastic Shortest Path Model via Posterior Sampling
  58. Reinforcement Learning for Industrial Control Network Cyber Security Orchestration
  59. ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs
  60. Tensor feature hallucination for few-shot learning
  61. Stein Latent Optimization for Generative Adversarial Networks
  62. Attentional Meta-learners for Few-shot Polythetic Classification
  63. Visual Sensor Pose Optimisation Using Visibility Models for Smart Cities
  64. DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact
  65. Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
  66. Explaining Time Series Predictions with Dynamic Masks
  67. Grover's Algorithm for Question Answering
  68. CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
  69. Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows
  70. Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
  71. Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
  72. NeRF in detail: Learning to sample for view synthesis
  73. TempoRL: Learning When to Act
  74. We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature
  75. Generative Models as a Data Source for Multiview Representation Learning
  76. Bayesian Attention Belief Networks
  77. What Would a Teacher Do? Predicting Future Talk Moves
  78. Local Algorithms for Finding Densely Connected Clusters
  79. Multi-Facet Clustering Variational Autoencoders
  80. XBNet : An Extremely Boosted Neural Network
  81. I Don't Need u: Identifiable Non-Linear ICA Without Side Information
  82. Do Transformers Really Perform Bad for Graph Representation?
  83. Realizing GANs via a Tunable Loss Function
  84. Speech Recovery for Real-World Self-powered Intermittent Devices
  85. Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling
  86. Single-Server Private Linear Transformation: The Individual Privacy Case
  87. Single-Server Private Linear Transformation: The Joint Privacy Case
  88. A machine learning pipeline for aiding school identification from child trafficking images
  89. Implicit field learning for unsupervised anomaly detection in medical images
  90. Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
  91. Avoiding Traps in Nonconvex Problems
  92. EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback
  93. Independent mechanism analysis, a new concept?
  94. DIGRAC: Digraph Clustering Based on Flow Imbalance
  95. Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields
  96. On the Use of Minimum Penalties in Statistical Learning
  97. Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision
  98. A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
  99. Case Studies on using Natural Language Processing Techniques in Customer Relationship Management Software
  100. Rethinking Transfer Learning for Medical Image Classification
All 231
  1. Scaling Up Graph Neural Networks Via Graph Coarsening
  2. Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting
  3. Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids
  4. Neighborhood Contrastive Learning Applied to Online Patient Monitoring
  5. AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT
  6. Pretrained Encoders are All You Need
  7. Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
  8. Quantum Annealing for Automated Feature Selection in Stress Detection
  9. A multi-stage GAN for multi-organ chest X-ray image generation and segmentation
  10. Deep Clustering based Fair Outlier Detection
  11. Efficient Active Search for Combinatorial Optimization Problems
  12. PCNet: A Structure Similarity Enhancement Method for Multispectral and Multimodal Image Registration
  13. Grounding inductive biases in natural images:invariance stems from variations in data
  14. Mixture weights optimisation for Alpha-Divergence Variational Inference
  15. More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activity
  16. A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition
  17. Self-Paced Context Evaluation for Contextual Reinforcement Learning
  18. Gaussian Mixture Estimation from Weighted Samples
  19. An Efficient Point of Gaze Estimator for Low-Resolution Imaging Systems Using Extracted Ocular Features Based Neural Architecture
  20. Learning normal form autoencoders for data-driven discovery of universal,parameter-dependent governing equations
  21. ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
  22. Semi-supervised lane detection with Deep Hough Transform
  23. Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
  24. Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
  25. Agile wide-field imaging with selective high resolution
  26. Learning Pseudo-Backdoors for Mixed Integer Programs
  27. Operationalizing Complex Causes: A Pragmatic View of Mediation
  28. Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
  29. Quickest change detection with unknown parameters: Constant complexity and near optimality
  30. Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
  31. Multiple Kernel Representation Learning on Networks
  32. Salient Object Ranking with Position-Preserved Attention
  33. Hermite Polynomial Features for Private Data Generation
  34. Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
  35. Towards Defending against Adversarial Examples via Attack-Invariant Features
  36. Estimation of Optimal Dynamic Treatment Assignment Rules under Policy Constraints
  37. Bayesian Bellman Operators
  38. Loss function based second-order Jensen inequality and its application to particle variational inference
  39. Network insensitivity to parameter noise via adversarial regularization
  40. Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
  41. Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing
  42. No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
  43. Salient Positions based Attention Network for Image Classification
  44. Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study
  45. Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
  46. It Takes Two to Tango: Mixup for Deep Metric Learning
  47. CLCC: Contrastive Learning for Color Constancy
  48. Multistep Electric Vehicle Charging Station Occupancy Prediction using Hybrid LSTM Neural Networks
  49. Energy-Based Models for Code Generation under Compilability Constraints
  50. Information Avoidance and Overvaluation in Sequential Decision Making under Epistemic Constraints
  51. Cooperative Online Learning with Feedback Graphs
  52. The dilemma of quantum neural networks
  53. Understanding Softmax Confidence and Uncertainty
  54. GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
  55. Towards Explainable Abnormal Infant Movements Identification: A Body-part Based Prediction and Visualisation Framework
  56. Psycholinguistic Tripartite Graph Network for Personality Detection
  57. Spatio-Temporal Dual-Stream Neural Network for Sequential Whole-Body PET Segmentation
  58. Auto-tagging of Short Conversational Sentences using Natural Language Processing Methods
  59. Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games
  60. Real Time Egocentric Object Segmentation: THU-READ Labeling and Benchmarking Results
  61. Expectation Programming: Adapting Probabilistic Programming Systems to Estimate Expectations Efficiently
  62. Non-Parametric Stochastic Sequential Assignment With Random Arrival Times
  63. Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
  64. Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding
  65. Attacking Adversarial Attacks as A Defense
  66. Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units
  67. Fast and More Powerful Selective Inference for Sparse High-order Interaction Model
  68. A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
  69. Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
  70. Self-supervision of Feature Transformation for Further Improving Supervised Learning
  71. Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning
  72. Towards Deep Industrial Transfer Learning for Anomaly Detection on Time Series Data
  73. Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection
  74. Exploiting Learned Symmetries in Group Equivariant Convolutions
  75. On Margin-Based Cluster Recovery with Oracle Queries
  76. Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning
  77. Automatic Sexism Detection with Multilingual Transformer Models
  78. DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching
  79. Fragmented and Valuable: Following Sentiment Changes in Food Tweets
  80. Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks
  81. Continuous-discrete multiple target tracking with out-of-sequence measurements
  82. Unsupervised Automatic Speech Recognition: A Review
  83. Interaction-Grounded Learning
  84. Fully differentiable model discovery
  85. Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms
  86. Self-Improved Retrosynthetic Planning
  87. Recovering AES Keys with a Deep Cold Boot Attack
  88. Planning for Novelty: Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning
  89. Bayesian Boosting for Linear Mixed Models
  90. DravidianMultiModality: A Dataset for Multi-modal Sentiment Analysis in Tamil and Malayalam
  91. Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
  92. UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction
  93. Nonlinear Hawkes Processes in Time-Varying System
  94. Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
  95. Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System
  96. RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
  97. Probing Multilingual Language Models for Discourse
  98. MICE: A Crosslinguistic Emotion Corpus in Malay, Indonesian, Chinese and English
  99. Catchphrase: Automatic Detection of Cultural References
  100. Taxonomy of Machine Learning Safety: A Survey and Primer
  101. Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network
  102. Contextual Recommendations and Low-Regret Cutting-Plane Algorithms
  103. ChaCha for Online AutoML
  104. Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing
  105. Phase Retrieval using Single-Instance Deep Generative Prior
  106. Streaming Belief Propagation for Community Detection
  107. EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models
  108. CoAtNet: Marrying Convolution and Attention for All Data Sizes
  109. Probabilistic task modelling for meta-learning
  110. Diffusion Source Identification on Networks with Statistical Confidence
  111. Pretraining Representations for Data-Efficient Reinforcement Learning
  112. Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off
  113. Towards the Memorization Effect of Neural Networks in Adversarial Training
  114. Sentence Embeddings using Supervised Contrastive Learning
  115. Accelerating Neural Architecture Search via Proxy Data
  116. Encoding physics to learn reaction-diffusion processes
  117. Point Cloud Upsampling via Disentangled Refinement
  118. Reconstruction of People in Loose Clothing
  119. Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos
  120. A 2020 taxonomy of algorithms inspired on living beings behavior
  121. Geospatial Reasoning with Shapefiles for Supporting Policy Decisions
  122. Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space
  123. Submodular + Concave
  124. Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
  125. Predicting Deep Neural Network Generalization with Perturbation Response Curves
  126. Fixed-Budget Best-Arm Identification in Structured Bandits
  127. Communication-efficient SGD: From Local SGD to One-Shot Averaging
  128. On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation
  129. Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Prediction
  130. Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincar'e Recurrence
  131. A Review of Human Evaluation for Style Transfer