| title | VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models |
|---|---|
| authors | Suho Yoo, Youngjoon Jang, Hyebin Cho, Taeyeop Lee, Jaewook Jeong, Joon Son Chung |
| date | 2026-11-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.22666 |
| affiliation | KAIST AI |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-21) |
| links | abs pdf hf code |
| cite | |
| primer | Vision-language-action models |
| related | OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs Language Models Can Control Their Own Attention OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources GRACE: Generation-aware latent compression for efficient video generation |
| abstract | Our aim is to accelerate autoregressive vision-language-action models (VLAs), which generate robot actions one token at a time. Speculative decoding makes this possible: a lightweight draft model proposes several tokens at once, and the VLA verifies them in a single pass, accepting only those that match its own predictions, so decoding remains lossless. The speedup, however, is limited in robot control, where many different tokens encode nearly the same motion and a draft close to the correct action is still rejected. To address this, our approach, VSpark, is built upon three design choices: (i) rollouts collected with calibrated action noise, which expose the draft to a wider range of robot states; (ii) feature alignment, which trains the draft to match the VLA's hidden features rather than its output tokens alone; and (iii) continuation reuse, which keeps the predictions the VLA has already computed along rejected drafts as candidates for the next verification step, instead of discarding them. On four VLAs with different action tokenizers and four manipulation benchmarks, VSpark achieves 1.28x to 2.10x speedup while keeping the VLA's decoding lossless. |
bibtex
@misc{yoo2026vspark,
title={VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models},
author={Suho Yoo and Youngjoon Jang and Hyebin Cho and Taeyeop Lee and Jaewook Jeong and Joon Son Chung},
year={2026},
eprint={2611.22666},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.22666}
}