Mingsheng Li

Mingsheng Li is an AI researcher on the Qwen Team at Alibaba Group, where he works on large vision-language models, multi-agent systems, generative AI, and embodied AI. He is a co-first author of Qwen-VLA, a unified vision-language-action model for robotic manipulation and navigation. He graduated from Fudan University under the supervision of Professor Tao Chen and has collaborated with researchers at Tencent, Shanghai AI Lab, and A*STAR.