{"total":204,"rows":[{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503,"area":null},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262,"area":null},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161,"area":null},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156,"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":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86,"area":null},{"id":"2301.02679","title":"Grokking modular arithmetic","created":"2023-01-06","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":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2303.06173","title":"Unifying Grokking and Double Descent","created":"2023-03-10","cited_by_count":50,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","cited_by_count":48,"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":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33,"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":"2311.07568","title":"Feature emergence via margin maximization: case studies in algebraic tasks","created":"2023-11-13","cited_by_count":33,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","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":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"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":"2409.15771","title":"Zero-shot forecasting of chaotic systems","created":"2024-09-24","cited_by_count":28,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"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":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2310.13061","title":"To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets","created":"2023-10-19","cited_by_count":24,"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":"2402.15175","title":"Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition","created":"2024-02-23","cited_by_count":23,"area":null},{"id":"2412.09810","title":"The Complexity Dynamics of Grokking","created":"2024-12-13","cited_by_count":22,"area":null},{"id":"2502.07551","title":"Early Stopping Against Label Noise Without Validation Data","created":"2025-02-11","cited_by_count":21,"area":null},{"id":"2505.20896","title":"How Do Transformers Learn Variable Binding in Symbolic Programs?","created":"2025-05-27","cited_by_count":21,"area":null},{"id":"2406.03495","title":"Grokking Modular Polynomials","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2312.02566","title":"Structured World Representations in Maze-Solving Transformers","created":"2023-12-05","cited_by_count":16,"area":null},{"id":"2403.10381","title":"Monotonic Representation of Numeric Properties in Language Models","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2406.18400","title":"Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers","created":"2024-06-26","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":"2310.17247","title":"Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2402.05173","title":"Towards Understanding Inductive Bias in Transformers: A View From Infinity","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2503.10065","title":"Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild","created":"2025-03-13","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":"2505.20172","title":"A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2311.06597","title":"Understanding Grokking Through A Robustness Viewpoint","created":"2023-11-11","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":"2504.16041","title":"Muon Optimizer Accelerates Grokking","created":"2025-04-22","cited_by_count":12,"area":null},{"id":"2410.07041","title":"Emergent properties with repeated examples","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2410.18808","title":"Delving into the Reversal Curse: How Far Can Large Language Models Generalize?","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2410.22244","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2410.03006","title":"Formation of Representations in Neural Networks","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2508.03616","title":"Hidden Dynamics of Massive Activations in Transformer Training","created":"2025-08-05","cited_by_count":10,"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":"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":"2503.18114","title":"Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry","created":"2025-03-23","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":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2505.11411","title":"Is Grokking a Computational Glass Relaxation?","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2506.04434","title":"Grokking and Generalization Collapse: Insights from \\texttt{HTSR} theory","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","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":"2310.12802","title":"An effective theory of collective deep learning","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2402.01082","title":"Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors","created":"2024-02-02","cited_by_count":7,"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":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"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":"2602.16967","title":"Early-Warning Signals of Grokking via Loss-Landscape Geometry","created":"2026-02-19","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":"2401.11600","title":"Understanding the Generalization Benefits of Late Learning Rate Decay","created":"2024-01-21","cited_by_count":6,"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":"2408.09414","title":"Clustering and Alignment: Understanding the Training Dynamics in Modular Addition","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5,"area":null},{"id":"2409.10715","title":"Self-Attention Limits Working Memory Capacity of Transformer-Based Models","created":"2024-09-16","cited_by_count":5,"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":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2605.05683","title":"Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2605.06258","title":"The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks","created":"2026-05-07","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":"2402.05916","title":"GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2405.17209","title":"How Do Transformers \"Do\" Physics? Investigating the Simple Harmonic Oscillator","created":"2024-05-23","cited_by_count":4,"area":null}],"next_cursor":"100"}