open-h/open-h-embodiment

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

NeurIPS2026 , Scalable annotation pipeline for action-aglined fine-grained instruciton for Visual-language-Action model

Official Repository for MolmoAct2

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

Official Repository for MolmoAct

From Vision-Language-Action Models to a Real-World Robot Learning Stack

Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.

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