About me
I am a senior-year Doctoral Researcher in Computational Psychiatry in the Institute for Human-Centered AI at Helmholtz Munich and the Ludwig-Maximilians-University Munich under the supervison of Dr. Eric Schulz.
My research spans two main areas. First, I develop reliable computational models of human decision-making and study how these processes relate to symptoms of anxiety and depression. Second, I investigate how Large Language Models (LLMs) can be used to understand and support mental health. This work includes examining how anxious responding can be induced in LLMs, and building an LLM system capable of supervising and improving Cognitive Behavioural Therapy.
Through this work I have become very interested in AI Safety and findings ways to optimally evaluate LLMs in an effort to predict and prevent catastrophic consequences of emerging AI technologies. I am eargerly learning about AI alignment techniques as well as AI evaluations and stress-testing.
More broadly, I am committed to finding a way that research can have a real impact on people’s well-being.
Next to my research, I enjoy bouldering, hiking, dancing, reading, sailing and generally spending time outdoors.
News
- July 2025: The paper A foundation model to predict and capture human cognition was accepted for publication in Nature.
- July 2025: I am attending the third edition of the Computational Psychiatry Conference in Tuebingen and presenting a poster on a proof-of-concept study of the usage of open source LLMs in psychological talking therapy
- June 2025: Our paper on the reliability and validity of exploration task parameters was accepted for publication in Scientific Reports. You can find the full article here
- October 2024: A new preprint, Centaur: a foundation model of human cognition, is out.