【#Tech24H】On January 30, AI company Robbyant under Ant Group announced the open-sourcing of its embodied world model, LingBot-VA. This model introduces the first autoregressive video-action world modeling framework, integrating the capabilities of large-scale video generation models with robot control. While generating the "next world state," the model directly infers and outputs corresponding action sequences, enabling robots to "reason while acting" much like humans.