A latent world-action model for humanoid whole-body loco-manipulation, pre-trained on 10,000+ hours of human data
Partly confirmed
The takeaway
Chinese robotics startup BeingBeyond published a technical report on Being-M0.7 (dated July 14, 2026), a latent world-action model for humanoids.
Status
- Claim
Partly confirmed
- Our reporting
- Medium confidence
- Importance
- 2 of 5
- Last verified
- 12 October 2026
Your AI and this story
- GPT-6 Astra75 days after its cutoff
- Claude Opus 5.514 days after its cutoff
- Gemini 3.8 Flash105 days after its cutoff
- Grok 4.744 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 14 days before it.
Key facts
- Technical report ‘Being-M0.7: A Latent World-Action Model for Humanoid Robots’, dated July 14, 2026; authors Junpeng Yue, Boyuan Li, Yuxuan Wang and others, last author Zongqing Lu
- Pre-training: more than 10,000 hours of human-centric mixed-modality data (raw, before filtering and segmentation)
- Design: a pretrained prior predicts future egocentric visual states and a compact whole-body motion sequence; a lightweight future-conditioned action expert outputs low-level action chunks
- Robot: Unitree G1 humanoid; robot data collected by VR teleoperation with a motion-tracking controller at 50 Hz
- No arXiv listing was found; the project page gives no benchmark scores or baselines and does not mention a code or weights release
What happened
Being-M0.7 extends the company’s earlier models for tabletop manipulation to whole-body movement: walking, reaching and carrying with one policy. Instead of generating future video frames, it predicts the future scene and body motion in a latent space and then converts that plan into robot commands. The model is first trained on human video and motion data and then post-trained on a small amount of teleoperated robot data.
The Pandaily article (October 12) was readable only as a headline; its URL mentions a score of 71.1 on a benchmark called SIMPLE, which the project page does not report and which is therefore not stated here as a fact.
Why it matters
Human video is far cheaper to collect than robot teleoperation data. Several Chinese labs (BeingBeyond, Robotera) now train “world-action” models on it and use robot data only for the last step.
Sources
3 sources from 2 sites. Numbers match the chips in the text.
3 sources: 2 primary, 1 press
Primary
- BeingBeyond: Being-M0.7 project pageresearch.beingbeyond.com, official
- Being-M0.7 technical report (PDF)research.beingbeyond.com, paper
Press
Changes
- Filed (evening)