- Interpretability Guarantees with Merlin-Arthur ClassifiersIn Artificial Intelligence and Statistics (AISTATS), 2024
- Extending Merlin-Arthur Classifiers for Improved InterpretabilityIn Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium, co-located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023), Jul 20236-page extended abstract. Awarded Best Doctoral Proposal at xAI-2023.
- Robustness of Hybrid Discriminative-Generative ModelsTechnical University of Berlin, Jul 2022
- Modeling and Simulation of Convective Flows in the Outer Earth’s Core using the Finite Element MethodTechnical University of Berlin, Jul 2018