Metraipolis › archive › dc_b013bc23130c

Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization — arXiv:2610.05230

Source
arXiv
Original
https://arxiv.org/abs/2610.05230
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:43.885Z
SHA-256 of the archived text
2e8fd38f1c37071d4a84c2071c8031ac91ca64f773b42dbc1783b8781417ffd4
Stable URL of this page
https://metraipolis.com/documento/dc_b013bc23130c

How to cite

Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization — arXiv:2610.05230 — arXiv, https://arxiv.org/abs/2610.05230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b013bc23130c (Metraipolis archive dc_b013bc23130c, sha256 2e8fd38f1c37071d4a84c2071c8031ac91ca64f773b42dbc1783b8781417ffd4)
BibTeX
@misc{dcb013bc23130c,
  title = {Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization — arXiv:2610.05230},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05230},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b013bc23130c; sha256 2e8fd38f1c37071d4a84c2071c8031ac91ca64f773b42dbc1783b8781417ffd4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise representation wastes capacity on highly correlated neighboring actions, leaves temporal continuity and smoothness to be learned implicitly, and forces a tradeoff between long-horizon coverage and the local precision required for contact-rich manipulation. To address these limitations, we introduce Vela, a vision-language-action foundation model that represents future robot behavior as continuous trajectories. Vela combines a compact spline-based action representation with motion-dependent temporal support and a shared action interface for heterogeneous embodiments, allowing a fixed output budget to adapt its temporal resolution across motions. We pretrain Vela on large-scale multi-embodiment robot data and evaluate it on LIBERO-X, EBench, and two real-world long-horizon tasks, egg-cake cooking and potato shredding, obtaining promising results across simulation and physical manipulation. These results highlight the potential of continuous action representations as a foundation for future embodied foundation models. Project page and more results: this https URL .

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/2610.05230 — 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 2026-10-06T05:24:05.980Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).