{"total":45,"rows":[{"id":"2501.04697","title":"Grokking at the Edge of Numerical Stability","created":"2025-01-08","cited_by_count":46,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"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":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2412.18283","title":"On the Local Complexity of Linear Regions in Deep ReLU Networks","created":"2024-12-24","cited_by_count":9,"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":"2511.01938","title":"The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2405.12755","title":"Progress Measures for Grokking on Real-world Tasks","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2509.17738","title":"Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking","created":"2025-09-22","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":"2505.15624","title":"Mechanistic Insights into Grokking from the Embedding Layer","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2407.14055","title":"Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2505.18023","title":"Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time","created":"2025-05-23","cited_by_count":4,"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":"2509.20829","title":"Explaining Grokking and Information Bottleneck through Neural Collapse Emergence","created":"2025-09-25","cited_by_count":4,"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":"2405.16658","title":"Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2508.03867","title":"Constraining the outputs of ReLU neural networks","created":"2025-08-05","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":"2604.11962","title":"The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts","created":"2026-04-13","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":"2506.12284","title":"GrokAlign: Geometric Characterisation and Acceleration of Grokking","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2510.12700","title":"Topological Signatures of ReLU Neural Network Activation Patterns","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2605.06352","title":"Topological Signatures of Grokking","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.27078","title":"Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2607.23967","title":"Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries","created":"2026-07-27","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":"2504.05677","title":"Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2504.12700","title":"A Two-Phase Perspective on Deep Learning Dynamics","created":"2025-04-17","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":"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":"2408.04809","title":"On the Geometry of Deep Learning","created":"2024-08-09","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":"2507.09897","title":"Algorithm Development in Neural Networks: Insights from the Streaming Parity Task","created":"2025-07-14","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":"2508.19028","title":"GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.17381","title":"Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2601.08316","title":"Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2607.10430","title":"Emergent Generalization by Representation Learning in Artificial Neural Networks","created":"2026-07-11","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":"2609.32695","title":"Affine Geometry of Gaussian ReLU Networks via Conditional Kac-Rice Formulas","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39115","title":"Beyond Local Linearity: Scale-Resolved Geometry of Learned Image Encoders","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01633","title":"Generalization in Neural Networks Through the Lens of Magnitude Potential","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}