specific method · not yet filed
native multimodal training from the start of training
Also called native multimodal training.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Kimi K3 adopts a native multimodal training strategy in which language and vision are jointly optimized from the start of training, rather than grafting a vision encoder onto a pre-trained language model through a post-hoc alignment stage.
coreunclearin Kimi K3Moonshot AI