🧑‍🔬 Edward Hughes

🏛️ Affiliations

🎓Queen Mary University of LondonLondon · United Kingdom2006–2025 · 21 paperscurrent🏢Google DeepMindLondon · United Kingdom2019–2025 · 18 paperscurrent🏢GoogleLondon · United Kingdom2023–2025 · 3 paperscurrent🎓Royal Holloway University of LondonEgham · United Kingdom1992–2006 · 22 papers🎓Durham UniversityDurham · United Kingdom1951–1965 · 10 papers🏢GoogleMountain View · United States2018–2020 · 9 papers🎓Carleton UniversityOttawa · Canada1974–1998 · 5 papers🎓University of LondonLondon · United Kingdom2013 · 2 papers🎓University of PittsburghPittsburgh · United States1992–2002 · 2 papers🎓California State University, Long BeachLong Beach · United States1992–1995 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 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. Open-Endedness is Essential for Artificial Superhuman Intelligence (2024 · 14 citations)
   This position paper from Google DeepMind (ICML 2024) asks what an AI system would need in order to keep generating new knowledge by itself.
2. Training AI Scientists to Replicate Research (2026 · 2 citations)
   Replicating published results is central to trustworthy science, but it is hard for AI agents. Papers leave out details, current models are mostly trained on well-defined problems, and replication offers no single metric to optimise. The authors built Replica, an automatically constructed task space. In each task, a…

All works

4 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. Learning to Understand Goal Specifications by Modelling Reward ↗arXiv (Cornell University) · no summary yetDzmitry Bahdanau et al.2018 · 91 citations
2. Open-Endedness is Essential for Artificial Superhuman IntelligencearXiv:2406.04268Edward Hughes, Michael Dennis, Jack Parker-Holder, et al.2024 · 14 citations
3. Jointly Learning "What" and "How" from Instructions and Goal-States. ↗International Conference on Learning Representations · no summary yetDzmitry Bahdanau et al.2018 · 3 citations
4. Training AI Scientists to Replicate ResearcharXiv:2608.13331Damon Falck, Samer Sabri, Anja Surina, et al.2026 · 2 citations

🤝 Co-authors here

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

• Anja Surina
• Feryal Behbahani
• Kaloyan Aleksiev
• Louis Kirsch
• Tim Rocktaschel
• Tom Schaul

Venues

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

• International Conference on Learning Representations

🔗 Cited by

Papers of our library cite their works 62 times (of the 149,439 papers whose bibliographies we read); 18 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

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