I am a doctoral student in the Learning & Adaptive Systems Group at ETH Zurich supervised by Prof. Andreas Krause and Dr. Katja Hofmann. I am part of the Microsoft Swiss Joint Research Center, and an associated PhD student of the ETH AI Center. During my PhD, I was an intern at DeepMind and at the Center for Human-Compatible AI, UC Berkeley. Previously, I received a master’s degree in Data Science from ETH Zurich and a bachelor’s degree in physics from University of Cologne.

Research

My research aims to build safe, robust, and interpretable artificial intelligence (AI). Currently, I am primarily working on Reinforcement Learning from Human Feedback (RLHF) which I think is a key ingredient for building safe AI. My work in this context has two goals: first, making RLHF more sample efficient via active learning, and second, using constraint models in addition to reward models to specify tasks, particularly in contexts where safety is a critical concern. Recently, my interests have expanded to other areas including interpretability, specifically mechanistically understanding neural network models, and red-teaming models before and during deployment. Through my work, I strive to ensure AI models we deploy today and in the coming years are safe, robust, and transparent.

News

• May 2023: New preprint on arXiv: “Learning Safety Constraints from Demonstrations with Unknown Rewards”
• January 2023: New preprint on arXiv: “Tracr: Compiled Transformers as a Laboratory for Interpretability”
• December 2022: Our paper “Red-Teaming the Stable Diffusion Safety Filter” won a best paper award at the NeurIPS ML Safety workshop 2022.
• September 2022: Our paper “Active Exploration for Inverse Reinforcement Learning” was accepted to NeurIPS 2022.
• July 2022: Our paper “Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning” was accepted to the Communication in Human-AI Interaction Workshop at IJCAI-ECAI-2022.
• July 2022: Our paper “Active Exploration for Inverse Reinforcement Learning” was accepted to ReALML @ ICML2022.
• June 2022: I will spend the summer as a research scientist intern in DeepMind’s Scalable Alignment team in London.
• May 2022: Our paper “Interactively Learning Preference Constraints in Linear Bandits” was accepted to ICML 2022. I’m looking forward to attending the conference in person.