LATIDIA · Robótica

No estima que la denuncia de un instrumento de derechos humanos equivalga a una violación en gran escala de los derechos humanos.

arXiv:2610.41877v1 Anuncio Tipo: nuevo Resumen: El escalado de los modelos de fundamentos de movimiento humanoide está limitado por la escasez de datos diversos y ejecutables por robots y por la dificultad de aprender conjuntamente a partir de múltiples heterogéneos.

La noticia

arXiv:2610.41877v1 Announce Type: new Abstract: Scaling humanoid motion foundation models is constrained by the scarcity of diverse, robot-executable data and by the difficulty of jointly learning from heterogeneous multimodal inputs while supporting real-time closed-loop control. We present Movens-5M, constructed from raw Internet videos through clip generation, quality filtering, semantic annotation, motion recovery, and physical refinement with humanoid retargeting and execution verification. It contains 15 million human-motion sequences and 5 million physically executable humanoid-motion sequences spanning over 10,000 hours, aligned with text, RGB video, speech, and music. Building on this data, we introduce Movens-Zero, a scalable understanding-generation-execution architecture that supports joint learning across modalities and real-time closed-loop execution. Task-mixed flow-matching training