MSAT, a multi-scale attention transformer, achieves state-of-the-art accuracy on complex-geometry PDE problems (L2_rel=0.0101 on Heat2D-CG) with 3.7x improvement over FNO and far lower inference time than Mamba-NO.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
No citing papers match the current filters.