Metraipolis › archive › dc_ca6f09e1e693

How (and How Not) to Use Data Augmentation in VLA Post-Training — arXiv:2610.05994

Source
arXiv
Original
https://arxiv.org/abs/2610.05994
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:25.330Z
SHA-256 of the archived text
215ee16617eaf8ce4cdf5aedabd732e5309c550436d8e096b9fd5d5041e76b81
Stable URL of this page
https://metraipolis.com/documento/dc_ca6f09e1e693

How to cite

How (and How Not) to Use Data Augmentation in VLA Post-Training — arXiv:2610.05994 — arXiv, https://arxiv.org/abs/2610.05994 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca6f09e1e693 (Metraipolis archive dc_ca6f09e1e693, sha256 215ee16617eaf8ce4cdf5aedabd732e5309c550436d8e096b9fd5d5041e76b81)
BibTeX
@misc{dcca6f09e1e693,
  title = {How (and How Not) to Use Data Augmentation in VLA Post-Training — arXiv:2610.05994},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05994},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca6f09e1e693; sha256 215ee16617eaf8ce4cdf5aedabd732e5309c550436d8e096b9fd5d5041e76b81},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05994. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models currently demonstrate strong performance in a wide range of real-world robotics tasks. However, they often still lack the generalization ability to handle large visual out-of-distribution shifts. Post-training of VLAs with reinforcement learning (RL) has been shown to benefit robustness, but significant room for improvement remains. In this work, we systematically study the effect of image augmentation on VLA post-training. We find that it is crucial to augment only the critic module during RL updates, while leaving the actor's input clean during both rollouts and updates. For $\pi_{0.5}$ and GR00T N1.5 this raises out-of-distribution success on LIBERO-Plus by $7.8$ and $10.0$ points respectively, while augmenting the actor collapses training entirely. We investigate a range of augmentation types and strengths, and provide practical recommendations for improving generalization in VLA post-training.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05994 — 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 2026-10-06T05:27:06.021Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).