{"total":12,"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":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35,"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":"2309.17281","title":"Information Flow in Self-Supervised Learning","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2311.06597","title":"Understanding Grokking Through A Robustness Viewpoint","created":"2023-11-11","cited_by_count":12,"area":null},{"id":"2406.03999","title":"Unveiling the Dynamics of Information Interplay in Supervised Learning","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2310.02903","title":"FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2410.10672","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2409.16767","title":"Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2505.08727","title":"Memorization-Compression Cycles Improve Generalization","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2606.11023","title":"Generative Archetype-Grounded Item Representations for Sequential Recommendation","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2502.20763","title":"Information-Theoretic Perspectives on Optimizers","created":"2025-02-28","cited_by_count":0,"area":null}],"next_cursor":null}