BeingBeyond

We introduce Being-H0.8, our latest general-purpose embodied foundation model. Being-H0.8 extends latent world-action modeling from visual prediction to tactile-aware interaction and, to our knowledge, is the first model to bring tactile pretraining to egocentric human video at this scale.

These real-world demonstrations probe continuous force modulation, deformable-object handling, contact coordination, rapid adaptation, and precise tool use. Each task is shown from a single focused view so that its contact sequence remains easy to follow.

To train Being-H0.8, we assemble 500,000+ hours of raw human video. To the best of our knowledge, this is the first human-centric corpus at this scale for which every sample is traceable to its source.

From raw video to retained training data

UniHand 3.0500,000+raw hoursFilter by source