A controlled study of decay in linear attention finds median decay near 0.8 works best, vector decay generally beats scalar decay, and RoPE/TPE give little benefit for models with sub-unity decay.
Xmixers: A collection of SOTA efficient token/channel mixers , August 2025
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Elucidating the Design Space of Decay in Linear Attention
A controlled study of decay in linear attention finds median decay near 0.8 works best, vector decay generally beats scalar decay, and RoPE/TPE give little benefit for models with sub-unity decay.