Model techniques map
Techniquesmodel architecturemultimodal architecture

specific method · filed under model architecture

From-scratch vision-encoder training with next-token prediction

The vision encoder is trained from scratch using next-token prediction.

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 train Kimi K3 vision encoder, MoonViT-V2, entirely from scratch with next-token prediction.

usedtraining objectivein Kimi K3Moonshot AI

Filed alongside

Other methods under model architecture :: multimodal architecture.