{"total":17,"rows":[{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2508.00212","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2507.04683","title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2508.18258","title":"ANO : Faster is Better in Noisy Landscape","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2512.23419","title":"The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2604.01563","title":"Does Your Optimizer Care How You Normalize? Normalization-Optimizer Coupling in LLM Training","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2606.09762","title":"Preserving Plasticity in Continual Learning via Dynamical Isometry","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.24752","title":"Can Scale Save Us From Plasticity Loss in Large Language Models?","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2511.07308","title":"Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2603.07787","title":"Vision Transformers that Never Stop Learning","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.16426","title":"Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2606.14022","title":"Placing Degree Scales After LayerNorm","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.17922","title":"PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}