LATIDIA · Robótica

Thinker-WM: un modelo mundial unificado con representaciones multimodales compartidas para la inteligencia incorporada

arXiv:2610.18447v1 Anuncio Tipo: cruz Resumen: Los modelos mundiales han surgido como un paradigma prometedor para la IA incorporada, sin embargo, los sistemas existentes a menudo permanecen fragmentados en las modalidades que modelan y las funciones que soportan

La noticia

arXiv:2610.18447v1 Announce Type: cross Abstract: World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a unified multimodal world model that jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders. The model performs multimodal unification at the representation level: appearance, geometry, and action are