VSpark:視覚言語行動モデルのための投機的デコーディング
VSpark: Speculative Decoding for Autoregressive Vision-Language-Action Models
ロボット制御向けVLAの自己回帰生成を、軽量ドラフトモデルと検証で損失なく高速化する手法VSparkを提案。行動ノイズ付きロールアウト、特徴整合、継続再利用の3工夫で1.28〜2.10倍の高速化を実現。
著者: Suho Yoo, Youngjoon Jang, Hyebin Cho, Taeyeop Lee, Jaewook Jeong, Joon Son Chung
分類: cs.CV, cs.RO
原文アブストラクト
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.
