🧑‍🔬 Mark Rowland

🏛️ Affiliations

🏢GoogleMountain View · United States2019–2026 · 4 paperscurrent🏢Google DeepMindLondon · United Kingdom2018–2025 · 16 papersEmployment since 2018🎓University of CambridgeCambridge · United Kingdom2015–2019 · 16 papersEducation until 2018🎓University of LondonLondon · United Kingdom2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

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

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A General Theoretical Paradigm to Understand Learning from Human Preferences (2023 · 263 citations)
   This paper by researchers at Google DeepMind provides a theoretical foundation for methods that train language models from human preferences.
2. Nash Learning from Human Feedback (2023 · 32 citations)
   Standard RLHF reduces pairwise human judgments to a scalar reward, typically through a Bradley-Terry model, and then optimizes the LLM against that score.

🤝 Co-authors here

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

• Daniele Calandriello ×2
• Michal Valko ×2
• Mohammad Gheshlaghi Azar ×2
• Rémi Munos ×2
• Andrea Michi
• Bilal Piot
• Daniel Guo
• Matthieu Geist
• Sertan Girgin

🔗 Cited by

Papers of our library cite their works 280 times (of the 149,439 papers whose bibliographies we read); 75 citing papers with a page here →.

Updated 3 November 2026

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