{"total":21,"rows":[{"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":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2311.00522","title":"Text Rendering Strategies for Pixel Language Models","created":"2023-11-01","cited_by_count":22,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2306.14975","title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2510.03313","title":"Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2507.22543","title":"Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law","created":"2025-07-30","cited_by_count":3,"area":null},{"id":"2311.01358","title":"The Universal Statistical Structure and Scaling Laws of Chaos and Turbulence","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2508.04461","title":"Small transformer architectures for task switching","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2511.18517","title":"Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2604.23665","title":"HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.15613","title":"Toward LLMs Beyond English-Centric Development","created":"2026-05-15","cited_by_count":0,"area":null}],"next_cursor":null}