Martin Trapp
Almost surely
AoF Postdoctoral Researcher
Aalto University, Finland
Martin is an Academy of Finland postdoctoral researcher at Aalto University and a member of the ELLIS society, working on probabilistic machine learning. His research is centred around representing, quantifying, and reducing uncertainties to make machine learning more reliable. He is particularly interested in efficient and principled approaches for large-scale systems with applications in language and vision.
See my biography for more details.
Research Interests
- Tracable Models: Probabilistic circuits, limits of tractability, 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, uncertainty quantification, and uncertainty reduction.
News & Updates
CVPR Workshop on Uncertainty Quantification for Computer Vision.
June 2025Together with collegues we organised the 4th Workshop on Uncertainty Quantification for Computer Vision at CVPR 2025.
UAI Paper accepted!
May 2025Our BitVI paper has been accepted to UAI 2025. Check out the paper, the code will be released soon.