I am a PhD student at the Machine Learning Group of Prof. Dr. Ulf Brefeld at the Leuphana University of Lüneburg. My master degree was in Management & Data Science at Leuphana University, my bachelor degree was in Psychology at Leuphana University. I was working on the KISS-KI project which concerns itself with the anomaly detection and protection of cyber-physical systems, demonstrating the effects of different geometrical method on anomaly detection in water data. While geometrical methods show obvious advantages, implementing them can be rather involved. To alleviate this, Max and I proposed Geodesic Ball Regularisation, a lightweight regulariser.

My main area of research is geometric deep learning, especially exploring Riemannian manifolds as latent spaces of deep learning models. An example of possible expansions of geometries is the Poincaré disc with individual curvature per dimension.

• Decomposing Neural Networks (W22)
• Applied statistics (Professional School) (S23, S24, S25, S26)
• Introduction to Artificial Intelligence (Exercises) (S26)

• M. Reinhardt, T. Paulsen, U. Brefeld. Regularising Latent Representations with Geodesic Balls. ECMLPKDD, 2026.

• S. Fadel, T. Paulsen, S. Mair. Towards General Geometries for Embedding Knowledge Graphs. GRAM@ICML, 2024.

• T. Paulsen, U. Brefeld. Studying properties of water data using manifold-aware anomaly detectors. DCS-Water, 2024.

• S. Fadel, T. Paulsen, U. Brefeld. Exploring the Poincaré ellipsis. MLG@ECML, 2023.

• Teaching award for Decomposing Neural Networks (W22)