{"total":21,"rows":[{"id":"2406.02550","title":"Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks","created":"2024-06-04","cited_by_count":40,"area":null},{"id":"2401.10463","title":"Critical Data Size of Language Models from a Grokking Perspective","created":"2024-01-19","cited_by_count":24,"area":null},{"id":"2408.08944","title":"Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition","created":"2024-08-16","cited_by_count":17,"area":null},{"id":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15,"area":null},{"id":"2402.16726","title":"Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials","created":"2024-02-26","cited_by_count":14,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2509.06931","title":"Learning words in groups: fusion algebras, tensor ranks and grokking","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2512.25060","title":"On the geometry and topology of representations: the manifolds of modular addition","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2502.01739","title":"Grokking vs. Learning: Same Features, Different Encodings","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2511.00580","title":"TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection","created":"2025-11-01","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":"2602.08302","title":"On the Dynamics of Delayed Generalization in Linear Models","created":"2026-02-09","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":"2605.24420","title":"Batch Normalization Amplifies Memorization and Privacy Risks","created":"2026-05-23","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":"2507.11645","title":"Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2510.26792","title":"Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.21761","title":"LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.23784","title":"Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2606.07563","title":"Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.24460","title":"Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}