About

I’m a dual-background researcher who will start an appointment as assistant professor for medical AI at ETH Zurich, starting this fall (see announcement). Prior to this, I was a postdoctoral researcher at Stanford University in the group of Prof. Jure Leskovec. Previously, I completed my PhD at ETH Zurich in the Machine Learning and Computational Biology Lab of Prof. Karsten Borgwardt, and my MD and medical training at the University of Basel. Here, you can find my CV.
During my PhD, I developed machine learning models for medical time series and developed methods for representation learning, spiked with topological data analysis. Since joining Stanford CS for my postdoc, I have been exploring novel frontiers of medical AI involving zero-shot and few-shot learning, knowledge injection, multimodal medical reasoning, and large pre-trained models.
My current research focuses on developing flexible and reusable pre-trained machine learning (ML) models for multimodal biomedical data involving time series, graphs, images, and text.
Concretely, my vision is to develop generalist models for biomedicine (see figure excerpt below), i.e. large, pre-trained biomedical foundation models that can flexibly ingest multiple modalities, solve dynamically specified tasks (zero-shot or few-shot) and reason over (and retrieve from) structured and editable biomedical knowledge sources.