MANO replaces quadratic self-attention with multiscale windowed attention over progressively downsampled grids, keeping complexity linear and reporting competitive accuracy on vision and PDE benchmarks.
Neural machine translation by jointly learning to align and translate
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics
MANO replaces quadratic self-attention with multiscale windowed attention over progressively downsampled grids, keeping complexity linear and reporting competitive accuracy on vision and PDE benchmarks.