Metraipolis › archive › dc_06e91a04caab

Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models — arXiv:2609.19923

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19923
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:36.144Z
SHA-256 of the archived text
4769c8a9f887b2edc95c88fca0f0d7f7a33f0f85afb61d58d31cf7c0598d56b4
Stable URL of this page
https://metraipolis.com/documento/dc_06e91a04caab

How to cite

Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models — arXiv:2609.19923 — arXiv (en), https://arxiv.org/abs/2609.19923 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06e91a04caab (Metraipolis archive dc_06e91a04caab, sha256 4769c8a9f887b2edc95c88fca0f0d7f7a33f0f85afb61d58d31cf7c0598d56b4)
BibTeX
@misc{dc06e91a04caab,
  title = {Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models — arXiv:2609.19923},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19923},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06e91a04caab; sha256 4769c8a9f887b2edc95c88fca0f0d7f7a33f0f85afb61d58d31cf7c0598d56b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19923. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action models (VLAs) have emerged as a promising paradigm for general-purpose robot learning, with performance improving as models and datasets scale. Scaling robot data collection, however, remains challenging because data are naturally distributed across robots, tasks, and locations, making centralization costly or impractical. Federated learning offers a way to train on decentralized robot data, but applying it to VLAs requires accounting for heterogeneous robot client data distributions. We present Co-VLA, which applies consensus optimization using the Alternating Direction Method of Multipliers~(ADMM) to federated VLA training. We show that the same algorithm supports both full-model training and parameter-efficient fine-tuning with both fixed-rank and rank-adaptive adapters. The name Co-VLA reflects both consensus and collaboration: clients with different local robot datasets collaboratively train a shared model without sharing their data. Our experiments demonstrate that Co-VLA achieves performance comparable to centralized training in both full-model training and parameter-efficient fine-tuning settings. The project website and videos of our real-world experiments are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.19923 — 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 2026-10-10T04:47:38.864Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).