Elamur Research⌕
☰
home / authors / Naomi Saphra

Naomi Saphra

Naomi Saphra has 2 papers in our library, in 2019–2024, most of them on Language models & pretraining; often with Adam Lopez, Benjamin L. Edelman, Eran Malach.

2 papers in our library · 2019–2024

OpenAlex · ORCID · h-index 10 · 45 works · 724 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 470 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #7988

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Boston UniversityBoston · United States2025–2026 · 2 papersEmployment since 2026 · Assistant Professor, Faculty of Computing and Data Sciencecurrent🎓Harvard UniversityCambridge · United States2022–2026 · 13 papersEmployment 2023–2026 · Kempner Research Fellow, Kempner Institute for the Study of Natural and Artificial Intelligence🎓University of EdinburghEdinburgh · United Kingdom2016–2021 · 10 papersEducation until 2021 · PhD, informatics🎓Johns Hopkins UniversityBaltimore · United States2013–2015 · 3 papersEducation until 2015 · MEng, computer science🎓New York UniversityNew York · United States2021–2023 · 2 papersEmployment 2021–2023 · Postdoctoral Researcher, Center for Data Science🎓University of CambridgeCambridge · United Kingdom2020–2021 · 2 papers🎓Carnegie Mellon UniversityPittsburgh · United States2012–2013 · 2 papersEducation until 2013 · BS, computer science🏢GoogleMountain View · United States2019–2021 · 1 paperEmployment 2019–2020 · Research intern
🏛️MosaicMLNew York · United States2021–2023Employment 2021–2023 · Consultant

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 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

20241 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Understanding Learning Dynamics Of Language Models with SVCCA (2019 · 107 citations)
    Earlier work showed that neural networks implicitly capture linguistic categories, but not how those encodings develop during training.
  2. Transcendence: Generative Models Can Outperform The Experts That Train Them (2024 · 12 citations)
    Models trained with cross-entropy learn to mimic the distribution of their training data. This suggests they cannot outperform the humans who produced that data. The authors examine this assumption and define "transcendence" as a generative model earning higher reward than every expert behind its training set.

All works

11 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. State-of-the-art generalisation research in NLP: A taxonomy and review ↗arXiv:2210.03050 · Nat Mach Intell 5, 1161-1174 (2023) · no summary yetDieuwke Hupkes et al.2022 · 120 citations
  2. Understanding Learning Dynamics Of Language Models with SVCCAConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Naomi Saphra, Adam Lopez2019 · 107 citations
  3. Understanding Objects in Detail with Fine-Grained Attributes ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAndrea Vedaldi et al.2014 · 92 citations
  4. The MultiBERTs: BERT Reproductions for Robustness Analysis ↗arXiv:2106.16163 · no summary yetThibault Sellam et al.2021 · 57 citations
  5. Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ↗arXiv (Cornell University) · no summary yetAngelica Chen et al.2023 · 49 citations
  6. Linear Connectivity Reveals Generalization Strategies ↗arXiv (Cornell University) · no summary yetJeevesh Juneja et al.2022 · 32 citations
  7. First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models ↗Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yetNaomi Saphra et al.2024 · 18 citations
  8. AMRICA: an AMR Inspector for Cross-language Alignments ↗Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · no summary yetNaomi Saphra, Adam Lopez2015 · 16 citations
  9. Transcendence: Generative Models Can Outperform The Experts That Train ThemConference on Neural Information Processing Systems (NeurIPS)Edwin Zhang, Vincent Zhu, Naomi Saphra, et al.2024 · 12 citations
  10. Latent State Models of Training Dynamics ↗arXiv (Cornell University) · no summary yetMichael Y. Hu et al.2023 · 7 citations
  11. Towards a detailed understanding of objects and scenes in natural images ↗INRIA a CCSD electronic archive server · no summary yetMatthew B. Blaschko et al.2012 · 2 citations

 Co-authors here

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

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 470 times (of the 149,439 papers whose bibliographies we read); 88 citing papers with a page here →.

Updated

↑ back to top

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