Unified Embodied Understanding, Action Generation, and Future-State Prediction
-
DeepCybo/PhysBrain1.5-8B
Any-to-Any • 9B • Updated • 301 • 25 -
DeepCybo/PhysBrain1.5-2B
Any-to-Any • 2B • Updated • 197 • 13 -
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
Paper • 2609.14973 • Published • 175 -
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Paper • 2609.18487 • Published • 33