# NVIDIA releases VFlash visual planning decoding framework, robot action decoding up to 12x faster

- Source: 机器人前瞻 · 微信公众号
- Published: 2026-11-06T10:07:19.000Z
- RoboHot: https://robohot.news/en/items/ai2vqh36del586fsznrfs0qe4
- Original: https://mp.weixin.qq.com/s?__biz=Mzk0NDU5NjMwMA==&mid=2247495940&idx=1&sn=c49a54a458ca25dfbd5c2cf48c95e7cc&chksm=c2b67ee4deaca4b2b8fcfcdec69f085a41d5c32920e8c51ec07cc08e9e352e8be6536be2bc0f&scene=126&sessionid=1793985448#rd

## Summary

NVIDIA has released VFlash, a general-purpose decoding framework for fast visual planning that replaces token-by-token coordinate generation with parallel decoding of complete visual primitives, allowing it to predict robot grasp positions and motion trajectories in one pass. At batch size 1 on H100, single-generation speed improved by about 25x; across four MolmoSpaces tasks, the world action model averaged a 70.2% success rate versus a 62.6% baseline. Jim Fan shared that it achieves up to 12x faster action decoding, 5.1x overall robot inference speedup, and up to 61% lower 3D trajectory error.

## Why it matters

NVIDIA's new decoding framework changes visual planning from token-by-token generation to parallel prediction, and provides speedup and success-rate comparisons across multiple robot and autonomous-driving benchmarks.