teaching

I teach, mentor, and supervise students at TUM and Helmholtz Munich, mostly around machine learning, deep learning, and computational biology. Most of my graduate teaching takes place at the TUM School of Computation, Information and Technology (CIT) and is supervised through the Theis Lab.

Graduate Level

• Statistical Learning — SS24, WS25
  • Master’s course on fundamentals and modern applications of statistical learning theory.
  • Covers generalization, regularization, kernel methods, ensembles, and the link between classical statistics and modern self-supervised representation learning.
• Deep Learning Seminar — WS21 to WS24, SS26
  • Organizer since WS24, continuing as organizer for SS26.
  • Advanced seminar in which students read and present recent papers from top-tier conferences and journals (NeurIPS, ICLR, ICML, Nature) on representation learning, generative models, and foundation models.

Undergraduate Level

• Analysis for Informatics — WS23, WS24
  • Bachelor’s course covering the mathematical foundations of analysis for computer science students.

Tutoring

• Machine Learning / ML for Graphs and Sequential Data — 2020 to 2021
  • Tutor in the Data Analytics and Machine Learning Group at TUM. Supported the lecture, evaluated student projects and exams, and provided programming support.

Student Supervision

I supervise and co-supervise students working at the intersection of machine learning and single-cell / spatial omics. If you are interested in a Bachelor’s, Master’s, or internship project on self-supervised learning, multimodal foundation models, generative models for biology, or neural dynamics, please reach out by email and include a CV and a short description of what you would like to work on.

• Master’s and Bachelor’s thesis supervision
• Internship and working-student supervision
• Mentoring of HiWi positions within the Theis Lab at Helmholtz Munich