AI RESEARCH
GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
arXiv CS.LG
•
ArXi:2603.16849v1 Announce Type: new Adapting transformer positional encoding to meshes and graph-structured data presents significant computational challenges: exact spectral methods require cubic-complexity eigendecomposition and can inadvertently break gauge invariance through numerical solver artifacts, while efficient approximate methods sacrifice gauge symmetry by design.