Metraipolis › archive › dc_6f2c700ff239

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models — arXiv:2610.40748

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40748
License (as archived): CC0-1.0
Archived: 2026-11-03T05:47:11.580Z
SHA-256 of the archived text: 5b4e1dc4f0fef82c04988ea072c5d5f4306c312ea6deb85c8d2ca028351d26d2
Stable URL of this page: https://metraipolis.com/documento/dc_6f2c700ff239

How to cite

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models — arXiv:2610.40748 — arXiv (en), https://arxiv.org/abs/2610.40748 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f2c700ff239 (Metraipolis archive dc_6f2c700ff239, sha256 5b4e1dc4f0fef82c04988ea072c5d5f4306c312ea6deb85c8d2ca028351d26d2)

BibTeX

@misc{dc6f2c700ff239,
  title = {WorldBridge: Bridging Video and Action for Task Generalization in World Action Models — arXiv:2610.40748},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40748},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f2c700ff239; sha256 5b4e1dc4f0fef82c04988ea072c5d5f4306c312ea6deb85c8d2ca028351d26d2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40748. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two complementary capabilities: video generalization, which predicts the visual evolution of new tasks, and action generalization, which translates these predictions into executable behavior through a video-to-action bridge. By varying video and action supervision for tasks outside an initial training set, we examine their respective contributions to task transfer. On RoboTwin 2.0, using only in-distribution video-action supervision yields a 25.07% success rate on out-of-distribution tasks. Introducing videos of these tasks without their action labels raises success to 55.90%, while adding just one action-labeled demonstration per task further improves it to 70.70%. These findings suggest that broader video coverage enables task transfer by leveraging existing inverse-dynamics capabilities, while even sparse action supervision further strengthens those capabilities. Guided by this perspective, we introduce WorldBridge, a WAM with separate video and action experts connected through structured attention and trained with joint flow matching. WorldBridge incorporates visual memory at two temporal scales and action forcing, alongside a unified data processing pipeline that standardizes and filters heterogeneous robot trajectories and egocentric hand-derived supervision. Across multiple manipulation benchmarks, WorldBridge achieves state-of-the-art performance among the compared methods, including 96.23% on RoboTwin 2.0 full data setting and 80.9% on clean to random setting, 82.8% on RoboCasa GR1 TableTop, and 57.6% on DOMINO Level-1. Our study highlights the complementary roles of video prediction and action grounding in developing robots that generalize across tasks.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.40748 — 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 2026-11-03T05:33:47.999Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).