{"total":34,"rows":[{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2504.13292","title":"Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model","created":"2025-04-17","cited_by_count":13,"area":null},{"id":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2505.15624","title":"Mechanistic Insights into Grokking from the Embedding Layer","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2603.25009","title":"A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2411.17617","title":"An Ensemble Approach for Brain Tumor Segmentation and Synthesis","created":"2024-11-26","cited_by_count":5,"area":null},{"id":"2605.09724","title":"Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2603.24746","title":"Grokking as a Falsifiable Finite-Size Transition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2607.04333","title":"Structure-Specific Representational Priors Causally Control the Grokking Delay","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2504.17243","title":"NeuralGrok: Accelerate Grokking by Neural Gradient Transformation","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2506.12284","title":"GrokAlign: Geometric Characterisation and Acceleration of Grokking","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2510.04930","title":"Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.05361","title":"MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2512.06370","title":"Greedy Alignment Principle for Optimizer Selection","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2603.25047","title":"The Order Is The Message","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.13123","title":"Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2604.20923","title":"ILDR: Geometric Early Detection of Grokking","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2606.12966","title":"Learned Structure Shows Up Earlier in the Task's Own Basis: A Controlled Look at a Synchronisation Precursor in Grokking","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2504.03162","title":"Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2511.04760","title":"When Data Falls Short: Grokking Below the Critical Threshold","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2603.06120","title":"Dynamic Momentum Recalibration in Online Gradient Learning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.12394","title":"Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.32000","title":"Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.11666","title":"How to Tame Grokking: Representation Geometry as a Control Signal","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.20512","title":"The Active Ingredient in Muon's Grokking","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.18415","title":"The Road Taken: The Role of Optimizers at the Edge of Stability","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2601.04283","title":"Mitigating Position-Shift Failures in Text-Based Modular Arithmetic via Position Curriculum and Template Diversity","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2604.27295","title":"Learning Rate Engineering: From Coarse Single Parameter to Layered Evolution","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.08464","title":"The Geometric Structure of Models Learning Sparse Data","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.28184","title":"Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.13197","title":"Algorithmic Information Dynamics of Learning: A Certified, Differentiable Complexity Controller for Grokking","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.32290","title":"A Journey to the Edge of Stability","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.18811","title":"Statistical Vignettes on the Grokking Phenomenon","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}