Martin Trapp
Almost surely
Assistant Professor in Machine Learning & WASP Fellow
KTH Royal Institute of Technology
I am an Assistant Professor in Machine Learning at KTH Royal Institute of Technology, WASP fellow, and a member of the ELLIS society. Before joining KTH, I was an Academy of Finland postdoctoral researcher at Aalto University working with Arno Solin. My research is centred on making machine learning more #reliable by representing, quantifying, and reducing #uncertainty. I am particularly interested in #efficient and #principled approaches for large-scale machine learning models and AI agents.
See biography for more details.
Research Interests
- Tractable Models: Probabilistic circuits, neurosymbolics, and exact & approximate Bayesian inference.
- Bayesian Learning: Uncertainty quantification & reduction in deep learning, inductive biases, and non-parametric & function-space methods.
- Probabilistic Numerics: Probabilistic programming, numerical imprecision, error and uncertainty quantification.
If you want to join my group, check the information for prospective PhD students and Postdocs.
News & Updates
ECCV Workshop proposal accepted!
[April 2026]Exciting news, we will organised a new version of our successfull workshop series on Uncertainty Quantification for Computer Vision at ECCV!
ICLR Paper accepted!
[January 2026]Our paper on Post-hoc Probabilistic Vision-Language Models (BayesVLM) has been accepted to ICLR 2026. Check out the paper
CVPR Workshop on Uncertainty Quantification for Computer Vision.
[June 2025]Together with collegues we organised the 4th Workshop on Uncertainty Quantification for Computer Vision at CVPR 2025.