# VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding > Source: > Published: 2026-11-06 06:00:35+00:00 Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one co