Performers approximate full-rank softmax attention in Transformers via FAVOR+ random features for linear complexity, with theoretical guarantees of unbiased estimation and competitive results on pixel, text, and protein tasks.
Efficient attention: Attention with linear complexities
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
unclear 1representative citing papers
VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintaining competitive performance.
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.
Toeplitz MLP Mixers replace attention with masked Toeplitz multiplications for sub-quadratic complexity while retaining more sequence information and outperforming on copying and in-context tasks.
citing papers explorer
-
Elastic Attention Cores for Scalable Vision Transformers
VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintaining competitive performance.