{"topic":{"slug":"scaling-laws","name":"Scaling Laws & Compute-Optimal Training","domain":"ai","description":"Empirical laws relating loss and capability to parameters, data and compute; data-constrained and synthetic-data scaling; emergent abilities and their measurement.","keywords":["scaling laws","compute-optimal","emergent abilities","data-constrained","synthetic data","scaling law"],"paper_count":205,"latest_published":"2026-10-27","url":"https://space-kitty.com/topics/scaling-laws","api_url":"https://space-kitty.com/api/v1/topics/scaling-laws"},"dossier":null,"top_papers":[{"id":"arxiv:2001.08361","kind":"preprint","title":"Scaling Laws for Neural Language Models","authors":["Jared Kaplan A","Sam McCandlish","Tom Henighan","Brown, Tom B.","Benjamin Chess","Rewon Child"],"author_count":10,"year":2020,"published":"2020-01-23","venue":null,"cited_by":1751,"doi":null,"arxiv_id":"2001.08361","nct_id":null,"source_url":"http://arxiv.org/abs/2001.08361","archive_url":"https://space-kitty.com/papers/arxiv:2001.08361"},{"id":"doi:10.1111/modl.12924","kind":"article","title":"Twenty‐first century technologies and language education: Charting a path forward","authors":["Richard Kern"],"author_count":1,"year":2024,"published":"2024-05-08","venue":"Modern Language Journal","cited_by":82,"doi":"10.1111/modl.12924","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1111/modl.12924","archive_url":"https://space-kitty.com/papers/doi:10.1111/modl.12924"},{"id":"arxiv:2212.07143","kind":"article","title":"Reproducible scaling laws for contrastive language-image learning","authors":["Mehdi Cherti","Romain Beaumont","Ross Wightman","Mitchell Wortsman","Gabriel Ilharco","Cade Gordon"],"author_count":9,"year":2022,"published":"2022-12-14","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 2818-2829","cited_by":672,"doi":"10.1109/cvpr52729.2023.00276","arxiv_id":"2212.07143","nct_id":null,"source_url":"https://arxiv.org/abs/2212.07143","archive_url":"https://space-kitty.com/papers/arxiv:2212.07143"},{"id":"doi:10.1021/acsphyschemau.4c00004","kind":"review","title":"The Potential of Neural Network Potentials","authors":["Timothy T. Duignan"],"author_count":1,"year":2024,"published":"2024-03-21","venue":"ACS Physical Chemistry Au","cited_by":64,"doi":"10.1021/acsphyschemau.4c00004","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1021/acsphyschemau.4c00004","archive_url":"https://space-kitty.com/papers/doi:10.1021/acsphyschemau.4c00004"},{"id":"doi:10.1093/jlb/lsz013","kind":"article","title":"Integrating artificial intelligence into health care through data access: can the GDPR act as a beacon for policymakers?","authors":["Mélanie Bourassa Forcier","Hortense Gallois","Siobhan M. Mullan","Yann Joly"],"author_count":4,"year":2019,"published":"2019-08-17","venue":"Journal of Law and the Biosciences","cited_by":135,"doi":"10.1093/jlb/lsz013","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1093/jlb/lsz013","archive_url":"https://space-kitty.com/papers/doi:10.1093/jlb/lsz013"},{"id":"doi:10.1017/cfl.2024.16","kind":"article","title":"The architecture of language: Understanding the mechanics behind LLMs","authors":["Andrea Filippo Ferraris","Davide Audrito","Luigi Di","Cristina Poncibò"],"author_count":4,"year":2025,"published":"2025-01-01","venue":"Cambridge Forum on AI Law and Governance","cited_by":34,"doi":"10.1017/cfl.2024.16","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1017/cfl.2024.16","archive_url":"https://space-kitty.com/papers/doi:10.1017/cfl.2024.16"},{"id":"arxiv:2601.07372","kind":"preprint","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","authors":["Xin Cheng","Rui Tian","Wangding Zeng","Damai Dai","Qinyu Chen","Bingxuan Wang"],"author_count":21,"year":2026,"published":"2026-01-12","venue":null,"cited_by":21,"doi":null,"arxiv_id":"2601.07372","nct_id":null,"source_url":"https://doi.org/10.48550/arxiv.2601.07372","archive_url":"https://space-kitty.com/papers/arxiv:2601.07372"},{"id":"doi:10.3389/frai.2024.1490698","kind":"article","title":"Language writ large: LLMs, ChatGPT, meaning, and understanding","authors":["Stevan R. Harnad"],"author_count":1,"year":2025,"published":"2025-02-12","venue":"Frontiers in Artificial Intelligence","cited_by":29,"doi":"10.3389/frai.2024.1490698","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3389/frai.2024.1490698","archive_url":"https://space-kitty.com/papers/doi:10.3389/frai.2024.1490698"},{"id":"arxiv:2010.14701","kind":"preprint","title":"Scaling Laws for Autoregressive Generative Modeling","authors":["Tom Henighan","Jared Kaplan","Mor Katz","Mark Chen","Christopher Hesse","Jacob Jackson"],"author_count":19,"year":2020,"published":"2020-10-28","venue":null,"cited_by":150,"doi":null,"arxiv_id":"2010.14701","nct_id":null,"source_url":"https://arxiv.org/abs/2010.14701","archive_url":"https://space-kitty.com/papers/arxiv:2010.14701"},{"id":"arxiv:2102.01293","kind":"preprint","title":"Scaling Laws for Transfer","authors":["Danny Hernandez","Jared Kaplan A","Tom Henighan","Sam McCandlish"],"author_count":4,"year":2021,"published":"2021-02-02","venue":null,"cited_by":51,"doi":null,"arxiv_id":"2102.01293","nct_id":null,"source_url":"http://arxiv.org/abs/2102.01293","archive_url":"https://space-kitty.com/papers/arxiv:2102.01293"},{"id":"arxiv:2305.02309","kind":"preprint","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","authors":["Erik Nijkamp","Hayashi, Hiroaki","Caiming Xiong","Silvio Savarese","Yingbo Zhou"],"author_count":5,"year":2023,"published":"2023-05-03","venue":null,"cited_by":35,"doi":null,"arxiv_id":"2305.02309","nct_id":null,"source_url":"http://arxiv.org/abs/2305.02309","archive_url":"https://space-kitty.com/papers/arxiv:2305.02309"},{"id":"arxiv:2202.13852","kind":"preprint","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","authors":["Menglin Yang","Min Zhou","Tong Zhang","Jiahong Liu","Zhihao Li","Lujia Pan"],"author_count":8,"year":2022,"published":"2022-02-28","venue":null,"cited_by":33,"doi":null,"arxiv_id":"2202.13852","nct_id":null,"source_url":"http://arxiv.org/abs/2202.13852","archive_url":"https://space-kitty.com/papers/arxiv:2202.13852"},{"id":"arxiv:2305.13035","kind":"article","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","authors":["Ibrahim Alabdulmohsin","Xiaohua Zhai","Alexander Kolesnikov","Lucas Beyer"],"author_count":4,"year":2023,"published":"2023-05-22","venue":"37th Conference on Neural Information Processing Systems (NeurIPS 2023)","cited_by":13,"doi":"10.52202/075280-0722","arxiv_id":"2305.13035","nct_id":null,"source_url":"https://arxiv.org/abs/2305.13035","archive_url":"https://space-kitty.com/papers/arxiv:2305.13035"},{"id":"arxiv:2402.07043","kind":"preprint","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","authors":["Elvis Dohmatob","Yunzhen Feng","Pu Yang","Francois Charton","Julia Kempe"],"author_count":5,"year":2024,"published":"2024-02-10","venue":"ICML 2024","cited_by":20,"doi":null,"arxiv_id":"2402.07043","nct_id":null,"source_url":"https://arxiv.org/abs/2402.07043","archive_url":"https://space-kitty.com/papers/arxiv:2402.07043"},{"id":"doi:10.1093/schbul/sbx040","kind":"article","title":"Thoughts About Disordered Thinking: Measuring and Quantifying the Laws of Order and Disorder","authors":["Brita Elvevåg","Peter W. Foltz","Mark Rosenstein","Ramon Ferrer‐i‐Cancho","Simon De Deyne","Eduardo Mizraji"],"author_count":7,"year":2017,"published":"2017-03-07","venue":"Schizophrenia Bulletin","cited_by":31,"doi":"10.1093/schbul/sbx040","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1093/schbul/sbx040","archive_url":"https://space-kitty.com/papers/doi:10.1093/schbul/sbx040"}],"newest_papers":[{"id":"arxiv:2610.36911","kind":"preprint","title":"Developing a Speech Language Model for Basque","authors":["Andoni Sudupe","Inma Hernaez","Ander Arriandiaga","Christoforos Souganidis","Ibon Saratxaga","Eva Navas"],"author_count":6,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36911","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36911","archive_url":"https://space-kitty.com/papers/arxiv:2610.36911"},{"id":"arxiv:2610.37105","kind":"preprint","title":"Text Generation in Low-Resource Languages Using Human-Curated Vocabularies","authors":["Michael Christlambert Sinanta","Muhammad Dehan Al Kautsar","Amanda Nurul Izzah","Thanh-Nhi Nguyen","Phan Phuong Mai Chau","Zheng Wei Lim"],"author_count":7,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37105","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37105","archive_url":"https://space-kitty.com/papers/arxiv:2610.37105"},{"id":"arxiv:2610.37648","kind":"preprint","title":"Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis","authors":["Andrew Szot","Samira Abnar","Omar Attia","Abbas Kazerouni","Michael Kirchhof","Cheng-Yu Hsieh"],"author_count":8,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37648","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37648","archive_url":"https://space-kitty.com/papers/arxiv:2610.37648"},{"id":"arxiv:2610.34875","kind":"preprint","title":"RubriX: A Fast, Fine-Tunable Non-Autoregressive Rubric Judge","authors":["Balamurugan Paramasivam","Sudalai Rajkumar"],"author_count":2,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.34875","nct_id":null,"source_url":"https://arxiv.org/abs/2610.34875","archive_url":"https://space-kitty.com/papers/arxiv:2610.34875"},{"id":"arxiv:2610.35029","kind":"preprint","title":"Synthetic Child-Adult Interactions Are Not Developmentally Plausible","authors":["Bastian Bunzeck","Francesca Padovani"],"author_count":2,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.35029","nct_id":null,"source_url":"https://arxiv.org/abs/2610.35029","archive_url":"https://space-kitty.com/papers/arxiv:2610.35029"},{"id":"arxiv:2610.35163","kind":"preprint","title":"Sequential versus fully conditional specification for tree-based synthesis of health data","authors":["R{é}my Chapelle","Mohammed Sedki"],"author_count":2,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.35163","nct_id":null,"source_url":"https://arxiv.org/abs/2610.35163","archive_url":"https://space-kitty.com/papers/arxiv:2610.35163"},{"id":"arxiv:2610.35164","kind":"preprint","title":"Accelerating SO(2)-Equivariant Materials Models through Low-Precision Emulation","authors":["Denghui Lu","Alexander Maeder","Alexandros Nikolaos Ziogas","Mathieu Luisier","Manasa Kaniselvan"],"author_count":5,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.35164","nct_id":null,"source_url":"https://arxiv.org/abs/2610.35164","archive_url":"https://space-kitty.com/papers/arxiv:2610.35164"},{"id":"arxiv:2610.35514","kind":"preprint","title":"Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks","authors":["Taishi Watanabe","Ryo Karakida","Jun-nosuke Teramae"],"author_count":3,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.35514","nct_id":null,"source_url":"https://arxiv.org/abs/2610.35514","archive_url":"https://space-kitty.com/papers/arxiv:2610.35514"},{"id":"arxiv:2610.36110","kind":"preprint","title":"Dirichlet Process Mixtures within Semiparametric Bayesian Networks: A Novel Conditional Density Estimation Approach","authors":["Victor Alejandre","Pedro Larrañaga","Concha Bielza"],"author_count":3,"year":2026,"published":"2026-10-26","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.36110","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36110","archive_url":"https://space-kitty.com/papers/arxiv:2610.36110"},{"id":"arxiv:2610.36195","kind":"preprint","title":"Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs","authors":["Kartik Jangra","Atharva Gawane","Siddharth Pulipaka","Hemachandran Karah","Raj Dabre"],"author_count":5,"year":2026,"published":"2026-10-26","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36195","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36195","archive_url":"https://space-kitty.com/papers/arxiv:2610.36195"}],"related_topics":[{"slug":"llm-architectures","name":"LLM Architectures & Pretraining","api_url":"https://space-kitty.com/api/v1/topics/llm-architectures"},{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","api_url":"https://space-kitty.com/api/v1/topics/reasoning-models"},{"slug":"alignment-safety","name":"AI Alignment & Safety","api_url":"https://space-kitty.com/api/v1/topics/alignment-safety"},{"slug":"interpretability","name":"Mechanistic Interpretability","api_url":"https://space-kitty.com/api/v1/topics/interpretability"},{"slug":"ai-agents","name":"LLM Agents & Tool Use","api_url":"https://space-kitty.com/api/v1/topics/ai-agents"},{"slug":"generative-multimodal","name":"Generative & Multimodal Models","api_url":"https://space-kitty.com/api/v1/topics/generative-multimodal"},{"slug":"efficient-ai","name":"Efficient Training & Inference","api_url":"https://space-kitty.com/api/v1/topics/efficient-ai"},{"slug":"ai-for-science","name":"AI for Science","api_url":"https://space-kitty.com/api/v1/topics/ai-for-science"},{"slug":"robotics-embodied","name":"Robot Learning & Embodied AI","api_url":"https://space-kitty.com/api/v1/topics/robotics-embodied"}],"premium":{"dossier":null,"research_pack":{"url":"https://space-kitty.com/api/v1/topics/scaling-laws/pack","price_usd":"0.20"}},"more":"https://space-kitty.com/api/v1/topics/scaling-laws/papers?sort=top&limit=100"}