According to Wallstreetcn, Xpeng Group announced a major upgrade to its second-generation VLA model, saying its physical-world foundation model has for the first time incorporated "time," moving AI's understanding of the world from "3D space" to "4D spacetime." Xpeng also said its X-Foresight predictive world model has been installed in a vehicle for the first time and can predict what will happen in the next six seconds and infer the possible future behavior of surrounding traffic participants.