VSpark:自回歸視覺語言動作模型的推測解碼
VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models
VSpark透過改良推測解碼,加速自回歸視覺語言動作模型,在多項機械人操作任務中達到 1.28x–2.10x 無損加速。方法包括校準動作噪聲 rollout、隱藏特徵對齊,以及重用被拒草稿的後續預測。測試涵蓋四個採用不同動作 tokenizer 的 VLA,以及四項操作基準。
Abstract
VSpark accelerates autoregressive vision-language-action models by improving speculative decoding with calibrated action-noise rollouts, hidden-feature alignment, and reuse of rejected-draft continuations, achieving lossless 1.28x–2.10x speedups across multiple robot manipulation tasks.
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.
View arXiv page View PDF Project page GitHub 5 Add to collection
Models citing this paper 1
Robotics • Updated 2 days agosuhoyoo/VSpark
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.22666 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.22666 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co