Elamur Research⌕
☰
home / authors / Mary Phuong

Mary Phuong

Mary Phuong has 2 papers in our library, in 2023–2024, most of them on Evaluation & benchmarks; often with Elliot Catt, Matthew Aitchison, Matthew Rahtz.

2 papers in our library · 2023–2024

OpenAlex · h-index 8 · 15 works · 1,255 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 2,319 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7625

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

🏢Google DeepMindLondon · United Kingdom2026 · 2 paperscurrent🏢GoogleLondon · United Kingdom2026 · 1 papercurrent🎓Institute of Science and Technology AustriaKlosterneuburg · Austria2019–2023 · 5 papers

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 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksEngineering · 2 worksSafety Research · 2 worksSafety, Risk, Reliability and Quality · 2 worksSocial Sciences · 2 works

🧭 Topics 1Research subjects and languages the work is about.Evaluation & benchmarks · 2 works

 Works by year

2020s

20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Model evaluation for extreme risks (2023 · 104 citations)
    This position paper, from authors at Google DeepMind, OpenAI, Anthropic, GovAI and academic institutions, argues that general-purpose AI models may develop harmful abilities their creators never targeted.
  2. Evaluating Frontier Models for Dangerous Capabilities (2024 · 36 citations)
    Popular benchmarks measure broad skills such as coding or maths, and most safety tests check whether a model refuses harmful requests.

All works

3 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. Distillation-Based Training for Multi-Exit Architectures ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetMary Phuong, Christoph H. Lampert2019 · 189 citations
  2. Model evaluation for extreme risksarXiv:2305.15324Toby Shevlane, Sebastian Farquhar, Ben Garfinkel, et al.2023 · 104 citations
  3. Evaluating Frontier Models for Dangerous CapabilitiesarXiv:2403.13793Mary Phuong, Matthew Aitchison, Elliot Catt, et al.2024 · 36 citations

 Co-authors here

6 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 2,319 times (of the 149,439 papers whose bibliographies we read); 636 citing papers with a page here →.

Updated

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