Model techniques map
Techniquespost-trainingsupervised fine-tuning

specific method · filed under post-training

Autoregressive fine-tuning

Fine-tuning a vision encoder connected to a language model using a next-token prediction objective.

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.

In the autoregressive fine-tuning stage, we connect the vision encoder to a 4B MoE LLM and train on 236B tokens across datasets including image captions, alt text, charts, and OCR, using a next-token prediction objective.

usedunclearin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under post-training :: supervised fine-tuning.