Open Models Almanac
Methodsmodel architecturemultimodal architecture

implementation detail · filed under model architecture

3×3 PixelUnshuffle downsampling

A vision-token reduction operation that applies PixelUnshuffle with a 3×3 downsampling factor.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.

Also called 3×3 pixel-unshuffle downsampling.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2
↑