LATIDIA · Robótica

Magic-W0: un modelo estructurado de base de acción mundial para la inteligencia física

arXiv: 2609.39870v2 Tipo de anuncio: reemplazar Resumen: Los modelos de acción mundial (WAM) aumentan las políticas de robots con dinámicas de entorno condicionadas por la acción, sin embargo, los enfoques existentes se basan en gran medida en la reconstrucción de la observación futura

La noticia

arXiv:2609.39870v2 Announce Type: replace Abstract: 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