Pictured in Muscat, Omman

Fangyikang Wang

Hi there 👋. I am currently a research scientist at Minimax. My research interests include visual generation and the theoretical understanding of generative models. I am active in top international AI conferences such as NeurIPS, ICML, and ICLR.

I received both my bachelor’s and master’s degrees from the Department of Computer Science and Technology, Zhejiang University (浙江大学计算机科学与技术学院), under the supervision of Prof. Hui Qian and Prof. Chao Zhang. I also collaborate closely with Hubery Yin (WeChat Vision), Dr. Li Chen (WeChat Vision), Dr. Zebang Shen (ETH Zürich), and Prof. Mingming Gong (MBZUAI & UniMelb).

🎓Education

2025.11 - 2026.02, Visit Student, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi.
2023.09 - 2026.03, M.Eng. in Computer Science, Zhejiang University, Hangzhou.
2019.09 - 2023.06, B.Eng. in Computer Science, Zhejiang University, Hangzhou.

🏅Honors

China National Scholarship. (2025)
Tsingshan Fellowship. (2025)
NRCC Fellowship of Swiss National Science Foundation. (2025)
Tencent Scholarship. (2024)
Scholarship of Zhejiang University. (2020, 2021, 2022)

💻 Internships

2024.03 - 2025.08, Wechat Vision, Shenzhen

📚Publications

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models

Fangyikang Wang, Hubery Yin, Yue-Jiang Dong, Huminhao Zhu, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li

NeurIPS, 2024
GAD-PVI: A General Accelerated Dynamic-Weight Particle-based Variational Inference Framework

Fangyikang Wang, Huminhao Zhu, Chao Zhang, Hanbin Zhao, Hui Qian

AAAI, 2024
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

Fangyikang Wang, Hubery Yin, Huminhao Zhu, Shaobin Zhuang, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li

ICML, 2025
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin

Fangyikang Wang, Hubery Yin, Huminhao Zhu, Yanlong Tang, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li

ICCV, 2025
Video-GPT via Next Clip Diffusion

Shaobin Zhuang, Zhipeng Huang, Ying Zhuang, Fangyikang Wang, Canmiao Fu, Binxin Yang, Chong Sun, Chen Li, Yali Wang

ICLR, 2026
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision

Shaobin Zhuang, Yiwei Guo, Yanbo Ding, Kunchang Li, Xinyuan Chen, Yaohui Wang, Fangyikang Wang, Ying Zhang, Chen Li, Yali Wang

ICML, 2025
Analyzing and Improving Model Collapse in Rectified Flow Models

Huminhao Zhu, Fangyikang Wang, Tianyu Ding, Qing Qu, Zhihui Zhu

CPAL, 2026
Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective

Zhichao Chen, Haoxuan Li, Fangyikang Wang, Odin Zhang, Hu Xu, Xiaoyu Jiang, Zhihuan Song, Hao Wang

NeurIPS, 2024
Wetok: Powerful discrete tokenization for high-fidelity visual reconstruction

Shaobin Zhuang, Yiwei Guo, Fangyikang Wang, Canmiao Fu, Zhipeng Huang, Zeyue Tian, Ying Zhang, Chen Li, Yali Wang

ICLR, 2026

📝Academic Services

Conference Reviewer:
- NeurIPS 2024-2025
- ICLR 2025-2026
- ICML 2025-2026
- CVPR 2026

✈️Miscellaneous

I love traveling and experiencing different cultures, and my dream is to visit 100 countries (currently 20/100).
I love playing football. I play as a midfielder, and I’m a fan of Luka Modrić.