{"total":14,"rows":[{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2407.20199","title":"Emergence in non-neural models: grokking modular arithmetic via average gradient outer product","created":"2024-07-29","cited_by_count":28,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2309.00570","title":"Mechanism of feature learning in convolutional neural networks","created":"2023-09-01","cited_by_count":17,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2404.01139","title":"Structured Initialization for Attention in Vision Transformers","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2409.19460","title":"On the universality of neural encodings in CNNs","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2501.18283","title":"Random Feature Representation Boosting","created":"2025-01-30","cited_by_count":4,"area":null},{"id":"2602.07156","title":"Mimetic Initialization of MLPs","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2509.11711","title":"The Quest for Universal Master Key Filters in DS-CNNs","created":"2025-09-15","cited_by_count":1,"area":null}],"next_cursor":null}