mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 31 Oct 2022

213 papers

  1. Interactive Imitation Learning in Robotics: A SurveyOffline RL and imitation learning from data → Imitation learning methods
  2. Predicting Multi-Codebook Vector Quantization Indexes for Knowledge DistillationKnowledge distillation → Speech and audio distillation
  3. Fast and parallel decoding for transducerEfficient LLM inference and serving → Speculative decoding
  4. SEIL: Simulation-augmented Equivariant Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  5. Agent-Controller Representations: Principled Offline RL with Rich Exogenous InformationOffline RL and imitation learning from data → Offline RL algorithms
  6. Zero-Shot Text Classification with Self-TrainingSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
  7. Lila: A Unified Benchmark for Mathematical ReasoningLLM reasoning → Mathematical reasoning
  8. SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular ControlDiffusion models → Discrete and text diffusion
  9. Teacher-student curriculum learning for reinforcement learningKnowledge distillation → On-policy and self-distillation for LLMs
  10. Guided Conditional Diffusion for Controllable Traffic SimulationDiffusion models → Diffusion and flow policies for robotics
  11. Diffusion-based Generative Speech Source SeparationDiffusion models → Audio, speech and music
  12. Generative Negative Text Replay for Continual Vision-Language PretrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  13. Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal SamplesKnowledge distillation → Detection and dense prediction distillation
  14. Accelerating Distributed MoE Training and Inference with LinaMixture-of-experts → Efficient MoE training and inference systems
  15. Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation LearningOffline RL and imitation learning from data → Offline RL algorithms
  16. SDCL: Self-Distillation Contrastive Learning for Chinese Spell CheckingKnowledge distillation → Knowledge distillation for LLMs
  17. Diffusion models for missing value imputation in tabular dataDiffusion models → Flow matching, time series and science
  18. Intelligent Painter: Picture Composition With Resampling Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  19. Structured State Space Decoder for Speech Recognition and SynthesisState-space sequence models (S4, Mamba) → Speech and audio SSMs
  20. RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment TreesLLM reasoning → Knowledge- and tool-augmented reasoning
  21. Poison Attack and Defense on Deep Source Code Processing ModelsLLM safety and security → Backdoor and data poisoning attacks
  22. ModularFed: Leveraging Modularity in Federated Learning Frameworks
  23. Caching Contents with Varying Popularity using Restless Bandits
  24. Design Considerations For Hypothesis Rejection Modules In Spoken Language Understanding Systems
  25. Multilingual Speech Emotion Recognition With Multi-Gating Mechanism and Neural Architecture Search
  26. Revisiting Attention Weights as Explanations from an Information Theoretic Perspective
  27. Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence
  28. The role of prior information and computational power in Machine Learning
  29. Reinforcement Learning based Cyberattack Model for Adaptive Traffic Signal Controller in Connected Transportation Systems
  30. FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devices
  31. Class Interference of Deep Neural Networks
  32. A Profit-Maximizing Strategy for Advertising on the e-Commerce Platforms
  33. minoHealth.ai: A Clinical Evaluation Of Deep Learning Systems For the Diagnosis of Pleural Effusion and Cardiomegaly In Ghana, Vietnam and the United States of America
  34. A Federated Learning Scheme for Neuro-developmental Disorders: Multi-Aspect ASD Detection
  35. Farm-wide virtual load monitoring for offshore wind structures via Bayesian neural networks
  36. A Simple, Yet Effective Approach to Finding Biases in Code Generation
  37. Delay-penalized transducer for low-latency streaming ASR
  38. Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection
  39. Adaptive Compression for Communication-Efficient Distributed Training
  40. Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models
  41. FL Games: A Federated Learning Framework for Distribution Shifts
  42. The Numerical Stability of Hyperbolic Representation Learning
  43. Learning to Navigate Wikipedia by Taking Random Walks
  44. Xtreme Margin: A Tunable Loss Function for Binary Classification Problems
  45. Homodyned K-distribution: parameter estimation and uncertainty quantification using Bayesian neural networks
  46. Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
  47. Infusing known operators in convolutional neural networks for lateral strain imaging in ultrasound elastography
  48. Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats
  49. What is my math transformer doing? -- Three results on interpretability and generalization
  50. Improving Fairness in Image Classification via Sketching
  51. Large scale traffic forecasting with gradient boosting, Traffic4cast 2022 challenge
  52. Do LSTMs See Gender? Probing the Ability of LSTMs to Learn Abstract Syntactic Rules
  53. A Close Look into the Calibration of Pre-trained Language Models
  54. Improving Motion Forecasting for Autonomous Driving with the Cycle Consistency Loss
  55. A Machine Learning Tutorial for Operational Meteorology, Part II: Neural Networks and Deep Learning
  56. TaTa: A Multilingual Table-to-Text Dataset for African Languages
  57. Is Facial Recognition Biased at Near-Infrared Spectrum As Well?
  58. SIMPLE-RC: Group Network Inference with Non-Sharp Nulls and Weak Signals
  59. Textless Direct Speech-to-Speech Translation with Discrete Speech Representation
  60. SAGE: Saliency-Guided Mixup with Optimal Rearrangements
  61. Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
  62. Ruby: Unmasking Unsafe Rust in Stripped Binaries via Machine Learning
  63. A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?
  64. Where to start? Analyzing the potential value of intermediate models
  65. Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks
  66. Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI)
  67. Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms
  68. UmeTrack: Unified multi-view end-to-end hand tracking for VR
  69. Synthetic ID Card Image Generation for Improving Presentation Attack Detection
  70. Road Damages Detection and Classification with YOLOv7
  71. An analysis of degenerating speech due to progressive dysarthria on ASR performance
  72. Disentangled (Un)Controllable Features
  73. WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
  74. Spatial-Temporal Synchronous Graph Transformer network (STSGT) for COVID-19 forecasting
  75. Denoising neural networks for magnetic resonance spectroscopy
  76. Optimizing Closed-Loop Performance with Data from Similar Systems: A Bayesian Meta-Learning Approach
  77. Keywords for Bias
  78. The interaction of transmission intensity, mortality, and the economy: a retrospective analysis of the COVID-19 pandemic
  79. Generating Sequences by Learning to Self-Correct
  80. Very Low Resource Sentence Alignment: Luhya and Swahili
  81. A robust estimator of mutual information for deep learning interpretability
  82. Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
  83. Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
  84. Unclonability and Quantum Cryptanalysis: From Foundations to Applications
  85. Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning
  86. Query Refinement Prompts for Closed-Book Long-Form Question Answering
  87. Fully Adaptive Composition for Gaussian Differential Privacy
  88. Cost-aware Generalized α-investing for Multiple Hypothesis Testing
  89. Space-Fluid Adaptive Sampling by Self-Organisation
  90. Leveraging Pre-trained Models for Failure Analysis Triplets Generation
  91. Automated Code Extraction from Discussion Board Text Dataset
  92. Learning Modular Robot Locomotion from Demonstrations
  93. Quantum-Inspired Edge Detection Algorithms Implementation using New Dynamic Visual Data Representation and Short-Length Convolution Computation
  94. The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science
  95. TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
  96. Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs
  97. A-LAQ: Adaptive Lazily Aggregated Quantized Gradient
  98. Chronic pain patient narratives allow for the estimation of current pain intensity
  99. Blind Asynchronous Over-the-Air Federated Edge Learning
  100. Iterative Teaching by Data Hallucination
All 213
  1. Domain Curricula for Code-Switched MT at MixMT 2022
  2. Agglomeration of Polygonal Grids using Graph Neural Networks with applications to Multigrid solvers
  3. Adaptive Selection of the Optimal Strategy to Improve Precision and Power in Randomized Trials
  4. A Case Study of Chinese Sentiment Analysis on Social Media Reviews Based on LSTM
  5. AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
  6. Globally Gated Deep Linear Networks
  7. Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations
  8. A Faster Approach to Spiking Deep Convolutional Neural Networks
  9. Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities
  10. Learning New Tasks from a Few Examples with Soft-Label Prototypes
  11. Ensemble transport smoothing. Part II: Nonlinear updates
  12. Trade-off Between Efficiency and Consistency for Removal-based Explanations
  13. Tree Detection and Diameter Estimation Based on Deep Learning
  14. Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
  15. Emergent Linguistic Structures in Neural Networks are Fragile
  16. Exact and Approximate Conformal Inference for Multi-Output Regression
  17. Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
  18. Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation
  19. Probabilistic Decomposition Transformer for Time Series Forecasting
  20. Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency
  21. SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability
  22. Explainable Deep Learning to Profile Mitochondrial Disease Using High Dimensional Protein Expression Data
  23. A Faster Sampler for Discrete Determinantal Point Processes
  24. L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
  25. gCoRF: Generative Compositional Radiance Fields
  26. HARRIS: Hybrid Ranking and Regression Forests for Algorithm Selection
  27. Flexible categorization for auditing using formal concept analysis and Dempster-Shafer theory
  28. Real-time Mapping of Physical Scene Properties with an Autonomous Robot Experimenter
  29. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
  30. Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems
  31. Neural network-based CUSUM for online change-point detection
  32. Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5
  33. Towards Zero-Shot and Few-Shot Table Question Answering using GPT-3
  34. CausalBench: A Large-scale Benchmark for Network Inference from Single-cell Perturbation Data
  35. GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers
  36. Scoliosis Detection using Deep Neural Network
  37. Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
  38. QNet: A Quantum-native Sequence Encoder Architecture
  39. Multi-Camera Calibration Free BEV Representation for 3D Object Detection
  40. Tables to LaTeX: structure and content extraction from scientific tables
  41. Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task
  42. Latent Multimodal Functional Graphical Model Estimation
  43. When Language Model Meets Private Library
  44. 50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts
  45. CorrLoss: Integrating Co-Occurrence Domain Knowledge for Affect Recognition
  46. Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
  47. VertiBayes: Learning Bayesian network parameters from vertically partitioned data with missing values
  48. Improving Graph Neural Networks with Learnable Propagation Operators
  49. Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection
  50. Artificial intelligence in government: Concepts, standards, and a unified framework
  51. Symmetries, flat minima, and the conserved quantities of gradient flow
  52. Deep Gaussian Process-based Multi-fidelity Bayesian Optimization for Simulated Chemical Reactors
  53. The Effect of Multiple Replies for Natural Language Generation Chatbots
  54. IITD at the WANLP 2022 Shared Task: Multilingual Multi-Granularity Network for Propaganda Detection
  55. Self-Supervised Hierarchical Metrical Structure Modeling
  56. Automated Dominative Subspace Mining for Efficient Neural Architecture Search
  57. Variational Inference Aided Estimation of Time Varying Channels
  58. Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives
  59. Listen to what they say: Better understand and detect online misinformation with user feedback
  60. Improving Cause-of-Death Classification from Verbal Autopsy Reports
  61. PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks
  62. 1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector
  63. Tech Report: One-stage Lightweight Object Detectors
  64. Exploring the effectiveness of surrogate-assisted evolutionary algorithms on the batch processing problem
  65. LAD-RCNN:A Powerful Tool for Livestock Face Detection and Normalization
  66. Probability-Dependent Gradient Decay in Large Margin Softmax
  67. Exploring Train and Test-Time Augmentations for Audio-Language Learning
  68. Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks
  69. Studying inductive biases in image classification task
  70. Scoring Black-Box Models for Adversarial Robustness
  71. BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models
  72. Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
  73. Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
  74. ViT-LSLA: Vision Transformer with Light Self-Limited-Attention
  75. QuaLA-MiniLM: a Quantized Length Adaptive MiniLM
  76. SEVGGNet-LSTM: a fused deep learning model for ECG classification
  77. Do Charge Prediction Models Learn Legal Theory?
  78. Unrolled Graph Learning for Multi-Agent Collaboration
  79. Confidence-Nets: A Step Towards better Prediction Intervals for regression Neural Networks on small datasets
  80. DanZero: Mastering GuanDan Game with Reinforcement Learning
  81. FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
  82. TW-BAG: Tensor-wise Brain-aware Gate Network for Inpainting Disrupted Diffusion Tensor Imaging
  83. Computing Rule-Based Explanations by Leveraging Counterfactuals
  84. Private optimization in the interpolation regime: faster rates and hardness results
  85. Unified Optimal Transport Framework for Universal Domain Adaptation
  86. MambaNet: A Hybrid Neural Network for Predicting the NBA Playoffs
  87. Fault diagnosis for open-circuit faults in NPC inverter based on knowledge-driven and data-driven approaches
  88. DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning
  89. Real-time high-resolution CO2 geological storage prediction using nested Fourier neural operators
  90. Modular Hybrid Autoregressive Transducer
  91. Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics
  92. Evaluating Point-Prediction Uncertainties in Neural Networks for Drug Discovery
  93. Convergence of Dirichlet Forms for MCMC Optimal Scaling with Dependent Target Distributions on Large Graphs
  94. GPS: Genetic Prompt Search for Efficient Few-shot Learning
  95. CodeEditor: Learning to Edit Source Code with Pre-trained Models
  96. Improving Multi-generation Robustness of Learned Image Compression
  97. FrozenQubits: Boosting Fidelity of QAOA by Skipping Hotspot Nodes
  98. Evaluation of large-scale synthetic data for Grammar Error Correction
  99. Uncertainty Aware Trader-Company Method: Interpretable Stock Price Prediction Capturing Uncertainty
  100. Improved Learning-augmented Algorithms for k-means and k-medians Clustering
  101. Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation
  102. A Law of Data Separation in Deep Learning
  103. Blank Collapse: Compressing CTC emission for the faster decoding
  104. Emotional Brain State Classification on fMRI Data Using Deep Residual and Convolutional Networks
  105. Embedding Space Augmentation for Weakly Supervised Learning in Whole-Slide Images
  106. GotFlow3D: Recurrent Graph Optimal Transport for Learning 3D Flow Motion in Particle Tracking
  107. A picture of the space of typical learnable tasks
  108. Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds
  109. Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution
  110. Ensemble transport smoothing. Part I: Unified framework
  111. Convergence Rates of Stochastic Zeroth-order Gradient Descent for L ojasiewicz Functions
  112. Comparison of two artificial neural networks trained for the surrogate modeling of stress in materially heterogeneous elastoplastic solids
  113. STN: a new tensor network method to identify stimulus category from brain activity pattern