A learned gate selects the important KV blocks during long decoding, preserving math reasoning accuracy while skipping up to 90% of attention work.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
A learned gate selects the important KV blocks during long decoding, preserving math reasoning accuracy while skipping up to 90% of attention work.