Open Models Almanac
Methodsmodel architecture

general family · filed under model architecture

Flow-based vision-language-action model

A vision-language-action model or architecture using flow matching for action generation; the evidence does not establish one more specific shared design.

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

Also called Flow-based vision-language-action modeling, flow-matching-based VLA design, Flow-matching policy for action generation, flow-matching–based VLA framework, flow matching architecture.

sources
4
models
2
labs adopt it
2
strongest
core

Documented in

Physical Intelligence
X-VLA authors

Evidence

4 quotes from 4 sources, one card per model, each opening with its strongest.

How sources treat it
core 4

π0.5

Physical Intelligenceadopted2 sources

We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM)

coreunclearin π0Physical Intelligence
1 more from this model

the π₀ model, a flow-based vision-language-action model (VLA)

coremodel architecturein π0Physical Intelligence
↑