I am currently a second-year Ph.D. student supervised by Prof. Lei Zhang at ASGO, in the School of Computer Science, Northwestern Polytechnical University, Xi’an, China. I am broadly interested in computer vision, with a focus on generative AI.

Prior to my Ph.D. study, I obtained my M.S. degree in Computer Technology in 2024 at Northwestern Polytechnical University from the School of Computer Science at Northwestern Polytechnical University, advised by Prof. Lei Zhang. Before this, I obtained my B.S. degree in Computer Science and Technology from the School of Information Science and Engineering at Yanshan University, Qinhuangdao, China in 2021.

If you are interested in any aspect of me, I am always open to discussions and collaborations. Feel free to reach out to me via Email

🔥 News

• 2025.04: 🎉 One papers are accepted by IJCAI 2025
• 2025.02: 🎉 One papers are accepted by CVPR 2025
• 2025.02: 🤗 will be updated from now!

📝 Publications

Preprint

No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
Dengyang Jiang, Mengmeng Wang, Liuzhuozheng Li, Lei Zhang, Haoyu Wang, Wei Wei, Guang Dai, Yanning Zhang, Jingdong Wang

Project | Code

• Enhances Diffusion Transformers’ representation and generation through self-representation alignment via self-distillation, eliminating external components.

IJCAI2025

Prompt-Free Conditional Diffusion for Multi-object Image Augmentation
Haoyu Wang, Lei Zhang, Wei Wei, Chen Ding, Yanning Zhang

Code

• A framework for multi-object image augmentation using local-global semantic fusion and a reward model-based counting loss.

CVPR2025

Low-Biased General Annotated Dataset Generation
Dengyang Jiang*, Haoyu Wang*, Lei Zhang, Wei Wei, Guang Dai, Mengmeng Wang, Jingdong Wang, Yanning Zhang

Code

• A framework generating low-biased annotated datasets using a fine-tuned diffusion model with bi-level semantic alignment and quality assurance for enhanced backbone generalization.

IEEE TBD

Adapt Anything: Tailor Any Image Classifier across Domains And Categories Using Text-to-Image Diffusion Models
Weijie Chen*, Haoyu Wang*, Shicai Yang, Lei Zhang, Wei Wei, Yanning Zhang, Luojun Lin, Di Xie, Yueting Zhuang

Paper

• Uses text-to-image diffusion models to create synthetic data, enabling image classifier adaptation across domains and categories without real-world source data.

CVPR 2023

Glocal energy-based learning for few-shot open-set recognition
Haoyu Wang*, Guansong Pang*, Peng Wang*, Lei Zhang, Wei Wei, Yanning Zhang

Code

• A novel energy-based model for few-shot open-set recognition using global and local features.

📖 Educations and Experiences

• 2024.03 - present, Northwestern Polytechnical University, Ph.D. in Computer Science and Technology.
• 2023.06 - 2023.09, Hikvision Research Institute, Research Intern.
• 2021.09 - 2024.03, Northwestern Polytechnical University, Master of Computer Technology.
• 2017.09 - 2021.06, Yanshan University, Bachelor of Computer Science and Technology.

💻 Academic Services

• Conference Reviewer: ICCV’25, NeurIPS’25
• Journal Reviewer: PR, JSTAR