Open Models Almanac
Methodspost-training

single mention · post-training

Three-stage VLA training pipeline

A three-stage training pipeline for a vision-language-action model, with the stages not specified by the supplied evidence.

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

Also called three-stage training pipeline.

Filed under post-training