cs.ROOct 30, 2026

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

Authors: Wendong Bu, Tinghong Ye, Qizhou Wang, Jiacheng Li, Zhiqi Ge, Yuze Lin, Zhongqi Yue, Yi Su, 

Organizations: Zhejiang University · Joint Laboratory of Embodied Intelligence, ZJU & Unitree Robotics · Bit Oasis · Unitree Robotics · 

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 jointly optimizes a single action expert across seven generation tasks, enabling direct motion generation from text, speech, music, and video. Multimodal Real-Time Chunking connects overlapping chunks under continuously updated instructions and robot states for continuous closed-loop execution. We further introduce Movens-Intent, a four-track benchmark with 8,192 expert-verified condition-motion pairs across text, speech, music, and video. Experiments show consistent gains across all four modalities when scaling execution-verified data from 1% to 100% and action-expert capacity from 64M to 911M parameters, while demonstrating that data quality and cross-modal supervision improve generation and execution.

Figures & tables

Appendix figures & tables38 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation

    May 12, 2026Inwoo Hwang, Hojun Jang, Bing Zhou +3Text-to-Motion GenerationHuman Motion Generation

  2. TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation

    Jun 22, 2026Jianuo Cao, Yuxin Chen, Yuzhen Song +3Humanoid Robot ControlTest-Time Scaling