I work on probabilistic machine learning, vision-language models, and sample-efficient reinforcement learning.
Jonas Hübotter, Frederike Lübeck*, Lejs Behric*, Anton Baumann*, Marco Bagatella, Daniel Marta, Ido Hakimi, Idan Shenfeld, Thomas Kleine Buening, Carlos Guestrin, Andreas Krause
Best Paper ICLR 2026 Workshop on Test-Time Updates
Oral ICLR 2026 Workshop on Scaling Post-training for LLMs
Anton Baumann, Rui Li, Marcus Klasson, Santeri Mentu, Shyamgopal Karthik, Zeynep Akata, Arno Solin, Martin Trapp
Spotlight NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty
Anton Baumann, Thomas Roßberg, Michael Schmitt
Oral ICCV 2023 Workshop on Uncertainty in Computer Vision
Researched probabilistic ML for vision-language models in Arno Solin's lab.
Applied probabilistic ML and data fusion to remote sensing problems.
Implemented GNNs for chemical property prediction in PyTorch.
Extended Horn & Schunck optical flow for electrographic flow mapping.
Integrated the method into a prototype core product with a research engineering team.
Developed a logging/versioning system and JSON diff library in Go for privacy-first ad-tech infrastructure.
Thesis supervision by Andreas Krause (ETH Zürich) and Zeynep Akata (TUM), with day-to-day supervision by Jonas Hübotter.