Metraipolis › archive › dc_e72773f6afce

SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long-Horizon Manipulation — arXiv:2608.16172

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16172
License (as archived)
CC0-1.0
Archived
2026-10-18T23:05:59.464Z
SHA-256 of the archived text
00e561e706ec3424042ee3756d77dbff603aef3b572bcd9ce574f5d984162370
Stable URL of this page
https://metraipolis.com/documento/dc_e72773f6afce

How to cite

SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long-Horizon Manipulation — arXiv:2608.16172 — arXiv (en), https://arxiv.org/abs/2608.16172 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e72773f6afce (Metraipolis archive dc_e72773f6afce, sha256 00e561e706ec3424042ee3756d77dbff603aef3b572bcd9ce574f5d984162370)
BibTeX
@misc{dce72773f6afce,
  title = {SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long-Horizon Manipulation — arXiv:2608.16172},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16172},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e72773f6afce; sha256 00e561e706ec3424042ee3756d77dbff603aef3b572bcd9ce574f5d984162370},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16172. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

At every re-observation point in a hierarchical Vision-Language-Action (VLA) system, two interface decisions must be made: when to terminate the current subtask and how far to execute the proposed action chunk. These decisions are mutually dependent---the optimal stopping point depends on what the executor plans to do, while the optimal execution length depends on where the subtask boundary lies---yet existing architectures evaluate them in isolation, an asymmetry neither module can overcome alone. We present SparkVLA, a stop-aware hierarchical VLA that resolves this mutual dependency by formulating both decisions as a single ranking: Stop competes against every action-prefix length in a unified candidate set, and the system selects the highest-scoring option, eliminating threshold tuning and requiring only offline ordinal preferences. An Anchor-Conditioned Context Encoding module caches a history-aware subtask anchor encoding onset-state memory and goal semantics, guiding visual-token pruning toward task-relevant regions; a Stop-Aware Action-Prefix Selection head scores all candidates via full self bnattention at chunk boundaries for efficiency. On RoboCerebra, SparkVLA achieves 47.12% success rate, surpassing the official hierarchical baseline by 30.57% and the strongest reproducible method by 26.83% Real-robot experiments on multi-step tasks further validate these gains on physical hardware.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.16172 — 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 2026-10-18T23:01:50.376Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).