# Vision-Language-Action Flow

FlowerVLA is a pre-trained vision-language-action flow policy model for robotic manipulation tasks, trained on the LIBERO 10 dataset with only 1 billion parameters.

FlowerVLA is a vision-language-action flow model pre-trained on the CALVIN D dataset, employing an efficient flow-matching architecture that achieves general-purpose robot operation strategies with only about 1 billion parameters.

FlowerVLA is a robot operation model pre-trained on the CALVIN ABCD dataset, employing an innovative vision-language-action flow strategy with only 1 billion parameters, specifically designed for robot learning.

Pi0 is a general robot control model based on vision-language-action flow, supporting robot control tasks.