Metraipolis › archive › dc_d7874ebaf302
Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence — arXiv:2609.39870
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39870
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:12:15.057Z
- SHA-256 of the archived text
048d11f4338c9088bcd3ecd4cf09ce2411c09f2e23f17f204f185b608ca5d857- Stable URL of this page
https://metraipolis.com/documento/dc_d7874ebaf302
How to cite
Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence — arXiv:2609.39870 — arXiv (en), https://arxiv.org/abs/2609.39870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7874ebaf302 (Metraipolis archive dc_d7874ebaf302, sha256 048d11f4338c9088bcd3ecd4cf09ce2411c09f2e23f17f204f185b608ca5d857)
BibTeX
@misc{dcd7874ebaf302,
title = {Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence — arXiv:2609.39870},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39870},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7874ebaf302; sha256 048d11f4338c9088bcd3ecd4cf09ce2411c09f2e23f17f204f185b608ca5d857},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World-action models (WAMs) augment robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observation reconstruction or generic latent prediction and lack structured, control-oriented world representations tightly coupled with action generation. We introduce Magic-W0, a world-action foundation model that jointly models structured physical state evolution and continuous actions. Magic-W0 represents interaction as a Structured World Transition consisting of Current State, Transition, and Future State. Current State combines vision-language context with Current 3D Geometry; Transition is represented by 3D Motion capturing action-induced three-dimensional changes; and Future State is represented by Future Semantics describing task-relevant outcomes. To couple prediction and control, we propose a layer-aligned world-action interaction architecture in which evolving action hypotheses condition world-transition prediction, while predicted world representations continuously inform action generation. Magic-W0 is pre-trained on large-scale egocentric human manipulation, UMI, real-robot, and simulation data, with latent supervision for geometry, 3D motion, and future semantics from pre-trained visual models. Inference-time interventions show that structured world representations respond systematically to changes in candidate actions and that action-related information propagates through shared 3D representations into future semantic predictions. On RoboDojo-Sim, Magic-W0 achieves an average Score of 27.10, the highest among the compared WAMs. Across multiple real-robot tasks, it also demonstrates strong downstream performance after fine-tuning with limited downstream data, supporting generalization and rapid adaptation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.39870 — 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 2026-10-07T14:44:47.477Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).