BeingBeyond/Being-H

Being-H is BeingBeyond's family of human-centric embodied foundation models.

What it solves

Being-H provides human-centric foundation models that enable robots to learn complex actions and reasoning from human videos, addressing the challenge of cross-embodiment generalization (applying knowledge across different robot types).

How it works

The project offers a family of models based on different architectures:

  • Being-H0.7 (WAM): A World-Action Model that uses egocentric videos to perform future-aware latent reasoning.
  • Being-H0.5 (VLA): A Vision-Language-Action model designed for cross-embodiment generalization using a unified action space.
  • Being-H0 (VLA): An earlier version focused on pretraining from large-scale human videos.

Who it’s for

It is designed for robotics researchers and developers working on embodied AI, specifically those looking to implement VLA or WAM models for robot control and manipulation.

Highlights

  • Cross-Embodiment Generalization: Aims to make robot learning transferable across different hardware platforms.
  • Human-Centric Learning: Leverages large-scale human video data for pretraining.
  • Diverse Model Architectures: Includes both Vision-Language-Action (VLA) and World-Action Models (WAM).
  • Educational Support: Includes a dedicated tutorial workspace (Being-H-EDU) for post-training and deployment on robots like the SO101.

Related

  • Project
    X-Square-Robot/wall-x

    An open-source framework for embodied foundation models that enables robots to perform complex physical manipulations by bridging vision-language understanding with action prediction.

  • Project
    Robbyant/lingbot-vla-v2

    LingBot-VLA 2.0 is a Vision-Language-Action foundation model that enables robots to generalize across different embodiments and tasks using a unified action representation and MoE action experts.

  • Project
    NVIDIA/Isaac-GR00T

    An open vision-language-action (VLA) model for generalized humanoid robot skills, enabling cross-embodiment manipulation tasks via multimodal input.

  • Project
    dexmal/opendm

    OpenDM is a Vision-Language-Action (VLA) model framework for open-world robot control, providing tools for training, fine-tuning, and deploying models that can handle complex, multi-embodiment tasks.

  • Project
    alibaba-damo-academy/RynnBrain

    An embodied foundation model family that bridges vision-language understanding with real-robot control through 3D grounding and contact point prediction.