Zheng Gu

Zheng Gu 顾峥
Assistant Professor

I am currently an Assistant Professor with the Visual Computing Research Center (VCC) (led by Prof. Hui Huang) at the College of Computer Science and Software Engineering, Shenzhen University.

I received my Ph.D. degree from the Reasoning and Learning (RL) Group at College of Computer, Nanjing University in 2024, advised by Prof. Yang Gao and Prof. Jing Huo. I received my dual Ph.D. degree from Department of Computer Science, City Univercity of Hong Kong, advised by Prof. Jing Liao. Before that, I received my B.Sc. degree from Nanjing University in 2017.

My research focuses on machine learning, pattern analysis, and computer vision, aiming to enhance the transferability and controllability of visual generative models, exploring their applications in dynamic open-world scenarios such as few-shot learning, in-context learning and continual learning.

Address: L6-811, Shenzhen University Cang Hai Campus, Shenzhen, China

Email: guzheng@szu.edu.cn

Google Scholar / GitHub / 中文

I am looking for highly motivated graduate and undergraduate students for research opportunities in machine learning, computer vision, and generative models starting from Sep. 2025. Feel free to get in touch!

News

• [2025-01] I join the VCC group at Shenzhen University.

• [2024-12] I defend my PhD thesis at City University of Hong Kong.

• [2024-11] I defend my PhD thesis at Nanjing University.

• [2024-10] I am invited to give a talk at PRCV 2024 PhD Workshop.

• [2024-06] One paper (LiesGAN) is accepted by PRCV 2024.

• [2024-03] One paper (Analogist) is accepted by SIGGRAPH 2024.

Publication

	Task-Aware Few-Shot Image Generation via Dynamic Local Distribution Estimation and Sampling Zheng Gu, Wenbin Li, Tianyu Ding, Zhengli Wang, Jing Huo, Kuihua Huang, and Yang Gao Chinese Conference on Pattern Recognition and Computer Vision (PRCV)*, 2024 [Paper] [Code]
	Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model Zheng Gu, Shiyuan Yang, Jing Liao, Jing Huo, and Yang Gao ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2024 [Project Page] [Paper] [Arxiv] [Code] [Data]
	CariMe: Unpaired Caricature Generation with Multiple Exaggerations Zheng Gu, Chuanqi Dong, Jing Huo, Wenbin Li, and Yang Gao IEEE Transactions on Multimedia (TMM)*, 2021 [Paper] [Arxiv] [Code] [Data]
	LoFGAN: Fusing Local Representations for Few-shot Image Generation Zheng Gu†, Wenbin Li†, Jing Huo, Lei Wang, and Yang Gao International Conference on Computer Vision (ICCV)*, 2021 [Paper] [Code] [Data]
	Learning Task-aware Local Representations for Few-shot Learning Chuanqi Dong, Wenbin Li, Jing Huo, Zheng Gu, and Yang Gao* International Joint Conference on Artificial Intelligence (IJCAI), 2020 [Paper] [Code]
	Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition Wen Ji, Kelei He, Jing Huo, Zheng Gu, and Yang Gao European Conference on Computer Vision (ECCV)*, 2020 [Paper] [Code]
	DeepMEF: A Deep Model Ensemble Framework for Video Based Multi-modal Person Identification Chuanqi Dong, Zheng Gu, Zhonghao Huang, Wen Ji, Jing Huo, and Yang Gao ACM Conference on Multimedia (ACM MM), 2019 [Paper] [Code]