Being-M
$ 0
Whole-body motion generation model learning general human behavioral patterns from large-scale video; bridges robot brain and body; generates full-body motion sequences from high-level task instructions
Available on backorder
Brain Score
6
Specifications and details:
| Nationality | China |
|---|---|
| Website | https://beingbeyond.com/en/ |
| Model type | Foundation Model |
| Manufacturer | BeingBeyond |
| Release date | 2025 |
Description
Being-M is a whole-body motion generation model for humanoid robots. It learns general human behavioral patterns from large-scale video, enabling robots to generate coordinated full-body movements. Consequently, the model can transform high-level instructions into natural and fluid motion sequences. Moreover, it helps robots adapt to new tasks efficiently, reducing the need for extensive task-specific training. Through this approach, Being-M bridges the gap between robot intelligence and physical execution.
In addition, Being-M enhances robot versatility across various scenarios. Therefore, it allows robots to perform both simple and complex actions with consistent precision. As a result, robots can apply learned behaviors to new environments effectively. Furthermore, the model improves the coherence of motion, synchronizing limbs, torso, and overall posture seamlessly. This combination of adaptability, reliability, and generalization makes Being-M a key tool for advanced humanoid robotics.
New! 2026 Humanoid
Robot Market Report
198 pages of exclusive insight from global robotics experts — uncover funding trends, technology challenges, leading manufacturers, supply chain shifts, and surveys and forecasts on future humanoid applications.
now Google DeepMind
Contact Humanoid.guide
Website: https://beingbeyond.com/en/
