π0.5
Physical Intelligenceimplemented as a single transformer with two sets of weights (also known as experts [45]), where each token is routed to one of the experts
specific method · filed under model architecture
An action expert is one of two sets of weights in a single transformer, where each token is routed to one of the experts.1 Images and language prompts are routed to the larger VLM backbone, while inputs not seen during VLM pre-training are routed to the action expert, and the experts interact only through the self-attention layers.2,3
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
implemented as a single transformer with two sets of weights (also known as experts [45]), where each token is routed to one of the experts— π0\pi_{0}: A Vision-Language-Action Flow Model for General Robot Control Thanks: Physical Intelligence, San Francisco, California, USA.…
The images and language prompt, , are routed to the larger VLM backbone, which we initialize from PaliGemma. The inputs not seen during VLM pre-training, , are routed to the action expert— π0\pi_{0}: A Vision-Language-Action Flow Model for General Robot Control Thanks: Physical Intelligence, San Francisco, California, USA.…
Since the experts interact only in the self-attention layers— π0\pi_{0}: A Vision-Language-Action Flow Model for General Robot Control Thanks: Physical Intelligence, San Francisco, California, USA.…
Also called Transformer action expert.
2 quotes from 2 sources, one card per model, each opening with its strongest.
implemented as a single transformer with two sets of weights (also known as experts [45]), where each token is routed to one of the experts
SmolVLA’s action expert is a compact transformer (~100M parameters) that generates action chunks