Carving World Action Modeling at the Event Joints
Morefully open-source, trained with gradient-bridged co-training, and deployable on real robots straight from pretraining.
MoreAn end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision--language understanding, (2) strong language--action association, and (3) robust manipulation capability.
More