OpenVLA

An open-source Vision-Language-Action model built on the Prismatic VLM architecture, fine-tuned on the Open X-Embodiment dataset. OpenVLA predicts discretized robot actions from images and language instructions. As an open-weights model (7B parameters), it enables the research community to study, modify, and build upon VLA technology without proprietary restrictions.

See this in practice: our real-world evals →