---
id: "2026-07-14-beingbeyond-being-m0-7-latent-world-action-model"
url: "https://postcutoff.com/e/2026-07-14-beingbeyond-being-m0-7-latent-world-action-model/"
as_of: "2026-10-12T22:30:00+02:00"
date: "2026-07-14"
date_precision: day
category: robotics
importance: 2
confidence: medium
status: [Partly confirmed]
sources: 3
editor: Adam Bicz
human_review: null
version: null
---

As of: 2026-10-12 22:30 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code). Human editor: Adam Bicz.
Canonical page: https://postcutoff.com/e/2026-07-14-beingbeyond-being-m0-7-latent-world-action-model/

# A latent world-action model for humanoid whole-body loco-manipulation, pre-trained on 10,000+ hours of human data

Full title: BeingBeyond's Being-M0.7: a latent world-action model for humanoid whole-body loco-manipulation, pre-trained on 10,000+ hours of human data

Chinese robotics startup BeingBeyond published a technical report on Being-M0.7 (dated July 14, 2026), a latent world-action model for humanoids. It learns a video-and-motion prior from more than 10,000 hours of human-centric data, predicts future egocentric visual states and whole-body motion in latent space, and a small action expert turns them into commands for a Unitree G1. The project page reports no benchmark scores; Pandaily covered it on October 12, 2026.

## 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.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 75 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 14 days after its cutoff
- Gemini 3.8 Flash (training cutoff March 2026): 105 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 44 days after its cutoff

## Sources

1. [BeingBeyond: Being-M0.7 project page](https://research.beingbeyond.com/being-m07) (research.beingbeyond.com, official)
2. [Being-M0.7 technical report (PDF)](https://research.beingbeyond.com/being-m07/being-m07.pdf) (research.beingbeyond.com, paper)
3. [Pandaily: BeingBeyond's Being-M0.7 uses 10,000 hours of human video to teach humanoids to walk and grasp](https://pandaily.com/beingbeyond-being-m0-7-latent-world-action-model-humanoid-loco-manipulation-simple-71-1) (pandaily.com, press)

## Changes

- 2026-10-12 (filed): Created (evening)

## Related

- 2026-10-10: [Robotera's open-source VPP2 world action model tops the RoboDojo benchmark and scores 58.5% zero-shot on a real ALOHA robot vs 40% for pi0.5](https://postcutoff.com/e/2026-10-10-robotera-vpp2-world-action-model/index.md)