# Being-H0.5 uses 16,000 hours of human video to scale robot learning

> Original title: Scaling robot learning with 16,000+ hours of human video and Gemini video understanding 🎥

- Source: Paige Bailey
- Published: 2026-11-10T14:27:26.000Z
- Bad Influence: https://badinfluence.news/items/ad5p46bzuta184ocle53t1vjm
- Original: https://x.com/DynamicWebPaige/status/2120161414912389408

## Summary

Being-H0.5 researchers present a method that filters egocentric human video and labels it at two timescales for cross-embodiment robot learning. The labels cover 1-second fine-grained motions and 10-second intent summaries, drawing on more than 16,000 hours of footage with Gemini video understanding. The work is presented as an oral (O1) and a poster (S1 #67).

## Post

Scaling robot learning with 16,000+ hours of human video and Gemini video understanding  🎥

Being-H0.5 filters egocentric footage and generates dual-timescale labels (1s fine-grained motions + 10s intent summaries) for cross-embodiment VLAs.

📍 Oral O1 | Poster S1 #67
🔗 https://openreview.net/forum?id=cfzFrOJmKA

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWxTbR6XMAIIW5n.jpg&mode=thumb&exp=1794528000&sig=7e026a002ebd72ee)