Lars Doorenbos
University of Bonn
Bonn, Germany
I am a Postdoc in the Computer Vision Group of Juergen Gall in Bonn, Germany. My research mainly focuses on reliable AI, video understanding, and machine learning for science. I completed my Ph.D. at the University of Bern, focusing on safe and reliable deep learning. Before, I did my Bachelor’s and Master’s degree in Computing Science at the University of Groningen.
news
| Oct 28, 2024 | Our work Galaxy spectroscopy without spectra: Galaxy properties from photometric images with conditional diffusion models was accepted at The Astrophysical Journal. |
|---|---|
| Jul 1, 2024 | Our paper “Learning Non-Linear Invariants for Unsupervised Out-of-Distribution Detection” has been accepted at the European Conference on Computer Vision. |
| Apr 2, 2024 | I have been selected as a DAAD AInet fellow for 2024. |
selected publications
2024
- Learning Non-Linear Invariants for Unsupervised Out-of-Distribution DetectionEuropean Conference on Computer Vision, 2024
- Galaxy spectroscopy without spectra: Galaxy properties from photometric images with conditional diffusion modelsarXiv preprint arXiv:2406.18175, 2024*equal contribution
- Hyperbolic Random ForestsTransactions on Machine Learning Research, 2024
2023
- Stochastic Segmentation with Conditional Categorical Diffusion ModelsInternational Conference on Computer Vision, 2023*equal contribution
2022
- Generating astronomical spectra from photometry with conditional diffusion modelsNeurIPS: Machine Learning for the Physical Sciences Workshop, 2022
- Data invariants to understand unsupervised out-of-distribution detectionIn European Conference on Computer Vision, 2022