A polynomial state-summary mixer can replace multi-head attention in diffusion transformers at linear token complexity, with competitive ImageNet generation but weaker video results and an incomplete universality proof.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PoM: Efficient Image and Video Generation with the Polynomial Mixer
A polynomial state-summary mixer can replace multi-head attention in diffusion transformers at linear token complexity, with competitive ImageNet generation but weaker video results and an incomplete universality proof.