Sicheng Xie

Sicheng Xie is a master's student at Fudan University, where he is advised by Zuxuan Wu and conducts research in computer vision, vision-language modeling, and robotics. He is a co-author of Qwen-VLA, a vision-language-action model developed in collaboration with Alibaba's Tongyi Lab team, and has also contributed to FineVLA, a fine-grained instruction alignment framework for vision-language-action policies. His prior publications include work on fine-grained vision-language understanding presented at CVPR 2024 and video motion editing via score-guided diffusion at ICCV 2025.