AI RESEARCH
PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
arXiv CS.LG
•
ArXi:2512.23192v3 Announce Type: replace While Transformers have nstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshes with complex geometries remains a significant challenge. Existing efficient architectures often employ feature dimensionality reduction strategies, which inadvertently induces Geometric Aliasing, resulting in the loss of critical physical boundary information.