# Movens-Zero: Scaling humanoid motion foundation models with large-scale human videos

- Source: arXiv cs.RO
- Published: 2026-11-02T05:00:00.000Z
- RoboHot: https://robohot.news/en/items/j4bvbrzly569c637kjkbb1atv
- Original: https://arxiv.org/abs/2610.41877

## Summary

The research team proposes Movens-Zero, a scalable understanding-generation-execution architecture that supports real-time closed-loop humanoid motion generation under text, speech, music, and video inputs. Its accompanying dataset, Movens-5M, is built from Internet videos through clip generation, quality filtering, semantic annotation, motion recovery, and physical refinement with humanoid retargeting. It contains 15 million human motion sequences and 5 million physically executable humanoid motion sequences, totaling over 10,000 hours.

## Why it matters

This technical report presents a complete path for building a humanoid motion dataset from Internet videos and training a unified understanding-generation-execution model, offering a reference for data scale and architecture design.