Jisong Cai

Jisong Cai is a first-year Ph.D. student at Shanghai Jiao Tong University and a research intern at the Shanghai Artificial Intelligence Laboratory, working on Embodied AI, robotics, and world models. He is supervised by Yao Mu and co-developed UniVLA, a cross-embodiment vision-language-action framework, and AHA-WAM, an asynchronous world-action model for robotic manipulation. He also contributed to AgiBot World Colosseo, a large-scale manipulation platform for embodied systems. He previously completed an undergraduate degree in Cybersecurity at Wuhan University.