Publications: A paper about Merlin-Arthur Classifiers accepted to AISTATS (2024); A paper accepted as a long-form talk at ICML 2022 (top 2% of papers).
Research Experience
Researcher at IOL Lab, Zuse Institute Berlin, focusing on AI interpretability and the mathematics of deep neural networks.
Education
PhD, Technische Universität Berlin, defended in 2021. Advisor information not provided.
Background
Research interests: AI interpretability, mathematics of deep neural networks; Professional field: AI safety; Bio: Researcher in the Robust and Explainable Learning group at IOL Lab, Zuse Institute Berlin, and TU Berlin.