C4 Group
Creative, Controllable & Cognitive Computing Group
Innovating Tomorrow's Technology
Explosive Innovation in Creative, Controllable Content Generation & Cognitive Advancement
About
The Creative, Controllable & Cognitive Computing Group (C4G) at HKUST, founded in 2024, pioneers cutting-edge research at the intersection of content generation, precise control, and cognitive intelligence for visual and multimodal systems. We fuse creative AI (e.g., image/video, 3D/4D generation), controllable synthesis (e.g., motion/attribute-aware generation), and cognitive advancement (e.g., multimodal reasoning, human-AI interaction) to develop explosive innovations that bridge theory and real-world impact.
Why C4 Group
Like the explosive potential of its namesake, our group delivers high-impact solutions — validated by awards, patents, and publications at top conferences/journals. Join us to redefine the frontiers of intelligent content creation and multimodal computing.
Research Focus
Large Models
Developing and optimizing foundation models for various tasks
AIGC
- Image Generation & Edit
- Video Generation & Edit
- 3D/4D Generation
- Computer Graphics
Content Restoration
Enhancing and restoring low-quality media content
Multimodal AI
Advancing multimodal learning for unified understanding and generation
Latest News
Recent Publications
UNIC: Unified In-Context Video Editing
Zixuan Ye, Xuanhua He, Quande Liu, Qiulin Wang, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Qifeng Chen, Wenhan Luo
arXiv:2506.04216.
[arXiv] [Project Page]Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
Zhe Kong, Feng Gao, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Xunliang Cai, Guanying Chen, Wenhan Luo
arXiv:2505.22647.
[arXiv] [Project Page] [Code] [Hugging Face Model] [Gradio]
MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
Zebin He, Mingxin Yang, Shuhui Yang, Yixuan Tang, Tao Wang, Kaihao Zhang, Guanying Chen, Yuhong Liu, Jie Jiang, Chunchao Guo, Wenhan Luo
Proc. of International Conference on Computer Vision (ICCV), Hawaii, USA, 2025.
[arXiv] [Project Page] [Code]
MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration
Tao Wang, Peiwen Xia, Bo Li, Peng-Tao Jiang, Zhe Kong, Kaihao Zhang, Tong Lu, Wenhan Luo
Proc. of International Conference on Computer Vision (ICCV), Hawaii, USA, 2025.
DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution
Zhe Kong, Le Li, Yong Zhang, Feng Gao, Shaoshu Yang, Tao Wang, Kaihao Zhang, Zhuoliang Kang, Xiaoming Wei, Guanying Chen, Wenhan Luo
ACM SIGGRAPH, 2025.
[PDF] [Project Page] [Code]StyleMaster: Stylize Your Video with Artistic Generation and Translation
Zixuan Ye, Huijuan Huang, Xintao Wang, Pengfei Wan, Di Zhang, Wenhan Luo
Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2025.
[arXiv] [Github] [Project Page]
Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling
Jingyun Xue, Hongfa Wang, Qi Tian, Yue Ma, Andong Wang, Zhiyuan Zhao, Shaobo Min, Wenzhe Zhao, Kaihao Zhang, Heung-Yeung Shum, Wei Liu, Mengyang Liu, Wenhan Luo
International Conference on Learning Representations (ICLR), 2025.
[PDF] [Project Page] [API in Tencent Cloud]Our Group
Faculty
Associate Professor at HKUST, previously at Sun Yat-sen University. Former research scientist at Tencent and Amazon, developing deep learning solutions for products like WeChat, QQ, Tencent Video, Tencent Yuanbao, Tencent Cloud, and myapp.
Published 100+ papers in top venues (CVPR, ICML, NeurIPS, etc.). CVPR 2019 Best Paper Finalist, 2022 ACM China Rising Star Award (Guangzhou Chapter), Top 2% Scientist worldwide (2023-2024).
Serves as Senior Area Editor for IEEE SPL, Associate Editor for IEEE TIP, and Area Chair for NeurIPS/ICML/IJCAI/ACM-MM/BMVC.
Postdoctoral Researchers
PhD Students
Zhiqiang Wang
(2024 Fall, from Southern University of Science and Technology)
AI Safety
Yatian Wang
(2025 Spring, from Harbin Institute of Technology)
Agentic AI
Gongye Liu
(2025 Fall, from Tsinghua University)
Image & Video Generation
Zixuan Ye
(2025 Fall, from Huazhong University of Science and Technology)
Video Generation & Edit
HKPFS awardee
Haoqiang Guo
(2025 Fall, from Harbin Institute of Technology)
Multimodal MoE
Zhizhou Zhong
(2025 Fall, from Fudan University)
Digital Human
Research Assistant
Visiting Student/Research Intern
PhD/Master Students in Sun Yat-sen University
Sponsors
C4 Group @ HKUST, Copyright 2025
Clear Water Bay, Kowloon, Hong Kong