Large Engineering Models for instant design validation
Abstract
The multi-trillion high-tech industry heavily relies on simulations throughout their development cycles to model complex systems, optimize performance, and validate designs before costly and time intensive prototype fabrication. We are pioneering Large Engineering Model, which represent foundation models for specific engineering verticals (aerodynamics, crash testing, semiconductor design, injection moulding), capable of replacing the full numerical pipeline, and effectively consolidating the traditional, fragmented pipeline into a single interface that provides near-instantaneous feedback to the engineer. Picture a scenario where heat distribution and mechanical stresses are instantly visualized throughout a new semiconductor design! Our main hypothesis is that fully data-driven approaches can parallelize across engineering verticals, with minimal structural intervention, because operational patterns such as geometry representation, meshing algorithms, numerical solving schemes, and postprocessing routines are more uniform than underlying physics. We present our challenges we are facing along our way, and end with our first Large Engineering Model, and its integration into conventional software.
Fields of Study & Subjects
Model Reduction and Neural Networks
Scientific Computing and Data Management
Machine Learning in Materials Science
Publication details
- Publication date
- 5 February 2026