Metraipolis › archive › dc_604fde6a3db9

Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution — arXiv:2610.07946

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07946
License (as archived)
CC0-1.0
Archived
2026-10-07T11:21:23.537Z
SHA-256 of the archived text
d8b1017e66c67fdc4caf95a9d4cc6508d72fb85ad08c4c491da68eae9fd3cfd7
Stable URL of this page
https://metraipolis.com/documento/dc_604fde6a3db9

How to cite

Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution — arXiv:2610.07946 — arXiv (en), https://arxiv.org/abs/2610.07946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_604fde6a3db9 (Metraipolis archive dc_604fde6a3db9, sha256 d8b1017e66c67fdc4caf95a9d4cc6508d72fb85ad08c4c491da68eae9fd3cfd7)
BibTeX
@misc{dc604fde6a3db9,
  title = {Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution — arXiv:2610.07946},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07946},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_604fde6a3db9; sha256 d8b1017e66c67fdc4caf95a9d4cc6508d72fb85ad08c4c491da68eae9fd3cfd7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous action chunk, as self-supervision for test-time adaptation. Because consecutive chunks overlap in time, the leftover provides a temporally aligned target for the current prediction over the same future control interval. At the onset of a visual shift, the leftover can retain a plan formed before the corruption, so updating the policy toward it anchors the adaptation across the shift (Transition Anchoring). SALT keeps the adapted policy and regenerates the current chunk, whose leftover becomes the target at the next replan, carrying the correction forward along the execution trajectory (Sequential Correction Propagation). Supervision comes entirely from the policy's own predictions, requiring no disruption annotations, expert actions, or target-domain demonstrations, and a lightweight adaptation gate calibrated only on nominal trajectories decides when updates begin. On LIBERO-10, SALT increases average success across five persistent visual corruptions from 43.9% to 53.2% with SmolVLA and from 58.7% to 66.0% with GR00T N1.7, while largely preserving nominal performance. On a real robot, it raises task progress averaged over digital and physical disruptions from 0.49 to 0.61.

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/2610.07946 — 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 2026-10-07T11:15:24.787Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).