LATIDIA · Robótica
SALA: Las acciones latentes alineadas semánticamente permiten el escalado biaxial de los modelos fundacionales corporizados
arXiv:2611.17110v2 Tipo de anuncio: sustitución Resumen: Los modelos fundacionales corporizados dependen de diversos datos de interacción con robots, cuya recopilación resulta costosa. Los vídeos humanos egocéntricos ofrecen una fuente complementaria de experiencia, y
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.17110v2 Announce Type: replace Abstract: Embodied foundation models hinge on diverse robot interaction data, which are costly to collect. Egocentric human videos offer a complementary source of experience, and latent action models (LAMs) provide a popular means of leveraging these videos for policy supervision. Compared with world-action models (WAMs), LAMs can offer greater training efficiency and potentially lower inference costs by avoiding explicit pixel prediction during policy learning and execution. However, most existing LAMs learn latent actions solely through video reconstruction, which can cause their representations to cluster by visual appearance rather than by the underlying actions. As a result, they struggle to align human actions with their robot counterparts.