titleVFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
authorsYu-Cheng Chou, Shihao Wang, Jin Huang, Chi-Pin Huang, Chiao-An Yang, Xianzhe Fan, Jing Wang, Zhiqi Li, Yuanguo Kuang, Ruijie Zheng, Johan Bjorck, Sifei Liu, Hang Su, Abhishek Badki, Lei Zhang, Alan Yuille, Linxi "Jim'' Fan, Jan Kautz, Zhiding Yu
date2026-11-05
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.08449
affiliationNVIDIA
upvotes100 (Hugging Face Daily Papers, 2026-11-08)
linksabs pdf hf
cite
relatedCosmos 3: Omnimodal World Models for Physical AI
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
abstractModels 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 coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type, dimensionality, and length, supporting compact boxes and long, variable-length trajectories. Crucially, spatial accuracy need not require reproducing an autoregressive model's exact token sequence. VFlash therefore trains on annotated primitives and directly accepts structurally valid predictions without target-token agreement. Across the evaluated 2D and 3D robot trajectory tasks, VFlash consistently reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements indicate approximately 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans achieves 70.2% average success across four MolmoSpaces task suites, compared with 62.6% for the baseline.

bibtex

@misc{chou2026vflash,
  title={VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding},
  author={Yu-Cheng Chou and Shihao Wang and Jin Huang and Chi-Pin Huang and Chiao-An Yang and Xianzhe Fan and Jing Wang and Zhiqi Li and Yuanguo Kuang and Ruijie Zheng and Johan Bjorck and Sifei Liu and Hang Su and Abhishek Badki and Lei Zhang and Alan Yuille and Linxi "Jim'' Fan and Jan Kautz and Zhiding Yu},
  year={2026},
  eprint={2611.08449},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.08449}
}