FoundPDE: A generative foundation model for data-driven symbolic discovery of partial differential equations
By amortizing symbolic discovery across equation families, FoundPDE shifts PDE discovery from per-dataset search toward a reusable pretrained model that extends to new physics with limited additional data, a step toward foundation models that uncover interpretable governing laws directly from scientific data.
Lang-Chen Liu, Jun-Ling Luo, Min Zhu et al.
· 0 citations