Scholar
Sören Mindermann
Google Scholar ID: slBPlrQAAAAJ
University of Oxford, OATML
Citations & Impact
Citations
4,312
H-index
24
i10-index
25
Publications
20
Co-authors
8
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications as lead author have been covered by The Guardian, Time, etc., while others have been discussed by ministers or incorporated into national legislation; co-authored the International AI Safety Report and the Interim Report on the Safety of Advanced AI.
Research Experience
- Scientific Lead at Mila, leading the International AI Safety Report; previously completed PhD studies at the University of Oxford and conducted research at the Vector Institute and UC Berkeley.
Education
- PhD in ML from the University of Oxford, supervised by Yarin Gal and funded by Google DeepMind; worked on learning human preferences and game-theoretical machine learning with David Duvenaud and Roger Grosse at Toronto’s Vector Institute and UC Berkeley; studied machine learning (UCL), maths (Amsterdam) and Future Planet Studies (Amsterdam).
Background
- Research interests include risk management, LLM honesty, health applications, and data selection for large-scale deep learning. Currently the Scientific Lead of the International AI Safety Report, a project backed by 33 nations and intergovernmental organizations.
