Metraipolis › archive › dc_6efaef689325

FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models — arXiv:2610.31423

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31423
License (as archived)
CC0-1.0
Archived
2026-10-25T08:35:36.420Z
SHA-256 of the archived text
3c708e91c7e3d1a6280c16f040f49004e868afa790f564f95876b6615ef5b75c
Stable URL of this page
https://metraipolis.com/documento/dc_6efaef689325

How to cite

FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models — arXiv:2610.31423 — arXiv (en), https://arxiv.org/abs/2610.31423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6efaef689325 (Metraipolis archive dc_6efaef689325, sha256 3c708e91c7e3d1a6280c16f040f49004e868afa790f564f95876b6615ef5b75c)
BibTeX
@misc{dc6efaef689325,
  title = {FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models — arXiv:2610.31423},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31423},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6efaef689325; sha256 3c708e91c7e3d1a6280c16f040f49004e868afa790f564f95876b6615ef5b75c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable manipulation requires sufficient observation of objects, end-effectors, and their spatial relationships, multi-view inputs are widely used to provide complementary spatial information. However, our experiments show that existing VLA models do not fully exploit such multi-view complementarity. The policy tends to persistently rely on the wrist view, lacking the ability to dynamically adjust global-local view dependency across manipulation stages, which limits stage adaptability and robustness. To address this issue, we propose FocusVLA, a stage-aware multi-view routing framework. FocusVLA predicts future interaction intent from historical actions and uses it to guide dynamic view routing during action generation. By adaptively coordinating global and local observations across different task stages, FocusVLA improves multi-view utilization. On RoboTwin 2.0, FocusVLA improves the average success rate over the strongest baseline $\pi_{0.5}$ by 10.10 pp. In real-world evaluation, FocusVLA improves the success rate from 71.7\% to 85.0\%, achieving a 13.3\% gain over $\pi_{0.5}$. Moreover, the intent prediction and dynamic routing modules of FocusVLA can be integrated into existing VLA frameworks without modifying their core architectures.

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/2610.31423 — 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 2026-10-25T08:31:13.263Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).