{"total":18,"rows":[{"id":"2110.07143","title":"bert2BERT: Towards Reusable Pretrained Language Models","created":"2021-10-14","cited_by_count":70,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2102.08574","title":"Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks","created":"2021-02-17","cited_by_count":49,"area":null},{"id":"2111.05850","title":"Towards Green Automated Machine Learning: Status Quo and Future Directions","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2505.05587","title":"Steepest Descent Density Control for Compact 3D Gaussian Splatting","created":"2025-05-08","cited_by_count":13,"area":null},{"id":"2401.09192","title":"Preparing Lessons for Progressive Training on Language Models","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2312.09148","title":"Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2411.05855","title":"Learning Morphisms with Gauss-Newton Approximation for Growing Networks","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2508.19151","title":"Saddle Hierarchy in Dense Associative Memory","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.18842","title":"Shared-Weights Extender and Gradient Voting for Neural Network Expansion","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2110.08857","title":"Growing Representation Learning","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2201.06500","title":"Growing Neural Network with Shared Parameter","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2309.08615","title":"Energy Concerns with HPC Systems and Applications","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2402.12418","title":"Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2606.31110","title":"Explaining Machine Learning and Memorization with Statistical Mechanics","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}