I’m a Postdoctoral Fellow ‘25 at the ETH AI Center, mentored by Andreas Krause and Giorgia Ramponi. Before that, I was at The Alan Turing Institute and the University of Oxford, working with Marta Kwiatkowska and Lukasz Szpruch. From 2021 to 2024, I did my PhD at the University of Oslo, supervised by Christos Dimitrakakis, and previously studied Mathematics (BSc, MSc).
My research interests are in reinforcement learning and related areas, including reward learning, preference learning, and the intersection of machine learning with game theory. Currently, I’m particularly interested in applying these ideas to LLM training and alignment.
News
- 04/2025: The 2nd Edition of last year’s workshop on Models of Human Feedback for AI Alignment is taking place on July 18th at ICML 2025! Submission Deadline is May 25th!
- 03/2025: We released three new preprints on Strategyproof RLHF, Causal Imitation Learning and Multi-Agent RL.
- 12/2024: I’m visiting Haifeng Xu’s group at the University of Chicago. I’ll give a talk on Strategic Interactive Decision-Making on December 5th at the CS Department.
Selected Publications
Strategyproof Reinforcement Learning from Human Feedback [pdf]
Thomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska
NeurIPS 2025Strategic Linear Contextual Bandits [pdf]
Thomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu
NeurIPS 2024Environment Design for Inverse Reinforcement Learning [pdf]
Thomas Kleine Buening$^\star$, Victor Villin$^\star$, Christos Dimitrakakis
ICML 2024, Oral Presentation
You can reach me at thomas.kleinebuening@ai.ethz.ch.