mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 27 Jan 2023

177 papers

  1. Improved knowledge distillation by utilizing backward pass knowledge in neural networksKnowledge distillation → General knowledge distillation methods
  2. EmbedDistill: A Geometric Knowledge Distillation for Information RetrievalKnowledge distillation → Knowledge distillation for LLMs
  3. Minimizing Trajectory Curvature of ODE-based Generative ModelsDiffusion models → Diffusion foundations and sampling
  4. Case-Based Reasoning with Language Models for Classification of Logical FallaciesLLM reasoning → Reasoning benchmarks and evaluation
  5. Reinforcement Learning from Diverse Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. Mousai: Text-to-Music Generation with Long-Context Latent DiffusionDiffusion models → Audio, speech and music
  7. Improving Behavioural Cloning with Positive Unlabeled LearningOffline RL and imitation learning from data → Imitation learning methods
  8. Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?Diffusion models → Image generation, text-to-image and editing
  9. Input Perturbation Reduces Exposure Bias in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  10. Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?Knowledge distillation → Knowledge distillation for LLMs
  11. Theoretical Analysis of Offline Imitation With Supplementary DatasetOffline RL and imitation learning from data → Imitation learning methods
  12. A Denoising Diffusion Model for Fluid Field PredictionDiffusion models → Flow matching, time series and science
  13. ThoughtSource: A central hub for large language model reasoning dataLLM reasoning → Prompting and chain-of-thought reasoning
  14. Learning to Unlearn: Instance-wise Unlearning for Pre-trained ClassifiersLLM safety and security → Machine unlearning
  15. Accelerating Guided Diffusion Sampling with Splitting Numerical MethodsDiffusion models → Diffusion foundations and sampling
  16. PLay: Parametrically Conditioned Layout Generation using Latent DiffusionDiffusion models → Image generation, text-to-image and editing
  17. Talk the Walk: Synthetic Data Generation for Conversational Music RecommendationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  18. Effect of temporal resolution on the reproduction of chaotic dynamics via reservoir computing
  19. Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI
  20. Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVM
  21. PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations
  22. Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization
  23. Exploring External Knowledge for Accurate modeling of Visual and Language Problems
  24. Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments
  25. A Valid Self-Report is Never Late, Nor is it Early: On Considering the "Right" Temporal Distance for Assessing Emotional Experience
  26. Investigating the use of ChatGPT for the scheduling of construction projects
  27. SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention
  28. Incentives to Offer Algorithmic Recourse
  29. Identifying the Key Attributes in an Unlabeled Event Log for Automated Process Discovery
  30. Context Matters: A Strategy to Pre-train Language Model for Science Education
  31. Multi-task Highly Adaptive Lasso
  32. Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learning
  33. Meta Temporal Point Processes
  34. Epsilon-Identifiability of Causal Quantities
  35. Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases
  36. In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States
  37. Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation
  38. Vertex-based reachability analysis for verifying ReLU deep neural networks
  39. Prompt-Based Editing for Text Style Transfer
  40. Alignment with human representations supports robust few-shot learning
  41. Practical Differentially Private Hyperparameter Tuning with Subsampling
  42. Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstruction
  43. Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data
  44. A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
  45. Byte Pair Encoding for Symbolic Music
  46. Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI
  47. Adversarial Networks and Machine Learning for File Classification
  48. On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease
  49. Reduced-Order Autodifferentiable Ensemble Kalman Filters
  50. On the Connection Between MPNN and Graph Transformer
  51. Adaptive whitening in neural populations with gain-modulating interneurons
  52. Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation
  53. Deep Quantum Error Correction
  54. Training Full Spike Neural Networks via Auxiliary Accumulation Pathway
  55. Incorporating Background Knowledge in Symbolic Regression using a Computer Algebra System
  56. Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
  57. Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
  58. SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
  59. OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks
  60. Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees
  61. Uplink Scheduling in Federated Learning: an Importance-Aware Approach via Graph Representation Learning
  62. Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers
  63. DAG Learning on the Permutahedron
  64. Streaming LifeLong Learning With Any-Time Inference
  65. Polycraft World AI Lab (PAL): An Extensible Platform for Evaluating Artificial Intelligence Agents
  66. Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
  67. Optical Flow Estimation in 360^circ Videos: Dataset, Model and Application
  68. A Deep Learning Method for Comparing Bayesian Hierarchical Models
  69. Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean
  70. Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning
  71. ActiveLab: Active Learning with Re-Labeling by Multiple Annotators
  72. Predicting Sentence-Level Factuality of News and Bias of Media Outlets
  73. A Comparative Study of Pretrained Language Models for Long Clinical Text
  74. Learning the Effects of Physical Actions in a Multi-modal Environment
  75. Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking
  76. PhysGraph: Physics-Based Integration Using Graph Neural Networks
  77. SOBER: Highly Parallel Bayesian Optimization and Bayesian Quadrature over Discrete and Mixed Spaces
  78. Deep Clustering Survival Machines with Interpretable Expert Distributions
  79. PECAN: A Deterministic Certified Defense Against Backdoor Attacks
  80. HDPV-SLAM: Hybrid Depth-augmented Panoramic Visual SLAM for Mobile Mapping System with Tilted LiDAR and Panoramic Visual Camera
  81. BOMP-NAS: Bayesian Optimization Mixed Precision NAS
  82. PCV: A Point Cloud-Based Network Verifier
  83. Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds
  84. From Classification Accuracy to Proper Scoring Rules: Elicitability of Probabilistic Top List Predictions
  85. Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
  86. Graph Attention with Hierarchies for Multi-hop Question Answering
  87. Leveraging the Third Dimension in Contrastive Learning
  88. Certified Invertibility in Neural Networks via Mixed-Integer Programming
  89. Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
  90. Interpreting learning in biological neural networks as zero-order optimization method
  91. Automatic Modulation Classification with Deep Neural Networks
  92. CAPoW: Context-Aware AI-Assisted Proof of Work based DDoS Defense
  93. ExplainableFold: Understanding AlphaFold Prediction with Explainable AI
  94. Gene Teams are on the Field: Evaluation of Variants in Gene-Networks Using High Dimensional Modelling
  95. D'etection d'Objets dans les documents num'eris'es par r'eseaux de neurones profonds
  96. Inter-View Depth Consistency Testing in Depth Difference Subspace
  97. A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
  98. Side Auth: Synthesizing Virtual Sensors for Authentication
  99. Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
  100. Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
All 177
  1. Modeling human road crossing decisions as reward maximization with visual perception limitations
  2. Convolutional neural networks for valid and efficient causal inference
  3. Meta-Learning Mini-Batch Risk Functionals
  4. Single-Trajectory Distributionally Robust Reinforcement Learning
  5. The Exploration of Knowledge-Preserving Prompts for Document Summarisation
  6. Pre-training for Speech Translation: CTC Meets Optimal Transport
  7. Semantic Network Model for Sign Language Comprehension
  8. Improving deep learning precipitation nowcasting by using prior knowledge
  9. FedPH: Privacy-enhanced Heterogeneous Federated Learning
  10. TransNet: Transferable Neural Networks for Partial Differential Equations
  11. Image Restoration with Mean-Reverting Stochastic Differential Equations
  12. Big portfolio selection by graph-based conditional moments method
  13. SLCNN: Sentence-Level Convolutional Neural Network for Text Classification
  14. LegendreTron: Uprising Proper Multiclass Loss Learning
  15. Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding
  16. Neural Abstractions
  17. Towards Personalized Review Summarization by Modeling Historical Reviews from Customer and Product Separately
  18. Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
  19. Bayesian Self-Supervised Contrastive Learning
  20. Deep Residual Compensation Convolutional Network without Backpropagation
  21. Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning
  22. Semi-Supervised Machine Learning: a Homological Approach
  23. Multilayer hypergraph clustering using the aggregate similarity matrix
  24. Fast Region of Interest Proposals on Maritime UAVs
  25. Learning the Dynamics of Sparsely Observed Interacting Systems
  26. HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
  27. Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support
  28. Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
  29. Event Causality Extraction with Event Argument Correlations
  30. A Multi-View Joint Learning Framework for Embedding Clinical Codes and Text Using Graph Neural Networks
  31. A critical look at deep neural network for dynamic system modeling
  32. Improved Differential-neural Cryptanalysis for Round-reduced Simeck32/64
  33. Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties
  34. Adversarial Learning for Implicit Semantic-Aware Communications
  35. Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty
  36. Robust variance-regularized risk minimization with concomitant scaling
  37. A Green(er) World for A.I
  38. Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech
  39. AdaBoost is not an Optimal Weak to Strong Learner
  40. Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding
  41. Exponential tail bounds and Large Deviation Principle for Heavy-Tailed U-Statistics
  42. Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
  43. Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
  44. Conformal inference is (almost) free for neural networks trained with early stopping
  45. Robust Transformer with Locality Inductive Bias and Feature Normalization
  46. Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows
  47. Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation
  48. Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
  49. Targeted Attacks on Timeseries Forecasting
  50. Feasibility and Transferability of Transfer Learning: A Mathematical Framework
  51. Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
  52. Direct Parameterization of Lipschitz-Bounded Deep Networks
  53. Mixed Attention Network for Hyperspectral Image Denoising
  54. A Comparison of Tiny-nerf versus Spatial Representations for 3d Reconstruction
  55. SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
  56. Online Learning in Stackelberg Games with an Omniscient Follower
  57. Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
  58. Deep Industrial Image Anomaly Detection: A Survey
  59. CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification
  60. Exploring Deep Reinforcement Learning for Holistic Smart Building Control
  61. Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
  62. Theme-driven Keyphrase Extraction to Analyze Social Media Discourse
  63. Semi-Parametric Video-Grounded Text Generation
  64. Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation
  65. Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
  66. Dual-View Selective Instance Segmentation Network for Unstained Live Adherent Cells in Differential Interference Contrast Images
  67. D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
  68. Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks
  69. Learning Vortex Dynamics for Fluid Inference and Prediction
  70. Neural Episodic Control with State Abstraction
  71. Machine Learning Approach and Extreme Value Theory to Correlated Stochastic Time Series with Application to Tree Ring Data
  72. Projected Subnetworks Scale Adaptation
  73. Diffusion Denoising for Low-Dose-CT Model
  74. Are Equivariant Equilibrium Approximators Beneficial?
  75. Alien Coding
  76. Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
  77. Multi-limb Split Learning for Tumor Classification on Vertically Distributed Data