{"total":28,"rows":[{"id":"2501.04697","title":"Grokking at the Edge of Numerical Stability","created":"2025-01-08","cited_by_count":46,"area":null},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2508.10053","title":"xRFM: Accurate, scalable, and interpretable feature learning models for tabular data","created":"2025-08-12","cited_by_count":16,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2502.07998","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","created":"2025-02-11","cited_by_count":13,"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":"2601.19791","title":"To Grok Grokking: Provable Grokking in Ridge Regression","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2601.22510","title":"Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2604.13082","title":"The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2505.01751","title":"A dynamic view of some anomalous phenomena in SGD","created":"2025-05-03","cited_by_count":2,"area":null},{"id":"2505.03997","title":"Quiet Feature Learning in Algorithmic Tasks","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2507.05644","title":"The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.15563","title":"On the Neural Feature Ansatz for Deep Neural Networks","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2603.21928","title":"The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation","created":"2026-03-23","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":"2502.15575","title":"Feature maps for the Laplacian kernel and its generalizations","created":"2025-02-21","cited_by_count":1,"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":"2602.04548","title":"Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.29262","title":"Grokking From Abstraction to Intelligence","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.00316","title":"Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.18022","title":"Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2608.22513","title":"From Symmetry to Invariance: Learning Galois Equivalent Representations in Finite Fields","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2503.22059","title":"Low Rank and Sparse Fourier Structure in Recurrent Networks Trained on Modular Addition","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2507.01414","title":"Decomposing Prediction Mechanisms for In-Context Recall","created":"2025-07-02","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":"2607.00329","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.26679","title":"A Spectral Theory of Grokking: Weight Decay induces Feature Learning","created":"2026-09-22","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}