{"list":"other","total":63,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1810.10531","title":"A mathematical theory of semantic development in deep neural networks","created":"2018-10-23","cited_by_count":186},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72},{"id":"2409.10559","title":"Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers","created":"2024-09-09","cited_by_count":50},{"id":"2405.13698","title":"How to set AdamW's weight decay as you scale model and dataset size","created":"2024-05-22","cited_by_count":43},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29},{"id":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","cited_by_count":28},{"id":"2404.17563","title":"An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem","created":"2024-04-26","cited_by_count":22},{"id":"2206.05794","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","created":"2022-06-12","cited_by_count":19},{"id":"2311.03260","title":"From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach","created":"2023-11-06","cited_by_count":15},{"id":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15},{"id":"2602.16746","title":"Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking","created":"2026-02-18","cited_by_count":11},{"id":"2511.01938","title":"The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold","created":"2025-11-02","cited_by_count":9},{"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},{"id":"2505.11411","title":"Is Grokking a Computational Glass Relaxation?","created":"2025-05-16","cited_by_count":8},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8},{"id":"2601.19791","title":"To Grok Grokking: Provable Grokking in Ridge Regression","created":"2026-01-27","cited_by_count":8},{"id":"2602.16967","title":"Early-Warning Signals of Grokking via Loss-Landscape Geometry","created":"2026-02-19","cited_by_count":7},{"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},{"id":"2603.25009","title":"A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization","created":"2026-03-26","cited_by_count":6},{"id":"2603.05228","title":"The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology","created":"2026-03-05","cited_by_count":5},{"id":"2603.28964","title":"Spectral Edge Dynamics: An Analytical-Empirical Study of Phase Transitions in Neural Network Training","created":"2026-03-30","cited_by_count":4},{"id":"2603.29805","title":"From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability","created":"2026-03-31","cited_by_count":4},{"id":"2604.04655","title":"Grokking as Dimensional Phase Transition in Neural Networks","created":"2026-04-06","cited_by_count":4},{"id":"2605.09724","title":"Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds","created":"2026-05-10","cited_by_count":4},{"id":"2603.24746","title":"Grokking as a Falsifiable Finite-Size Transition","created":"2026-03-25","cited_by_count":3},{"id":"2604.13082","title":"The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior","created":"2026-03-30","cited_by_count":3},{"id":"2604.16431","title":"Dimensional Criticality at Grokking Across MLPs and Transformers","created":"2026-04-06","cited_by_count":3},{"id":"2312.03012","title":"A Waddington landscape for prototype learning in generalized Hopfield networks","created":"2023-12-04","cited_by_count":2},{"id":"2602.02859","title":"Late-Stage Generalization Collapse in Grokking: Detecting anti-grokking with Weightwatcher","created":"2026-02-02","cited_by_count":2},{"id":"2602.06702","title":"Explaining Grokking in Transformers through the Lens of Inductive Bias","created":"2026-02-06","cited_by_count":2},{"id":"2602.14445","title":"Selective Synchronization Attention","created":"2026-02-16","cited_by_count":2},{"id":"2603.03993","title":"Specialization of softmax attention heads: insights from the high-dimensional single-location model","created":"2026-03-04","cited_by_count":2},{"id":"2604.06256","title":"Spectral Edge Dynamics Reveal Functional Modes of Learning","created":"2026-04-06","cited_by_count":2},{"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},{"id":"2604.20923","title":"ILDR: Geometric Early Detection of Grokking","created":"2026-04-22","cited_by_count":2},{"id":"2605.06352","title":"Topological Signatures of Grokking","created":"2026-05-07","cited_by_count":2},{"id":"2605.08237","title":"Distributional Spectral Diagnostics for Localizing Grokking Transitions","created":"2026-05-07","cited_by_count":2},{"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},{"id":"2603.29262","title":"Grokking From Abstraction to Intelligence","created":"2026-03-31","cited_by_count":1},{"id":"2604.07380","title":"The Lifecycle of the Spectral Edge: From Gradient Learning to Weight-Decay Compression","created":"2026-04-08","cited_by_count":1},{"id":"2605.04396","title":"Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize","created":"2026-05-06","cited_by_count":1},{"id":"2605.12394","title":"Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory","created":"2026-05-12","cited_by_count":1}],"next_cursor":null}