Xinting Hu is a Professor at the University of Science and Technology of China. Previously, she was a postdoctoral researcher at the CVMI Lab, The University of Hong Kong. She received her Ph.D. from the MReal Lab, Nanyang Technological University, and later conducted postdoctoral research at the D2 Lab, Max Planck Institute for Informatics. She obtained her B.Eng. degree from the University of Science and Technology of China.

Her research focuses on developing visual intelligence systems that can perceive, interpret, and simulate the visual world. In particular, she is interested in three main directions: 1) building visual learning systems that are efficient, robust, and continually adaptable; 2) developing generative models with strong multi-view consistency and interactive controllability; and 3) advancing multimodal intelligence that integrates diverse signals to improve reasoning in real-world environments. More broadly, she is also interested in leveraging AI to advance scientific discovery and medical research.