Metraipolis › archive › dc_c979eff1a413
Decoupled Asynchronous System for Humanoids (DASH): Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation — arXiv:2611.11854
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11854
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:43:43.716Z
- SHA-256 of the archived text
22a816e4bad7c71fd6f2421fecc24917d5dd4ed7f47d7ffdc491cbac66b4781e- Stable URL of this page
https://metraipolis.com/documento/dc_c979eff1a413
How to cite
Decoupled Asynchronous System for Humanoids (DASH): Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation — arXiv:2611.11854 — arXiv (en), https://arxiv.org/abs/2611.11854 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c979eff1a413 (Metraipolis archive dc_c979eff1a413, sha256 22a816e4bad7c71fd6f2421fecc24917d5dd4ed7f47d7ffdc491cbac66b4781e)
BibTeX
@misc{dcc979eff1a413,
title = {Decoupled Asynchronous System for Humanoids (DASH): Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation — arXiv:2611.11854},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11854},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c979eff1a413; sha256 22a816e4bad7c71fd6f2421fecc24917d5dd4ed7f47d7ffdc491cbac66b4781e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11854. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) models pair a vision-language backbone with an action head, but in closed-loop control the backbone sits on the control-critical path: while it computes, the robot keeps moving, so each executed action is conditioned on an increasingly stale observation. A larger backbone therefore directly blocks reactivity, especially in humanoid dexterous manipulation. We present DASH, a Decoupled Asynchronous System for Humanoids that removes this coupling. DASH splits the policy into a slow vision-language model (System 2) and a fast flow-matching action head (System 1) that run as concurrent processes over the LCM communication protocol, so the control rate is set by the action head alone, independent of backbone size. The action head fuses stale semantics from a frozen backbone with fresh vision from its own ResNet encoder, desynchronized training exposes it to the staleness it meets at deployment, and an adaptive temporal aggregator aligns overlapping action chunks under variable inference latency. On an asynchronous RoboTwin benchmark that charges inference latency in simulated time, DASH holds 20 Hz control rate from 0.8B to 8B backbones while the synchronous rate falls from 9.7 to 4.1 Hz, with higher success at every size. On a real humanoid with dexterous hands, DASH achieves clearly higher pick-and-place success than the synchronous pipeline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.11854 — 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 2026-11-10T18:37:37.663Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).