Metraipolis › archive › dc_69adc4765ffc

SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation — arXiv:2609.16641

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16641
License (as archived)
CC0-1.0
Archived
2026-10-15T21:30:26.444Z
SHA-256 of the archived text
b494cc4cdb414ad97d5e5a5f589b29f078eec2a8cb29e7dd0bad862543af1ace
Stable URL of this page
https://metraipolis.com/documento/dc_69adc4765ffc

How to cite

SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation — arXiv:2609.16641 — arXiv (en), https://arxiv.org/abs/2609.16641 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69adc4765ffc (Metraipolis archive dc_69adc4765ffc, sha256 b494cc4cdb414ad97d5e5a5f589b29f078eec2a8cb29e7dd0bad862543af1ace)
BibTeX
@misc{dc69adc4765ffc,
  title = {SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation — arXiv:2609.16641},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16641},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69adc4765ffc; sha256 b494cc4cdb414ad97d5e5a5f589b29f078eec2a8cb29e7dd0bad862543af1ace},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16641. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models have become the dominant paradigm for language-conditioned robot manipulation. However, although images and language instructions inherently encode geometric information, VLAs acquire their spatial competence purely from demonstrations. As a result, they are reliable only within the range of scene poses that the demonstrations cover. We propose SAVLA, an end-to-end symmetry-aware VLA model for robust and data-efficient policy learning. Our approach keeps the pretrained vision-language backbone entirely frozen while combining it with an equivariant flow-matching action head and a learned canonicalizer. The head decomposes its state, action, and conditioning inputs into invariant and equivariant channels, and preserves this typing throughout all of its layers. The canonicalizer transforms oblique-view images into a canonical frame and rotates the geometric conditions consistently. We evaluate our model on LIBERO. Compared with the GR00T N1.5 baseline, SAVLA improves the success rate averaged over all four LIBERO suites by 5.1 points and increases the mean success rate under rotation on LIBERO-Goal from 41.5% to 90.4%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-16 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.16641 — 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 2026-10-15T21:30:17.328Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).