--- title: "Joel Hestness — author profile and papers" description: "Joel Hestness, Cerebras Systems: 2 papers on Elamur Research (2017–2024), h-index 13 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/joel-hestness/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/joel-hestness/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Joel Hestness # Joel Hestness Joel Hestness has 2 papers in our library, in 2017–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Biswajit Mishra](https://md.research.elamur.ai/free/en/authors/biswajit-mishra/), [Bokang Jia](https://md.research.elamur.ai/free/en/authors/bokang-jia/), [Greg Diamos](https://md.research.elamur.ai/free/en/authors/greg-diamos/). 2 papers in our library · 2017–2024 [OpenAlex](https://openalex.org/A5089825123) · [ORCID](https://orcid.org/0000-0001-6920-0906) · [**h-index 13**](https://openalex.org/authors/A5089825123) · [69 works](https://openalex.org/works?filter=author.id:A5089825123) · [6,522 citations](https://openalex.org/works?filter=author.id:A5089825123&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/joel-hestness/#papers) · [🔗 200 citations in our library](https://md.research.elamur.ai/free/en/authors/joel-hestness/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Star rank #2944](https://md.research.elamur.ai/free/en/paper-stars/page/30/#star-2944) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Joel+Hestness) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Joel+Hestness) · [dblp](https://dblp.org/search?q=Joel+Hestness) · [ACL Anthology](https://aclanthology.org/search/?q=Joel+Hestness) ## Affiliations [🏢**Cerebras Systems** Sunnyvale 2019–2026 · 12 papers*current*](https://ror.org/040zz8080) · [🏢**Baidu** Beijing · China 2017–2019 · 6 papers](https://md.research.elamur.ai/free/en/companies/baidu/) · [🎓**The University of Texas at Austin** Austin · United States 2010–2012 · 6 papers](https://md.research.elamur.ai/free/en/universities/the-university-of-texas-at-austin/) · [🎓**University of Wisconsin–Madison** Madison · United States 2014–2015 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-wisconsin-madison/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Language models & pretraining (1)](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/gosal-2024-bilingual-adaptation-monolingual-foundation-models/) ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/hestness-2017-deep-learning-scaling-predictable-empirically/) ## Papers The most cited first (OpenAlex and our library). 1. **[Deep Learning Scaling is Predictable, Empirically](https://md.research.elamur.ai/free/en/papers/hestness-2017-deep-learning-scaling-predictable-empirically/)** *(2017 · 497 citations)* Practitioners widely assume that more data and bigger models improve accuracy, but there was no reliable way to forecast how much gain a given increase in training data would bring. 2. **[Bilingual Adaptation of Monolingual Foundation Models](https://md.research.elamur.ai/free/en/papers/gosal-2024-bilingual-adaptation-monolingual-foundation-models/)** *(2024 · 7 citations)* English-dominant open LLMs such as Llama 2 handle other languages poorly. Training a bilingual model from scratch is costly and tends to give weaker English. Adapting an existing model brings its own problems: it can forget English, and its English-centric tokenizer splits foreign text into many pieces. The authors… ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 co-authors with a page, the most papers together first. - [Biswajit Mishra](https://md.research.elamur.ai/free/en/authors/biswajit-mishra/) - [Bokang Jia](https://md.research.elamur.ai/free/en/authors/bokang-jia/) - [Greg Diamos](https://md.research.elamur.ai/free/en/authors/greg-diamos/) - [Gurpreet Gosal](https://md.research.elamur.ai/free/en/authors/gurpreet-gosal/) - [Heewoo Jun](https://md.research.elamur.ai/free/en/authors/heewoo-jun/) - [Neha Sengupta](https://md.research.elamur.ai/free/en/authors/neha-sengupta/) - [Rituraj Joshi](https://md.research.elamur.ai/free/en/authors/rituraj-joshi/) - [Sharan Narang](https://md.research.elamur.ai/free/en/authors/sharan-narang/) - [Sunil Kumar Sahu](https://md.research.elamur.ai/free/en/authors/sunil-kumar-sahu/) - [Yang Yang](https://md.research.elamur.ai/free/en/authors/yang-yang/) - [Yanqi Zhou](https://md.research.elamur.ai/free/en/authors/yanqi-zhou/) - [Zhiming Chen](https://md.research.elamur.ai/free/en/authors/zhiming-chen/) ## Cited by Papers of our library cite their works 200 times (of the 140,884 papers whose bibliographies we read); [42 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/joel-hestness/cited-by/).