Abstract:Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural alternative, yet faces a fundamental gap: supervision on static geometry alone ignores dynamics and can lead to negative transfer on physics tasks. We present GeoPT, a unified pre-trained model for general physics simulation based on lifted geometric pre-training. The core idea is to augment geometry with synthetic dynamics, enabling dynamics-aware self-supervision without physics labels. Pre-trained on over one million samples, GeoPT consistently improves industrial-fidelity benchmarks spanning fluid mechanics for cars, aircraft, and ships, and solid mechanics in crash simulation, reducing labeled data requirements by 20-60% and accelerating convergence by 2$\times$. These results show that lifting with synthetic dynamics bridges the geometry-physics gap, unlocking a scalable path for neural simulation and potentially beyond. Code is available at this https URL.
| Comments: | Project Page: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.20399 [cs.LG] |
| (or arXiv:2602.20399v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.20399 arXiv-issued DOI via DataCite |
From: Haixu Wu [view email]
[v1]
Mon, 23 Feb 2026 22:32:08 UTC (27,264 KB)
[v2]
Wed, 20 May 2026 00:32:41 UTC (16,119 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。