{"total":47,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649,"area":null},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363,"area":null},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272,"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":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85,"area":null},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"area":null},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2206.10012","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","created":"2022-06-20","cited_by_count":35,"area":null},{"id":"2405.15124","title":"Scaling Law for Time Series Forecasting","created":"2024-05-24","cited_by_count":33,"area":null},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","cited_by_count":26,"area":null},{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2102.08380","title":"Topological Obstructions to Autoencoding","created":"2021-02-16","cited_by_count":20,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2108.11018","title":"A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?","created":"2021-08-25","cited_by_count":15,"area":null},{"id":"2110.12735","title":"Practical Galaxy Morphology Tools from Deep Supervised Representation Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2210.13447","title":"Precision Machine Learning","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2306.14670","title":"Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition","created":"2023-06-26","cited_by_count":14,"area":null},{"id":"2502.01481","title":"Intrinsic Entropy of Context Length Scaling in LLMs","created":"2025-02-03","cited_by_count":14,"area":null},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2402.05164","title":"A Resource Model For Neural Scaling Law","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2408.16947","title":"An Empirical Study of Scaling Laws for Transfer","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"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":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2312.02264","title":"Scaling Laws in Jet Classification","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2601.13308","title":"Scaling laws for amplitude surrogates","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2310.02258","title":"A Neural Scaling Law from Lottery Ticket Ensembling","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2511.02767","title":"Dynamic Reflections: Probing Video Representations with Text Alignment","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2111.08014","title":"Tensor network to learn the wavefunction of data","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2503.01314","title":"Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2511.12791","title":"Optimal Look-back Horizon for Time Series Forecasting in Federated Learning","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2605.24316","title":"Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.19781","title":"Towards Engineering Scaling Laws with Pretraining Data Composition","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2411.10622","title":"KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2602.02593","title":"Effective Frontiers: A Unification of Neural Scaling Laws","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.07363","title":"Benchmark Shadows: Data Alignment, Parameter Footprints, and Generalization in Large Language Models","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.16842","title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.28983","title":"The Hamilton-Jacobi Theory of Deep Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.01302","title":"Structure and Scale in Simplicial Sequence Modelling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.26617","title":"Sketched Linear Contrastive Learning: Approximation, Optimization, and Statistical Scaling","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}