Biography
Prof. Xiaojuan Qi is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Hong Kong. Prior to joining HKU, she was a Postdoctoral Researcher at the University of Oxford, UK. She received her Ph.D. from the Chinese University of Hong Kong (CUHK) in 2018 and her B.Eng. degree from Shanghai Jiao Tong University (SJTU) in 2014. She has also conducted research and academic exchanges at the University of Toronto and Intel Intelligent Systems Lab.
Prof. Qi has authored over 100 peer-reviewed papers in leading venues across computer vision, computer graphics, and machine learning, including SIGGRAPH Asia, CVPR, ICCV, and NeurIPS, with multiple papers selected for oral presentations. She received a Best Paper Honorable Mention at SIGGRAPH Asia, was named one of IEEE AI’s 10 to Watch in 2024, and was selected as MIT Technology Review TR35 China. She actively serves the research community and frequently acts as an Area Chair for major conferences such as CVPR, ICCV, NeurIPS, ICML, and AAAI.
Her research aims to endow machines with the ability to perceive, understand, and reconstruct the visual world. Her current research focuses on the following directions:
- World Models: Reconstructing and generating interactive, physically realistic 3D and 4D digital worlds.
- Spatial Intelligence: Developing vision–language and vision-centric models with a deep understanding of 3D/4D geometry, motion, and spatial relationships.
- Data and Model Design for Large-Scale Models: Addressing data challenges in large-scale training, developing foundational generative algorithms (e.g., autoregressive and diffusion models with unified generation-understanding), and improving efficiency through model compression, quantization, and hardware-aware optimization.
- Agent Systems: Designing intelligent agents that construct and utilize memory, leverage external tools, and perform long-horizon reasoning and decision-making for complex real-world tasks and embodied AI.
- Interdisciplinary AI: Advancing AI for science and medicine through close collaboration across disciplines.
Related Links
Selected Publications
- Chuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang, Xin Yu, Zehuan Yuan, Bingyue Peng, Xiaojuan Qi, “UniTok: A Unified Tokenizer for Visual Generation and Understanding”, Conference on Neural Information Processing Systems (NeurIPS), 2025.
- Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi, “SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes”, Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
- Xin Yu, Ze Yuan, Yuan-Chen Guo, Ying-Tian Liu, Jianhui Liu, Yangguang Li, Yan-Pei Cao, Ding Liang, Xiaojuan Qi, TEXGen: a Generative Diffusion Model for Mesh Textures, ACM Transactions on Graphics (TOG) (also appeared in SIGGRAPH Asia),2024 (Best Paper Honorable Mention).
- Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, Xiaojuan Qi, Is synthetic data from generative models ready for image recognition? International Conference on Learning Representations (ICLR), 2023
- M. Xu, R. Ding, H. Zhao, X. Qi, “PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds”, Conference on Computer Vision and Pattern Recognition (CVPR), 2021.