Low-Rank Spatial Attention unifies global mixing in neural operators with standard Transformer components and reduces error by over 17%.
org/CorpusID:273350739
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
-
Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
Low-Rank Spatial Attention unifies global mixing in neural operators with standard Transformer components and reduces error by over 17%.