Metraipolis › archive › dc_f5c08693bd42
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts — arXiv:2609.37150
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37150
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T19:15:32.885Z
- SHA-256 of the archived text
bc714c7a39a7af8856d935b78f6bada06dfdb9c13908e4613eba605a7f571f39- Stable URL of this page
https://metraipolis.com/documento/dc_f5c08693bd42
How to cite
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts — arXiv:2609.37150 — arXiv (en), https://arxiv.org/abs/2609.37150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5c08693bd42 (Metraipolis archive dc_f5c08693bd42, sha256 bc714c7a39a7af8856d935b78f6bada06dfdb9c13908e4613eba605a7f571f39)
BibTeX
@misc{dcf5c08693bd42,
title = {CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts — arXiv:2609.37150},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37150},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5c08693bd42; sha256 bc714c7a39a7af8856d935b78f6bada06dfdb9c13908e4613eba605a7f571f39},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainstream paradigm in embodied intelligence. However, multiple studies have reported VLA's substantial declines in task success under camera shifts, revealing a key vulnerability that limits reliable deployment. To address this vulnerability, existing methods collect paired observations of the same scene from different viewpoints to fine-tune the VLA or train visual adaptation modules. Unfortunately, they require additional data collection and VLA training costs. In this paper, we first identify \emph{cross-view coordination breakdown} under external camera shifts: the robot may rely too heavily on wrist-view cues and consequently execute subtasks in the wrong order when losing global view. Motivated by this, we propose CoRe-VLA, a plug-and-play framework requiring neither additional multi-view data collection nor VLA fine-tuning, which can incorporate with exsiting VLAs. It reconstructs a scene point cloud and renders the observation from the VLA's training viewpoint to restore cross-view coordination. In CoRe-VLA, Render-to-Camera (R2C) Restoration reduces rendering-induced visual degradation, while Execution-Trajectory-Conditioned Alignment (ETCA) reduces robot idle time and mitigates motion conflicts during asynchronous execution. Experiments on 5 real-robot tasks, LIBERO-100 and LIBERO-Plus demonstrate CoRe-VLA substantially improves task success across mainstream VLAs under camera shifts. For example, CoRe-VLA raises PI0.5's success rate from 13.3% to 83.3% at a 1.6m camera shift in real-robot environment.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.37150 — 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 2026-10-07T18:40:59.487Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).