{"total":37,"rows":[{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139,"area":null},{"id":"2311.00208","title":"What Formal Languages Can Transformers Express? A Survey","created":"2023-11-01","cited_by_count":124,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"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":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2305.18741","title":"Grokking of Hierarchical Structure in Vanilla Transformers","created":"2023-05-30","cited_by_count":53,"area":null},{"id":"2310.13897","title":"Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages","created":"2023-10-21","cited_by_count":49,"area":null},{"id":"2404.04393","title":"Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers","created":"2024-04-05","cited_by_count":39,"area":null},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2405.16674","title":"Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2201.12451","title":"Extracting Finite Automata from RNNs Using State Merging","created":"2022-01-28","cited_by_count":17,"area":null},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2505.00926","title":"How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2309.03004","title":"A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2510.00368","title":"The Transformer Cookbook","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2601.01754","title":"Context-Free Recognition with Transformers","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2403.07379","title":"Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2502.19416","title":"Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2507.04683","title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2512.01231","title":"Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamics","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2605.24850","title":"Repeated Sequences Reveal Gaps between Large Language Models and Natural Language","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2402.15227","title":"Fixed Random Classifier Rearrangement for Continual Learning","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2509.23487","title":"Temporal Generalization: A Reality Check","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2605.26489","title":"The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.12671","title":"On the Expressive Power of Transformers","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.39827","title":"Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}