(1) We released the 50 diffusion steps model (instead of 1000 steps) which runs 20X faster with comparable results. (2) Calling CLIP just once and caching the result runs 2X faster for all models.

Unlike traditional 2D models, 3D-VLA integrates 3D perception, reasoning, and action through a generative world model, similar to human cognitive processes. It is built on the 3D-LLM and uses ...

Six prototypes have been produced, and the first serial model has entered final assembly. Early indications are that it will have a top speed of Mach 1.8 and up to 17,000 lbs of payload. Pepsi2024 / ...