← Papers
Transformers

BIW crash surrogate

Neural surrogates for a full body-in-white crash

Paper title Automotive Crash Dynamics Modeling Accelerated with Machine Learning

Nabian et al. (NVIDIA) · Structures & crash · Public: code

Paper arXiv 2510.15201PDF

Predicts the deformed mesh of a car body through a frontal crash from the undeformed mesh and part thicknesses. Compares Transolver with MeshGraphNet (including a multiscale version) and three ways to handle time: conditioning on time, plain autoregression, and autoregression trained on rollouts.

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. TransformersMNC — Retrofitting foundation models to unstructured meshes
  2. TransformersPSP grounding — Correcting a CFD-trained wing surrogate with wind-tunnel pressure paint
  3. TransformersTransolver without attention — Does Transolver really need a Transformer?