Sören Mindermann

Sören Mindermann

Research Affiliate

Sören is a Research Affiliate at the Oxford Martin AI Governance Initiative. He works with Yoshua Bengio and Mila as the Scientific Lead of the first International AI Safety Report, a project backed by 33 nations and intergovernmental organizations.

His research in machine learning covers risk management, safety methods and evaluations, LLM honestyhealth applications, and data selection for large-scale deep learning. Across these areas, his publications as lead author have been covered by TV and newspapers like The GuardianTime, etc, while others have been cited by ministers or incorporated into national legislation.

Previously, Sören completed his PhD in machine learning at the University of Oxford under Yarin Gal funded by Google DeepMind, and worked on learning human preferences and game-theoretical machine learning with David Duvenaud and Roger Grosse at Toronto’s Vector Institute and UC Berkeley, and with the Centre for the Governance of AI at Oxford. He has completed additional degrees in machine learning (UCL), mathematics (Amsterdam) and Future Planet Studies (Amsterdam).