mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 11 Feb 2023

92 papers

  1. A Reparameterized Discrete Diffusion Model for Text GenerationDiffusion models → Discrete and text diffusion
  2. Synthesizing Human Gaze Feedback for Improved NLP PerformanceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  3. Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge LearningLLM reasoning → Mathematical reasoning
  4. Jaccard Metric Losses: Optimizing the Jaccard Index with Soft LabelsKnowledge distillation → Detection and dense prediction distillation
  5. Dual Relation Knowledge Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
  6. Improving Differentiable Architecture Search via Self-DistillationKnowledge distillation → General knowledge distillation methods
  7. Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  8. 3D Colored Shape Reconstruction from a Single RGB Image through DiffusionDiffusion models → 3D, point cloud and scene generation
  9. Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
  10. Unnoticeable Backdoor Attacks on Graph Neural Networks
  11. Orders-of-coupling representation with a single neural network with optimal neuron activation functions and without nonlinear parameter optimization
  12. Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
  13. See Your Heart: Psychological states Interpretation through Visual Creations
  14. Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech
  15. Explaining text classifiers through progressive neighborhood approximation with realistic samples
  16. Synaptic Stripping: How Pruning Can Bring Dead Neurons Back To Life
  17. Level Generation Through Large Language Models
  18. A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee
  19. Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
  20. TPE-Net: Track Point Extraction and Association Network for Rail Path Proposal Generation
  21. Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory
  22. Global Convergence Rate of Deep Equilibrium Models with General Activations
  23. Mutation-Based Adversarial Attacks on Neural Text Detectors
  24. Distributional GFlowNets with Quantile Flows
  25. Dimension Reduction and MARS
  26. Fairness-aware Multi-view Clustering
  27. Differentially Private Normalizing Flows for Density Estimation, Data Synthesis, and Variational Inference with Application to Electronic Health Records
  28. ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
  29. Predicting municipalities in financial distress: a machine learning approach enhanced by domain expertise
  30. How to prepare your task head for finetuning
  31. Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks
  32. Adversarial Online Collaborative Filtering
  33. Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications
  34. Interpretable Deep Learning for Forecasting Online Advertising Costs: Insights from the Competitive Bidding Landscape
  35. Confidence and Uncertainty Assessment for Distributional Random Forests
  36. Improving Sign Recognition with Phonology
  37. Multispectral Contrastive Learning with Viewmaker Networks
  38. DaliID: Distortion-Adaptive Learned Invariance for Identification Models
  39. Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes
  40. Removing Image Artifacts From Scratched Lens Protectors
  41. Verifying Generalization in Deep Learning
  42. Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
  43. Is Distance Matrix Enough for Geometric Deep Learning?
  44. UGAE: A Novel Approach to Non-exponential Discounting
  45. Cross-Modal Fine-Tuning: Align then Refine
  46. Divergence-Based Domain Transferability for Zero-Shot Classification
  47. Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
  48. A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3
  49. Sequential Embedding-based Attentive (SEA) classifier for malware classification
  50. Flexible-modal Deception Detection with Audio-Visual Adapter
  51. Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP
  52. On Differential Privacy and Adaptive Data Analysis with Bounded Space
  53. MTTM: Metamorphic Testing for Textual Content Moderation Software
  54. HateProof: Are Hateful Meme Detection Systems really Robust?
  55. Cross-center Early Sepsis Recognition by Medical Knowledge Guided Collaborative Learning for Data-scarce Hospitals
  56. Compositional Exemplars for In-context Learning
  57. A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based Testing
  58. Sequential Underspecified Instrument Selection for Cause-Effect Estimation
  59. CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models
  60. Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
  61. Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
  62. ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-Identification
  63. The Impact of Expertise in the Loop for Exploring Machine Rationality
  64. DocILE Benchmark for Document Information Localization and Extraction
  65. Dialectograms: Machine Learning Differences between Discursive Communities
  66. SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies
  67. Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph
  68. Operation-level Progressive Differentiable Architecture Search
  69. A Survey on Spectral Graph Neural Networks
  70. CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing Environments
  71. A novel approach to generate datasets with XAI ground truth to evaluate image models
  72. Dive into the Resolution Augmentations and Metrics in Low Resolution Face Recognition: A Plain yet Effective New Baseline
  73. Improved Dynamic Regret for Online Frank-Wolfe
  74. Evaluating the Robustness of Discrete Prompts
  75. Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis
  76. Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
  77. Metaphor Detection with Effective Context Denoising
  78. Emotion Detection From Social Media Posts
  79. Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
  80. Predicting Participants' Performance in Programming Contests using Deep Learning Techniques
  81. Pruning Deep Neural Networks from a Sparsity Perspective
  82. Communication and Storage Efficient Federated Split Learning
  83. Multi-class Brain Tumor Segmentation using Graph Attention Network
  84. MatKB: Semantic Search for Polycrystalline Materials Synthesis Procedures
  85. ReMIX: Regret Minimization for Monotonic Value Function Factorization in Multiagent Reinforcement Learning
  86. Windowed Fourier Analysis for Signal Processing on Graph Bundles
  87. Hierarchical Optimization-Derived Learning
  88. Procedural generation of meta-reinforcement learning tasks
  89. ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems
  90. Sketch Less Face Image Retrieval: A New Challenge
  91. NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization
  92. MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring based on A Dual-CNN Model