{"total":20,"rows":[{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2406.02917","title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","created":"2024-06-05","cited_by_count":104,"area":null},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2205.10279","title":"Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors","created":"2022-05-20","cited_by_count":43,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","cited_by_count":15,"area":null},{"id":"2306.13292","title":"Variance-Covariance Regularization Improves Representation Learning","created":"2023-06-23","cited_by_count":14,"area":null},{"id":"2403.18494","title":"Learning in PINNs: Phase transition, diffusion equilibrium, and generalization","created":"2024-03-27","cited_by_count":13,"area":null},{"id":"2410.07687","title":"Learning to Compress: Local Rank and Information Compression in Deep Neural Networks","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2412.07169","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2207.09408","title":"Bounding generalization error with input compression: An empirical study with infinite-width networks","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2404.12511","title":"Generalizing Machine Learning Evaluation through the Integration of Shannon Entropy and Rough Set Theory","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2501.02436","title":"Network Dynamics-Based Framework for Understanding Deep Neural Networks","created":"2025-01-05","cited_by_count":1,"area":null},{"id":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2409.01568","title":"Quantifying Emergence in Neural Networks: Insights from Pruning and Training Dynamics","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2506.00859","title":"FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models","created":"2025-06-01","cited_by_count":0,"area":null}],"next_cursor":null}