{"total":35,"rows":[{"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":"2504.16041","title":"Muon Optimizer Accelerates Grokking","created":"2025-04-22","cited_by_count":12,"area":null},{"id":"2609.11801","title":"Thinking with Looped Flows","created":"2026-09-10","cited_by_count":9,"area":null},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"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":"2506.13688","title":"What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers","created":"2025-06-16","cited_by_count":7,"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":"2605.06152","title":"Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2506.23286","title":"Not All Explanations for Deep Learning Phenomena Are Equally Valuable","created":"2025-06-29","cited_by_count":3,"area":null},{"id":"2603.24746","title":"Grokking as a Falsifiable Finite-Size Transition","created":"2026-03-25","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":"2504.17243","title":"NeuralGrok: Accelerate Grokking by Neural Gradient Transformation","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2506.04487","title":"OrthoGrad Improves Neural Calibration","created":"2025-06-04","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":"2604.19740","title":"Generalization at the Edge of Stability","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2605.08237","title":"Distributional Spectral Diagnostics for Localizing Grokking Transitions","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.29176","title":"Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2608.07436","title":"Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers","created":"2026-08-07","cited_by_count":2,"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":"2602.12039","title":"The Implicit Bias of Logit Regularization","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2605.18845","title":"First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.05957","title":"Dead Directions: Geometric Singular Learning","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.18465","title":"What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy","created":"2026-06-16","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":"2608.01833","title":"Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2609.26487","title":"When Recursive Models Finish Computing","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2507.01414","title":"Decomposing Prediction Mechanisms for In-Context Recall","created":"2025-07-02","cited_by_count":0,"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":"2601.22637","title":"Training Beyond Convergence: Grokking nnU-Net for Glioma Segmentation in Sub-Saharan MRI","created":"2026-01-30","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":"2605.17811","title":"One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.05113","title":"Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.28948","title":"From the Loss Landscape to Diverse Feature Learning in Neural Networks","created":"2026-08-28","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":"2610.00620","title":"Misalignment of Low-Loss Regions Causes Grokking","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}