{"total":22,"rows":[{"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":"2311.04930","title":"Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language","created":"2023-11-05","cited_by_count":32,"area":null},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2107.01131","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2411.01777","title":"Learning predictable and robust neural representations by straightening image sequences","created":"2024-11-04","cited_by_count":9,"area":null},{"id":"2601.22364","title":"Context Structure Reshapes the Representational Geometry of Language Models","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2306.00608","title":"On the Effectiveness of Hybrid Mutual Information Estimation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2105.13977","title":"Perturbation Theory for the Information Bottleneck","created":"2021-05-28","cited_by_count":6,"area":null},{"id":"2303.03432","title":"A polar prediction model for learning to represent visual transformations","created":"2023-03-06","cited_by_count":6,"area":null},{"id":"2405.12109","title":"Linguistic Structure from a Bottleneck on Sequential Information Processing","created":"2024-05-20","cited_by_count":5,"area":null},{"id":"2311.04896","title":"Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2405.07665","title":"Partial information decomposition: redundancy as information bottleneck","created":"2024-05-13","cited_by_count":3,"area":null},{"id":"2303.17762","title":"Generalized Information Bottleneck for Gaussian Variables","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2401.01489","title":"The Neuron as a Direct Data-Driven Controller","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2506.00330","title":"Accurate Estimation of Mutual Information in High Dimensional Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2410.07642","title":"Improving Numerical Stability of Normalized Mutual Information Estimator on High Dimensions","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2308.10913","title":"Automated mapping of virtual environments with visual predictive coding","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2502.11105","title":"Graceful forgetting: Memory as a process","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2510.14486","title":"Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2609.04134","title":"Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}