mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 22 May 2022

106 papers

  1. Chain of Thought Imitation with Procedure CloningLLM reasoning → Spatial and embodied reasoning +1
  2. Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement LearnerOffline RL and imitation learning from data → Inverse reinforcement learning
  3. Knowledge Distillation via the Target-aware TransformerKnowledge distillation → General knowledge distillation methods
  4. Interpretable Proof Generation via Iterative Backward ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  5. Housekeep: Tidying Virtual Households using Commonsense ReasoningLLM reasoning → Spatial and embodied reasoning
  6. aSTDP: A More Biologically Plausible Learning
  7. Edge Graph Neural Networks for Massive MIMO Detection
  8. Social Practices: a Complete Formalization
  9. Deep Low-Density Separation for Semi-Supervised Classification
  10. The Geometry of Multilingual Language Model Representations
  11. Investigating classification learning curves for automatically generated and labelled plant images
  12. An Automated System for Detecting Visual Damages of Wind Turbine Blades
  13. CYRUS Soccer Simulation 2D Team Description Paper 2022
  14. Generalization ability and Vulnerabilities to adversarial perturbations: Two sides of the same coin
  15. Incentivizing Federated Learning
  16. Evaluating deep tracking models for player tracking in broadcast ice hockey video
  17. Deep Direct Discriminative Decoders for High-dimensional Time-series Data Analysis
  18. Toward smart composites: small-scale, untethered prediction and control for soft sensor/actuator systems
  19. Diversity Enhanced Table-to-Text Generation via Type Control
  20. muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems
  21. On Elimination Strategies for Bandit Fixed-Confidence Identification
  22. AutoJoin: Efficient Adversarial Training against Gradient-Free Perturbations for Robust Maneuvering via Denoising Autoencoder and Joint Learning
  23. Argumentative Explanations for Pattern-Based Text Classifiers
  24. Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class Classification
  25. Test-Time Robust Personalization for Federated Learning
  26. Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited
  27. Limitations of a proposed correction for slow drifts in decision criterion
  28. Power and accountability in reinforcement learning applications to environmental policy
  29. Improved Modeling of Persistence Diagram
  30. Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification
  31. The Case for Perspective in Multimodal Datasets
  32. Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization
  33. Contextual Information-Directed Sampling
  34. Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
  35. Nonparametric likelihood-free inference with Jensen-Shannon divergence for simulator-based models with categorical output
  36. Improving AMD diagnosis by the simultaneous identification of associated retinal lesions
  37. Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation
  38. Fast Gaussian Process Posterior Mean Prediction via Local Cross Validation and Precomputation
  39. Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
  40. Dynamic Query Selection for Fast Visual Perceiver
  41. Fusion Subspace Clustering for Incomplete Data
  42. Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation
  43. Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks
  44. Federated Learning Aggregation: New Robust Algorithms with Guarantees
  45. Contrastive Learning of Coarse-Grained Force Fields
  46. Positioning Fog Computing for Smart Manufacturing
  47. RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning
  48. Relphormer: Relational Graph Transformer for Knowledge Graph Representations
  49. Vision-based Anti-UAV Detection and Tracking
  50. AFEC: A Knowledge Graph Capturing Social Intelligence in Casual Conversations
  51. Robust Quantity-Aware Aggregation for Federated Learning
  52. Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce
  53. Addressing Strategic Manipulation Disparities in Fair Classification
  54. Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation
  55. Deep Learning for Visual Speech Analysis: A Survey
  56. Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients
  57. Neural Inverse Kinematics
  58. Multilingual Machine Translation with Hyper-Adapters
  59. What Do Compressed Multilingual Machine Translation Models Forget?
  60. A Convolutional Dispersion Relation Preserving Scheme for the Acoustic Wave Equation
  61. ReLU Fields: The Little Non-linearity That Could
  62. A Graph Enhanced BERT Model for Event Prediction
  63. Deep Learning-Based Synchronization for Uplink NB-IoT
  64. GraphMAE: Self-Supervised Masked Graph Autoencoders
  65. PAC-Wrap: Semi-Supervised PAC Anomaly Detection
  66. Learning Muti-expert Distribution Calibration for Long-tailed Video Classification
  67. A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
  68. Responsible Artificial Intelligence -- from Principles to Practice
  69. Instruction Induction: From Few Examples to Natural Language Task Descriptions
  70. Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems
  71. Sleep Posture One-Shot Learning Framework Using Kinematic Data Augmentation: In-Silico and In-Vivo Case Studies
  72. A Domain-adaptive Pre-training Approach for Language Bias Detection in News
  73. Fast Instrument Learning with Faster Rates
  74. Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
  75. Neuro-Symbolic Artificial Intelligence (AI) for Intent based Semantic Communication
  76. Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
  77. Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
  78. Evidence for Hypodescent in Visual Semantic AI
  79. A Deep Conjugate Direction Method for Iteratively Solving Linear Systems
  80. How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts
  81. CNNs Avoid Curse of Dimensionality by Learning on Patches
  82. Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities
  83. Residual Channel Attention Network for Brain Glioma Segmentation
  84. Deep Feature Fusion via Graph Convolutional Network for Intracranial Artery Labeling
  85. Real Time Detection Free Tracking of Multiple Objects Via Equilibrium Optimizer
  86. Covariance Matrix Adaptation MAP-Annealing
  87. Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications
  88. Preparing data for pathological artificial intelligence with clinical-grade performance
  89. Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
  90. Classification of Quasars, Galaxies, and Stars in the Mapping of the Universe Multi-modal Deep Learning
  91. All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass
  92. Do Deep Learning Models and News Headlines Outperform Conventional Prediction Techniques on Forex Data?
  93. Offline Policy Comparison with Confidence: Benchmarks and Baselines
  94. OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
  95. Should Models Be Accurate?
  96. GraB: Finding Provably Better Data Permutations than Random Reshuffling
  97. Robust Flow-based Conformal Inference (FCI) with Statistical Guarantee
  98. Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path
  99. Neural Lyapunov Differentiable Predictive Control
  100. TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks
All 106
  1. Learnable Visual Words for Interpretable Image Recognition
  2. Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction
  3. Active Source Free Domain Adaptation
  4. Phrase-level Textual Adversarial Attack with Label Preservation
  5. GL-RG: Global-Local Representation Granularity for Video Captioning
  6. Lassoed Tree Boosting