Model techniques map
Techniquesmodel architecturemultimodal architecture

specific method · filed under model architecture

Decoupled Encoder Process (DEP)

A process that separates ViT and text training into stages and balances vision passes across pipeline-parallel stages.

Also called decoupled encoder process.

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.

we introduced the Decoupled Encoder Process (DEP) [59], which splits ViT and text training into separate stages and balances vision forward and backward passes across PP stages.

usedsoftware implementationin Kimi K3Moonshot AI

Filed alongside

Other methods under model architecture :: multimodal architecture.