NVIDIA (Yu-Cheng Chou et al.) · Flash Visual Planning

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

VFlash is a decoding method for visual planning in vision-language models, predicting points, boxes and trajectories jointly in one forward pass with a lightweight drafter instead of one coordinate token at a time. Across evaluated 2D and 3D robot trajectory tasks it reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements show about 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans reaches 70.2% average success across four MolmoSpaces task suites, against 62.6% for the baseline.