🧑‍🔬 Yair Carmon

🏛️ Affiliations

🎓Tel Aviv UniversityTel Aviv · Israel2020–2026 · 19 papersEmployment since 2020current🎓Stanford UniversityStanford · United States2016–2021 · 12 papersEducation until 2020🎓Technion – Israel Institute of TechnologyHaifa · Israel2008–2016 · 9 papersEducation until 2014

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)

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022 · 474 citations)
   When fine-tuning a large pre-trained network, the usual practice is to run a hyperparameter sweep, keep the single checkpoint that scores best on validation data, and discard the rest.
2. Resolving Discrepancies in Compute-Optimal Scaling of Language Models (2024 · 14 citations)
   Two influential compute-optimal scaling laws disagree. Kaplan et al. found that, as compute grows, model size should grow faster than training tokens. Hoffmann et al. ("Chinchilla") found that tokens per parameter should stay roughly fixed. Porian et al. investigate why. They reproduce the Kaplan-style result with…

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

9 co-authors with a page, the most papers together first.

• Ludwig Schmidt ×2
• Mitchell Wortsman ×2
• Ali Farhadi
• Ari S. Morcos
• Gabriel Ilharco
• Jenia Jitsev
• Rebecca Roelofs
• Samir Yitzhak Gadre
• Simon Kornblith

🔗 Cited by

Papers of our library cite their works 552 times (of the 140,884 papers whose bibliographies we read); 39 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yair-carmon/