Reproduce “SCANO: Restoring Boundary-Condition Completeness in Sampled Meshes with a Sliced-Cross-Attention Neural Operator for 3D Thermal Fields” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tianyu Li, Zhiwei Cao, Qingang Zhang, Ruihang Wang, Binyang Song, Yonggang Wen
SCANO keeps boundary conditions available to every queried point and makes global context independent of the query sample. It combines Boundary Quadrature Attention, which area-weights face records, with Anchored Global State, which estimates context from independent volume-weighted anchors. On a controlled convection–diffusion benchmark, adding boundary attention reduced Transolver’s whole-mesh relative L2 error from 0.800 to 0.189 in that setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.