The Machine Learning Research Lab focuses on fundamental machine learning research for probabilistic inference, time series modelling, efficient exploration, and control. Our work starts from probability theory, through neural networks, to applications inside and outside our lab.

This website is to inform you about our work through publications, blog posts, and other public output.

Disclaimer: The views, thoughts, and opinions expressed on this website belong solely to the individual authors/contributors and do not necessarily reflect the official policy or position of Volkswagen Group. The content provided is for informational purposes only and is not intended as legal, financial, or professional advice. Volkswagen Group makes no representations as to the accuracy, completeness, suitability, or validity of any information on this site and will not be liable for any errors, omissions, or delays in this information or any losses, injuries, or damages arising from its display or use. All information is provided on an as-is basis. It is the reader's responsibility to verify their own facts.

Action Inference by Maximising Evidence

AIME optimises toward the same objective function as model learning, i.e. ELBO, with a different sampling path for imitation.

Spatial World Models

Inferring a dense 3D scene in a fully-probabilistic way. Left half of the scene shows uncertainty.

Latent Matters

Inferring the state-space representation of a pendulum

A Tale of Gaps

A catastrophic example of the newly discovered conditioning gap.

Learning to Fly

A self-built drone controlled onboard by a learnt policy optimised in a learnt simulation


The front view of the lab building