Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

portfolio

publications

Universal Time Series Generation with Neural Controlled Differential Equations

Published in arXiv, 2026

Generative SLiCEs extend maximally expressive continuous-time state space models to flow matching on path space for probabilistic time-series forecasting.

Recommended citation: Torben Berndt*, Elyes Farjallah*, Leif Seute, Raeid Saqur, Benjamin Walker† and Jan Stühmer†. (2026). "Universal Time Series Generation with Neural Controlled Differential Equations." arXiv preprint.
Download Paper

talks

teaching