- 'Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection' in Transactions on Machine Learning Research.
- 'Leveraging the Structure of Medical Data for Improved Representation Learning' submitted to ICML 2025 Workshop on FM4LS.
Research Experience
Worked at ETH spin-off upicto (later sold to Logitech) for 4 years; currently a Postdoc.
Education
Completed Master's in Electrical Engineering and Information Technology in 2014; started PhD in 2018 and successfully defended thesis on June 14, 2023.
Background
Research Interests: Applying machine learning models to the medical domain; interested in generative models of multiple data types; trying to understand how different modalities can be combined to efficiently model inference and generative paths.