PulseAugur
EN
LIVE 03:32:08

BeingBeyond trains humanoid robots with 10,000 hours of human video data

By PulseAugur Editorial · [1 sources] ·

BeingBeyond has developed a new model called Being-M0.7, which utilizes 10,000 hours of human video data to train humanoid robots. This model is capable of predicting future visual states and entire-body movements, enabling robots to perform actions like walking and grasping. In simulations, Being-M0.7 achieved a 71.1% success rate in the SIMPLE benchmark and demonstrated strong performance on a Unitree G1 robot. AI

IMPACT This development could significantly advance humanoid robot capabilities in locomotion and manipulation, potentially accelerating their integration into various industries.

RANK_REASON The item describes a new model release and its capabilities in training robots, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Pandaily →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

BeingBeyond trains humanoid robots with 10,000 hours of human video data

How we ranked this

Signal score
39 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new model release and its capabilities in training robots, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    BeingBeyond's Being-M0.7 Uses 10,000 Hours of Human Video to Teach Humanoids to Walk and Grasp

    BeingBeyond's Being-M0.7 predicts future visual latents and whole-body motion before acting. It led SIMPLE simulation at 71.1% and tied the strongest baseline on a Unitree G1 robot.

RELATED TOPICS