Metraipolis › archive › dc_8a070a52be2a

StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models — arXiv:2610.07756

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07756
License (as archived)
CC0-1.0
Archived
2026-10-07T13:12:07.475Z
SHA-256 of the archived text
9cb834b93cc28d211e1d9ada95918f39e93ec8fa2edc4bfbf715799e13dd539f
Stable URL of this page
https://metraipolis.com/documento/dc_8a070a52be2a

How to cite

StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models — arXiv:2610.07756 — arXiv (en), https://arxiv.org/abs/2610.07756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a070a52be2a (Metraipolis archive dc_8a070a52be2a, sha256 9cb834b93cc28d211e1d9ada95918f39e93ec8fa2edc4bfbf715799e13dd539f)
BibTeX
@misc{dc8a070a52be2a,
  title = {StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models — arXiv:2610.07756},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07756},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a070a52be2a; sha256 9cb834b93cc28d211e1d9ada95918f39e93ec8fa2edc4bfbf715799e13dd539f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process the denoising trajectory in a largely uniform manner. However, we observe that the conditioning focus naturally shifts across denoising stages: early stages combine language instructions and visual observations to establish a coarse action trajectory, whereas later stages place greater emphasis on current visual observations for action alignment. Based on this insight, we introduce StairVLA, a stage-aware hierarchical action generation framework that uses partially denoised actions as a natural interface between coarse long-horizon action generation and local refinement. A high-level VLA performs early denoising to produce a reusable long-horizon partially denoised action trajectory, while a lightweight refiner operates at a higher frequency to refine local action chunks using the latest observations. This design amortizes expensive high-level VLA computation while preserving frequent closed-loop correction. On LIBERO, our GR00T-style instantiation improves average success from 96.5% to 97.8% while reducing amortized inference latency from 115.0 ms to 44.2 ms per action chunk. More broadly, across two VLA backbones, simulation benchmarks, and real-robot tasks, StairVLA consistently reduces inference cost while maintaining strong task performance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.07756 — 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 2026-10-07T12:42:33.572Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).