Andres Felipe Posada Moreno
  • Home
  • Experience
  • Publications
  • Research and Projects
  • Teaching
  • Blog

On this page

  • Research Overview
  • Related Publications

Foundation Models for Dynamical Systems

Foundation Models
Dynamical Systems
Time Series
Control
Exploring transformer-based foundation models pretrained on synthetic data for prediction and control of dynamical systems.
Published

September 1, 2024

Research Overview

Foundation models pretrained on large amounts of data have shown impressive performance across NLP and computer vision. This research line investigates whether the same paradigm applies to dynamical systems — can models pretrained on vast numbers of randomly generated systems generalize to unseen target systems?

We explore transformer-based architectures pretrained entirely on synthetic data from randomly generated ordinary differential equations. Our findings show surprising zero-shot generalization to new target systems of various complexities for both state prediction and control tasks. We also investigate combining these foundation models with classical estimation techniques like the Unscented Kalman Filter (UKF) for state estimation.

This work is funded by the JUPITER AI Factory (JAIF), part of the EuroHPC initiative.

Related Publications

  • On Foundation Models for Dynamical Systems from Purely Synthetic Data (2024) Ziegler, M., Posada-Moreno, A.F., Solowjow, F., Trimpe, S. Details | arXiv

  • Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF (2025) Holtmann, T., Stenger, D., Posada-Moreno, A., Solowjow, F., Trimpe, S. — CDC 2025 Details | DOI

© 2025 Andres Felipe Posada Moreno. Licensed under CC BY-NC-SA 4.0.

 

Built with Quarto.