16.09.2026
Vincent Fortuin Receives ERC Starting Grant for Reliable Small-Data AI
Advancing Bayesian Deep Learning for Data-Efficient AI
MCML PI Vincent Fortuin has been awarded an ERC Starting Grant for his project “AutoBayes – Unlocking Reliable Small-data AI through Bayesian Deep Learning.” Hosted at the University of Technology Nuremberg (UTN), the project will advance Bayesian deep learning methods that enable AI systems to learn reliably from limited datasets while better quantifying the uncertainty of their predictions.
Many scientific and practical applications face a fundamental challenge: only small amounts of data are available for training AI systems. Through AutoBayes, Fortuin aims to develop data-efficient and reliable machine learning methods that can make effective use of limited data while providing meaningful measures of uncertainty. The ERC Starting Grant provides up to €1.5 million over a maximum of five years and will support the establishment of a dedicated research team.
Related
05.10.2026
Honorable Mention at GCPR 2026
A GCPR 2026 paper co-authored by MCML Director Daniel Cremers received an Honorable Mention at the conference in Siegen.
05.10.2026
Honorable Mention at GCPR 2026
A GCPR 2026 paper co-authored by MCML Director Daniel Cremers and MCML PI Riccardo Marin received an Honorable Mention.
05.10.2026
How a Startup Is Making AI Faster and More Sustainable
Pruna AI, co-founded by MCML PI Stephan Günnemann, develops efficient AI models that use fewer resources while keeping high performance.
