PDEformer-2 is a pretrained graph-transformer and implicit-neural-representation model that solves a broad class of 2D PDEs from their symbolic form, with zero-shot, few-shot, and inverse-problem capabilities.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PDEformer-2: A Versatile Foundation Model for Two-Dimensional Partial Differential Equations
PDEformer-2 is a pretrained graph-transformer and implicit-neural-representation model that solves a broad class of 2D PDEs from their symbolic form, with zero-shot, few-shot, and inverse-problem capabilities.