Model techniques map
Techniquesmodel architecturetoken mixersparse attentionblock selection

implementation detail · filed under model architecture

Block Max Pooling

Compresses token-level scores into block-level scores for block selection.

Also called Block Max Pool.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Block Max Pool then compresses the token-level scores into block-level scores

usedmodel architecturein MiniMax-M3MiniMax

Filed alongside

Other methods under model architecture :: token mixer :: sparse attention :: block selection.