{"total":87,"rows":[{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111,"area":null},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108,"area":null},{"id":"2301.02679","title":"Grokking modular arithmetic","created":"2023-01-06","cited_by_count":83,"area":null},{"id":"2303.11873","title":"A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks","created":"2023-03-21","cited_by_count":83,"area":null},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80,"area":null},{"id":"2311.08360","title":"The Transient Nature of Emergent In-Context Learning in Transformers","created":"2023-11-14","cited_by_count":76,"area":null},{"id":"2501.04697","title":"Grokking at the Edge of Numerical Stability","created":"2025-01-08","cited_by_count":46,"area":null},{"id":"2405.20233","title":"Grokfast: Accelerated Grokking by Amplifying Slow Gradients","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2407.12332","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","cited_by_count":35,"area":null},{"id":"2310.02541","title":"Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data","created":"2023-10-04","cited_by_count":33,"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":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2407.20199","title":"Emergence in non-neural models: grokking modular arithmetic via average gradient outer product","created":"2024-07-29","cited_by_count":28,"area":null},{"id":"2310.16441","title":"Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding","created":"2023-10-25","cited_by_count":25,"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":"2404.16367","title":"Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers","created":"2024-04-25","cited_by_count":24,"area":null},{"id":"2406.03495","title":"Grokking Modular Polynomials","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2405.19454","title":"Deep Grokking: Would Deep Neural Networks Generalize Better?","created":"2024-05-29","cited_by_count":15,"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":"2310.05918","title":"Grokking as Compression: A Nonlinear Complexity Perspective","created":"2023-10-09","cited_by_count":14,"area":null},{"id":"2310.12956","title":"Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems","created":"2023-10-19","cited_by_count":14,"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":"2311.04163","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","created":"2023-11-07","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":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2311.06597","title":"Understanding Grokking Through A Robustness Viewpoint","created":"2023-11-11","cited_by_count":12,"area":null},{"id":"2408.05446","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","created":"2024-08-08","cited_by_count":12,"area":null},{"id":"2410.04489","title":"Grokking at the Edge of Linear Separability","created":"2024-10-06","cited_by_count":12,"area":null},{"id":"2602.16746","title":"Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","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":"2602.18523","title":"The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure","created":"2026-02-19","cited_by_count":9,"area":null},{"id":"2505.11411","title":"Is Grokking a Computational Glass Relaxation?","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","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":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2603.13331","title":"The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2310.19470","title":"Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks","created":"2023-10-30","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":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2307.09550","title":"The semantic landscape paradigm for neural networks","created":"2023-07-18","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":"2605.06152","title":"Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2310.11282","title":"ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation","created":"2023-10-17","cited_by_count":3,"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":"2405.17479","title":"A rationale from frequency perspective for grokking in training neural network","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2407.01825","title":"Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning","created":"2024-07-01","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":"2510.04930","title":"Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2602.06702","title":"Explaining Grokking in Transformers through the Lens of Inductive Bias","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2604.04171","title":"A Model of Understanding in Deep Learning Systems","created":"2026-04-05","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":"2606.12966","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":"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":"2504.03162","title":"Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.09855","title":"An evolutionary perspective on modes of learning in Transformers","created":"2025-05-14","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":"2601.03162","title":"On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime","created":"2026-01-06","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":"2602.08302","title":"On the Dynamics of Delayed Generalization in Linear Models","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.15492","title":"Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold","created":"2026-03-16","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":"2607.20512","title":"The Active Ingredient in Muon's Grokking","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.20552","title":"Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat","created":"2026-07-15","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":"2412.10898","title":"Exploring Grokking: Experimental and Mechanistic Investigations","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2504.09393","title":"Vision Transformers Exhibit Human-Like Biases: Evidence of Orientation and Color Selectivity, Categorical Perception, and Phase Transitions","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2506.20699","title":"Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2606.29679","title":"Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions","created":"2026-06-29","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":"2609.02373","title":"Percolation Dynamics in Optimization: Variance Cascades and Nested Symmetry","created":"2026-09-02","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":"2609.18314","title":"Beyond Quadratic Loss: The Stability Phase Diagram of Adam","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.19363","title":"Directions That Don't Drift: Stiefel Manifold Routing for Transformer Attention","created":"2026-09-16","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}