About
I am currently an associate professor at School of Artificial Intelligence, Sun Yat-sen University. I completed my Ph.D. at City University of Hong Kong advised by Prof. Qing Li and my B.Eng. at Nankai University. My research interests are in the areas of diffusion models, generative adversarial networks, and deep generative models.
Email: xudong.xdmao@gmail.com
Publications
CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization
Feize Wu*, Yun Pang*, Junyi Zhang*, Lianyu Pang*, Jian Yin, Baoquan Zhao, Qing Li, Xudong Mao†
[*indicates equal contribution]
Preprint, 2024
[arXiv] [project] [code (coming soon)]
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
Lianyu Pang, Jian Yin, Baoquan Zhao, Feize Wu, Fu Lee Wang, Qing Li, Xudong Mao†
Advances in Neural Information Processing Systems (NeurIPS), 2024
[arXiv] [project] [code]
Cross Initialization for Face Personalization of Text-to-Image Models
Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao†
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[arXiv] [code]
Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability
Xudong Mao, Liujuan Cao, Aurele Tohokantche Gnanha, Zhenguo Yang, Qing Li, Rongrong Ji
ACM Multimedia (ACM MM), 2022
[arXiv] [code]
The Residual Generator: An Improved Divergence Minimization Framework for GAN
Aurele Tohokantche Gnanha, Wenming Cao, Xudong Mao, Si Wu, Hau-San Wong, Qing Li
Pattern Recognition, 2021
Image-to-image Translation via Hierarchical Style Disentanglement
Xinyang Li, Shengchuan Zhang, Jie Hu, Liujuan Cao, Xiaopeng Hong, Xudong Mao, Feiyue Huang, Yongjian Wu, Rongrong Ji
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[arXiv] [code]
Generative Adversarial Networks for Image Generation
Xudong Mao and Qing Li
Springer Book, 2021
Generative Semi-supervised Learning for Multivariate Time Series Imputation
Xiaoye Miao, Yangyang Wu, Jun Wang, Yunjun Gao, Xudong Mao, Jianwei Yin
AAAI Conference on Artificial Intelligence (AAAI), 2021
Virtual Mixup Training for Unsupervised Domain Adaptation
Xudong Mao*,Yun Ma*, Zhenguo Yang, Yangbin Chen, Qing Li
[*indicates equal contribution]
Preprint, 2019
[arXiv] [code]
On the Effectiveness of Least Squares Generative Adversarial Networks
Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang, Stephen Paul Smolley
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2019
[arXiv] [code] [dataset]
Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
Xudong Mao and Qing Li
International Joint Conference on Artificial Intelligence (IJCAI), 2018
[arXiv] [code]
Least Squares Generative Adversarial Networks
Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang, Stephen Paul Smolley
International Conference on Computer Vision (ICCV), 2017
[arXiv] [code]
Academic Service
Reviewer for journals: TPAMI, TIP, IJCV, TNNLS, PR, TIST, TSC, NEUNET, NEUCOM, NEURCOMP, EAAI, CAIS
Reviewer for conferences: ICCV, ACM MM, CVPR, NeurIPS, ICLR, ECCV, AAAI, IJCAI, ACCV, WACV, ICME
Awards
Outstanding Research Thesis Award, 2019
Hong Kong PhD Fellowship Scheme (HKPFS), 2016-2019
Chow Yei Ching School of Graduate Studies Entrance Scholarships, 2016-2017
Research Tuition Scholarships, 2017-2019