Hi there!
I am a researcher in the MLR team at Bayer, where I work on uncertainty quantification.
Before joining Bayer, I did a short postdoc at Aalto University with Vikas Garg and Markus Heinonen. And before that, I was lucky to do my PhD on a topic I still love the most: differential geometry in machine learning (mostly variational autoencoders), supervised by Søren Hauberg and Georgios Arvanitidis. You can read my thesis here.
Even though I am now in industry, I stay very much connected to the academic world, with ongoing collaborations and workshops (GRaM 2024, 2026).
ICLR accepted two papers: The Spacetime of Diffusion Models: An Information Geometry Perspective (Oral) and Riemannian Variational Flow Matching for Material and Protein Design (Poster). A pleasure to work with Rafał, Olga and Floor.
GRaM got accepted as a workshop at ICLR, our second edition! We have a call for proceedings, tiny papers, blogposts and a competition coming soon.
Gave a talk at GPSS on Links between Riemannian geometry and Gaussian Processes. Thank you Carl Henrik Ek and Mauricio Alvarez for the invitation!
Started at Bayer in the MLR team.
End of the wonderful workshop on Geometry for statistics and AI organised by Libby Baker, Stefan Sommer and Erlend Grong.