Generating Physically Sound Designs from Text and a Set of Physical Constraints
Abstract
We present TIDES, a text informed design approach for generating physically sound designs based on a textual description and a set of physical constraints. TIDES jointly optimizes structural (topology) and visual properties. A pre-trained text-image model is used to measure the design's visual alignment with a text prompt and a differentiable physics simulator is used to measure its physical performance. We evaluate TIDES on a series of structural optimization problems operating under different load and support conditions, at different resolutions, and experimentally in the lab by performing the 3-point bending test on 2D beam designs that are extruded and 3D printed. We find that it can jointly optimize the two objectives and return designs that satisfy engineering design requirements (compliance and density) while utilizing features specified by text.
Cite
Text
Barber et al. "Generating Physically Sound Designs from Text and a Set of Physical Constraints." Advances in Neural Information Processing Systems, 2025.Markdown
[Barber et al. "Generating Physically Sound Designs from Text and a Set of Physical Constraints." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/barber2025neurips-generating/)BibTeX
@inproceedings{barber2025neurips-generating,
title = {{Generating Physically Sound Designs from Text and a Set of Physical Constraints}},
author = {Barber, Gregory and Henry, Todd and Haile, Mulugeta A},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/barber2025neurips-generating/}
}