Teaching

Seminar: Mechanistic Interpretability

Seminar, TU Dortmund, 2026

Neural networks are increasingly integrated into real-world decisions and everyday tasks. Current frontier models are extremely powerful, but also large and complex. We can precisely describe their architecture, control their inputs, and observe their outputs. However, it remains largely unknown what happens as data moves through dozens of layers and billions of weights. This seminar discusses the question Can we look inside a neural network and actually explain, step by step, why it gave a particular output?

Seminar: Adaptation and Fine-Tuning of Foundation Models

Seminar, TU Dortmund, 2026

Foundation models are pretrained once on broad and heterogeneous data distributions; however, real-world deployment typically requires reliable performance in narrow, specialized domains. This seminar will discuss fundamental and recent approaches to address the following question: How do we specialize foundation models to a target domain under computational and data constraints?

Seminar: Tabular Machine Learning

Seminar, TU Dortmund, 2025

Tabular data is everywhere and often at the core of data science tasks, from healthcare to e-commerce and the natural sciences. Yet it comes with unique challenges and research questions for machine learning:

Seminar: (Auto-)ML for tabular data

Seminar, University of Tübingen, 2024

What is tabular data? And which model would you use for it? Why is tabular data challenging for machine learning? And how would you compare learning approaches on tabular data?