About & Contact

Hi, I’m Frank! I’m an AI Researcher at Aleph Alpha Research, where I work on the evaluation of large language models, e.g., with our eval-framework.

Before joining Aleph Alpha, I was a postdoctoral researcher at the University of Tübingen in the Methods of Machine Learning group, led by Philipp Hennig. There, my research focused on efficient and user-friendly training methods for machine learning, in particular on eliminating tedious hyperparameters (e.g., learning rates, schedules) to automate neural network training. A key aspect of my work was designing rigorous and meaningful benchmarks for training methods, such as AlgoPerf. I also served as a chair of the Algorithms working group at MLCommons.

I earned my PhD in Computer Science from the University of Tübingen, supervised by Philipp Hennig, as part of the IMPRS-IS (International Max Planck Research School for Intelligent Systems). Before that, I studied Simulation Technology (B.Sc., M.Sc.) at the University of Stuttgart and Industrial and Applied Mathematics (M.Sc.) at TU/e Eindhoven. My master’s thesis, supervised by Maxim Pisarenco and Michiel Hochstenbach, explored novel preconditioners for structured Toeplitz matrices. This thesis was conducted at ASML (Eindhoven), a company specializing in lithography systems for the semiconductor industry.