Stephan T. Wäldchen

IOL Lab @ TUB and ZIB

Zuse Institute Berlin

TU Berlin

Researcher in AI Interpretabilty and Mathematics of Deep Neural Networks. Researcher in the Robust and Explainable Learning group at IOL Lab at Zuse Institute Berlin.

Currently also writing a Musical♫♫!

Generally interested in AI safety and specifically building a theory of neural network interpretability. My agenda. In case you want to hire me: My record.

news

Jan 20, 2024	Our paper about Merlin-Arthur Classifiers got accepted to AISTATS :)
Apr 1, 2023	~~We are looking for a new PhD student in AI Interpretability~~ (filled!)
May 12, 2022	Our paper go accepted as long-form talk at ICML 2022 (top 2% of papers)
Mar 9, 2021	Defended my PhD today! Took a long time, but I got it. :D