Dr. Sebastian Damrich

Sebastian Damrich
Sebastian is a Early Career Research Group Leader at the Hertie AI, where he develops and analyses machine learning models for biomedical data. His focus is on unsupervised and self-supervised methods for representation learning, in particular clustering, dimensionality reduction and visualization, but he has worked on image segmentation as well. With a background in Mathematics, he is also interested geometric deep learning and topological data analysis.
Annotated data is a scarce resource. Unsupervised and self-supervised learning techniques enable researchers to discover structure in unlabelled data sets.
01
Schmors, L., Gonschorek, D., Böhm, J. N., Qiu, Y., Zhou, N., Kobak, D., ... & Berens, P.

TRACE: Contrastive learning for multi-trial time-series data in neuroscience.

Dec 03, 2025 | NeurIPS 2025
02
Nazari, P., Damrich, S., Hamprecht, F.A.

Geometric Autoencoders – What You See is What You Decode

Jul 23, 2023 | International Conference on Machine Learning 2023
03
Damrich, S., Böhm, J. N., Hamprecht, F. A., & Kobak, D.

From t-SNE to UMAP with contrastive learning

May 30, 2023 | Proceedings of the International Conference on Learning Representations (ICLR)