Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos

The paper introduces Movens-5M, a dataset of 15 million human‑motion sequences and 5 million humanoid‑executed motions derived from raw Internet videos, aligned with text, RGB video, speech, and music. Using this data, the authors present Movens‑Zero, a scalable architecture that jointly learns across modalities and supports real‑time closed‑loop execution, enabling motion generation from text, speech, music, and video. They also release Movens‑Intent, a benchmark of 8,192 expert‑verified condition‑motion pairs, and demonstrate that scaling data quality and model capacity improves performance across all modalities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• rag
• robotics
• multimodal
• benchmarks
• data-engineering