Andrew Poulton
Andrew Poulton has 2 papers in our library, in 2022–2023, most of them on Language models & pretraining; often with Anthony Hartshorn, Diana Liskovich, Elvis Saravia.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 333 times in our library · ⭐ Paper Stars ranking: #3975
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work
🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work
Works by year
2020s
Papers
- Galactica: A Large Language Model for Science (2022 · 570 citations)
Scientific papers and data are accumulating faster than anyone can read or organize them. Search engines do not structure this knowledge. They only point to secondary resources such as encyclopedias and databases, which depend on expensive human curation. Meta AI's Galactica takes a different route: a family of large… - A Theory on Adam Instability in Large-Scale Machine Learning (2023 · 15 citations)
Very large language models sometimes show sudden loss spikes during training, and the cause has not been explained.
Co-authors here
- Anthony Hartshorn
- Diana Liskovich
- Elvis Saravia
- Guillem Cucurull
- Igor Molybog
- Moya Chen
- Naman Goyal
- Peter Albert
- Punit Singh Koura
- Robert Stojnic
- Sharan Narang
- Thomas Scialom
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/andrew-poulton/