SiftAttention skips top-k sorting in sparse attention by thresholding attention weights with a threshold predicted from a power-law fit of score quantiles over generation steps.
https://openai
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Power Law Guided Dynamic Sifting for Efficient Attention
SiftAttention skips top-k sorting in sparse attention by thresholding attention weights with a threshold predicted from a power-law fit of score quantiles over generation steps.