I am a postdoctoral researcher at the Tübingen AI center at the University of Tübingen, Germany, working with Jakob Macke.
Generally, I aim to build machine learning tools for scientific discovery. I try to understand machine learning algorithms through theory and empirical observations to then build rigorously grounded methods to solve scientific problems. Specifically, I am interested in
- scientific and mechanistic model discovery,
- simulation-based inference,
- foundation models for scientific data,
- modeling of dynamical systems.
On the applied side, I develop deep models for (1) systems pharmacology models, with focus on chronic kidney disease,and (2) for automated evaluation of electrocardiogram (ECG) recordings.
Background
- Currently: Postdoctoral fellow at Tübingen University, Germany.
- 2024: Ph.D. in deep learning at Uppsala University, Sweden.
- 2019: M.Sc. in systems and control at TU Delft, the Netherlands.
- 2015: B.Sc. in aerospace engineering at DHBW, Germany.
- 1994: born.
Latest news
September 18, 2025, NeurIPS paper: Our SBI foundation model paper using TabPFN got accepted to NeurIPS 2025. See you all in San Diego!
arXiv Code
September 12, 2025, New Preprint: A follow up work on our ECG based heart attack detection model, proposing direct acute occlusion myocardial infarction (OMI) identification and localization from ECGs rather than the STEMI-NSTEMI paradigm.
arXiv
April 25, 2025, New Preprint: My first paper on SBI. We integrate the latest foundation model for tabular data, TabPFN, for the use in Bayesian inference, specifically for SBI.
arXiv Code
Dezember 11, 2024, SBI hackathon: We organize a hackathon on the SBI toolbox that we maintain. The hackathon is remote and on-site at the University of Tübingen during 17-21 March 2025.
SBI website details
All news can be found here