Biography
I’m a Research Scientist at Weixin AI, Tencent. Before this, I obtained my Ph.D. degree from the School of Computer Science at Fudan University, supervised by Prof. Zuxuan Wu and Prof. Yu-Gang Jiang.
My research interest lies in multimodal understanding and generation. Currently, I work on Agentic RL, Generative Models, and Multimodal Understanding.
If you are interested in discussing potential collaborations, please feel free to email me at zhanghui98.gm@gmail.com.
📝 Publications
WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing
Hui Zhang, Zongkai Liu, Liqiang Niu, Juntao Liu, Han Li, Zhen Cao, Wenchao Chen, Chengduo Zhao, Fandong Meng
WeAgent-MMSearch: Native Text–Vision Interaction for Multimodal Search Agents
Zongkai Liu, Hui Zhang, Liqiang Niu, Zhen Cao, Han Li, Juntao Liu, Wenchao Chen, Chengduo Zhao, Chao Yu, Fandong Meng
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Hui Zhang, Juntao Liu, Zongkai Liu, Liqiang Niu, Fandong Meng, Zuxuan Wu, Yu-Gang Jiang
CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design
Hui Zhang, Dexiang Hong, Maoke Yang, Yutao Cheng, Zhao Zhang, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang
CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation
Hui Zhang, Dexiang Hong, Tingwei Gao, Yiyong Wang, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang
Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
Danfeng Li, Hui Zhang, Sheng Wang, Jiacheng Li, Zuxuan Wu
BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
Hui Zhang, Tingwei Gao, Jie Shao, Zuxuan Wu
AdaDiff: Adaptive Step Selection for Fast Diffusion Models
Hui Zhang, Zuxuan Wu, Zhen Xing, Jie Shao, Yu-Gang Jiang
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
Hui Zhang, Zheng Wang, Zuxuan Wu, Yu-Gang Jiang
Prototypical Residual Networks for Anomaly Detection and Localization
Hui Zhang, Zuxuan Wu, Zheng Wang, Zhineng Chen, Yu-Gang Jiang
🎖 Honors and Awards
- 2026.05, Shanghai Outstanding Graduate, Shanghai Municipal Education Commission
- 2025.12, National Scholarship of China (Top 1%, PhD)
- 2023.12, First Class Award Scholarship, Fudan University (Top 10%, PhD)
- 2022.12, Excellent Academic Scholarship, Fudan University (Top 5%, Master)
- 2021.03, Perfect Score (150/150) in Mathematics, Nationwide Master’s Program Unified Admissions Examination (Top 0.1%, Nationally)
- 2019.12, National Scholarship of China (Top 1%)
- 2019.07, Second Prizes, 15th ‘BoChuang Cup’ National College Students Embedded Design Contest (Top 3%)
- 2019.05, Second Prizes, 10th “Blue Bridge Cup” National C/C++ Programming Contest (Top 2%)
🔍 Experience
- 2025.07 - Present, Research Scientist.
- Tencent, Weixin AI
- Research: Agentic RL, Generative Models, Multimodal Understanding
- 2025.08 - 2026.06, Research Intern.
- Tencent, Weixin AI
- Research: Image Generation and Editing
- 2024.01 - 2025.07, Research Intern.
- ByteDance, Intelligent Creation
- Research: Efficient and Controllable Image Generation
- 2022.03 - 2023.03, Research Intern.
- Huawei, Central Media Technology Institute
- Research: Anomaly Detection
💼 Academic Service
- Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR
- Teaching Assistant: Artificial Intelligence at Fudan University
📄 Curriculum Vitae
A brief cv/resume of Hui Zhang.