Metraipolis › archive › dc_6750dd699573

WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models — arXiv:2608.08725

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08725
License (as archived)
CC0-1.0
Archived
2026-10-19T09:12:37.073Z
SHA-256 of the archived text
34b3a3a7438a965d87358a42c2d090f9d58c9e7996955696b4cba2ce61422e69
Stable URL of this page
https://metraipolis.com/documento/dc_6750dd699573

How to cite

WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models — arXiv:2608.08725 — arXiv (en), https://arxiv.org/abs/2608.08725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6750dd699573 (Metraipolis archive dc_6750dd699573, sha256 34b3a3a7438a965d87358a42c2d090f9d58c9e7996955696b4cba2ce61422e69)
BibTeX
@misc{dc6750dd699573,
  title = {WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models — arXiv:2608.08725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6750dd699573; sha256 34b3a3a7438a965d87358a42c2d090f9d58c9e7996955696b4cba2ce61422e69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) policies generate robot controls autoregressively, making closed-loop latency dominated by repeated target-model forward passes. Speculative decoding reduces this cost by verifying blocks of draft action tokens in parallel, and recent VLA methods further relax token-level acceptance because small differences in action-token space often map to similar continuous controls. However, this relaxation remains scene-agnostic. A fixed token-distance tolerance treats the same action-token deviation as equally safe across states, although deviations that are harmless in free space can cause collisions or grasp failures near contact. We propose WA-SpecDec, a world-aware speculative decoding framework that injects world-model-derived physical scene awareness during the VLA prefill stage, producing shared world-aware prefill states for draft proposal and target verification without changing the relaxed acceptance rule. Across three state-of-the-art relaxed acceptance schemes, WA-SpecDec preserves higher task success under looser relaxation and enables longer accepted prefixes. At comparable-success operating points, WA-SpecDec achieves a 1.5x matched-success speedup over VLA speculative decoding alone and reduces near-contact failure (NCF) by 18.6% on average relative to the corresponding speculative baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.08725 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:11:58.752Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).