Guo-Hua Wang (王国华)
 | Guo-Hua Wang, Ph.D., Algorithm Researcher & Engineer Alibaba, Hangzhou e-mail: wangguohuakey {at} gmail.com CV: English version |
Biography
Education
2018.9–2023.6, Ph.D. degree in LAMDA Group, Department of Computer Science and Technology, Nanjing University, advised by Prof. Jianxin Wu.
2014.9–2018.6, B.Sc. degree in School of Management & Engineering, Nanjing University.
Career
2024.8–present, algorithm researcher & engineer at Alibaba.
2023.7–2024.8, algorithm researcher & engineer at Consumer Cloud Service CBG, Huawei.
2022.3–2022.10, intern at Media Computing, MSRA, Microsoft.
Research Interests
His research interests include Machine Learning and Deep Learning. Currently, he focuses on:
Image Generation: Diffusion, Flow Matching.
Multi-model Learning: Knowledge Distillation, Model Compression/Acceleration.
Few-label Learning: Semi-Supervised Learning, Few-shot Learning.
Publications
Conference Articles
TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance
Minghao Fu, Guo-Hua Wang, Xiaohao Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang.
In: Proc. International Conference on Computer Vision (ICCV 2025), Honolulu, Hawai'i, Oct 2025, pp. xx-xx.
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
Minghao Fu, Guo-Hua Wang, Liangfu Cao, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang.
In: Proc. the International Conference on Machine Learning (ICML 2025), Vancouver, Canada, July 2025, pp. xx-xx.
[arXiv][code]Dense Vision Transformer Compression with Few Samples
Hanxiao Zhang, Yifan Zhou, Guo-Hua Wang.
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle WA, USA, June 2024, pp. 15825-15834.
[Open Access][arXiv][PDF][code]Practical Network Acceleration with Tiny Sets
Guo-Hua Wang, Jianxin Wu.
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 2023, pp. 20331-20340.
[Open Access][arXiv][PDF][poster][code][virtual]EVC: Towards Real-Time Neural Image Compression with Mask Decay
Guo-Hua Wang, Jiahao Li, Bin Li, Yan Lu.
In: Proc. the 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda, May 2023, pp.1-23.
[openreview][arXiv][PDF][poster][code][virtual]Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
Guo-Hua Wang, Jianxin Wu.
In: Proc. the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), New York, USA, Feb. 2020, pp. 6170-6177.
[paper][arXiv][PDF][poster][code]
Journal Articles
Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm (His best paper)
Guo-Hua Wang, Jianxin Wu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 46(12):9272 - 9285, 2024.
[IEEE Xplore][arXiv][PDF][code]How to Reduce Change Detection to Semantic Segmentation
Guo-Hua Wang, Bin-Bin Gao, Chengjie Wang.
Pattern Recognition (PR), Vol. 138, Article 109384, 2023.
[ScienceDirect][arXiv][PDF][code]
Distilling Knowledge by Mimicking Features
Guo-Hua Wang, Yifan Ge, Jianxin Wu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(11):8183-8195, 2022.
[IEEE Xplore][arXiv][PDF][code]
Technical Reports
Ovis-U1 Technical Report
Guo-Hua Wang, Shanshan Zhao, Xinjie Zhang, Liangfu Cao, Pengxin Zhan, Lunhao Duan, Shiyin Lu, Minghao Fu, Xiaohao Chen, Jianshan Zhao, Yang Li, Qing-Guo Chen
In arXiv preprint arXiv:2506.23044, 2025.
[arXiv][code][model][demo]Unified multimodal understanding and generation models: Advances, challenges, and opportunities
Xinjie Zhang, Jintao Guo, Shanshan Zhao, Minghao Fu, Lunhao Duan, Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang
In arXiv preprint arXiv:2505.02567, 2025.
[arXiv][code]Evaluating Image Caption via Cycle-consistent Text-to-Image Generation
Tianyu Cui, Jinbin Bai, Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Ye Shi
In arXiv preprint arXiv:2501.03567, 2025.
[arXiv]R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning
Guo-Hua Wang, Jianxin Wu.
In arXiv preprint arXiv:2202.08955, 2022.
[arXiv][PDF][code]PENCIL: Deep Learning with Noisy Labels
Kun Yi, Guo-Hua Wang, Jianxin Wu.
In arXiv preprint arXiv:2202.08436, 2022.
[arXiv][PDF][code]
Patent
Thesis
Research on Theories and Approaches for Deep Model Compression
Guo-Hua Wang
Services
Conference Reviewers
Journal Reviewers
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Teaching Assistant
Introduction to Computation Theory, Spring, 2021 (He builds the website)
Pattern Recognition, Spring, 2021
Introduction to Computation Theory, Spring, 2020
Pattern Recognition, Spring, 2019
Contests & Awards
Outstanding Graduate of Nanjing University. 2023
Microsoft Research Asia Stars of Tomorrow (Award of Excellence). 2022
National Scholarship for Doctoral Students. 2021
Excellent Student of Nanjing University. 2020,2021
Honorable mention in the competition of 2020 DIGIX Global AI Challenge. [slides][code]
Scholarship of CFETS Information Technology. 2019
Presidential Special Scholarship for first year Ph.D. Student in Nanjing University. 2018
Outstanding Graduate of Nanjing University. 2018
National Third Prize of the 3rd China Data Mining Competition. 2018
Excellent Student of Nanjing University. 2016,2017
Pacemaker to Excellent Youth League Member. 2016
National Scholarship for Undergraduate Students. 2015
Correspondence
Guo-Hua Wang
Alibaba
Hangzhou 310000, China