Fu-Yun Wang
fywang@link.cuhk.edu.hk

Fu-Yun Wang (Pronounced as "Foo-Yoon Wahng" IPA: [fu˧˥ yn˧˥ wɑŋ]) is a second-year Ph.D. student at MMLab@CUHK, supervised by Professor Xiaogang Wang and Professor Hongsheng Li.

Prior to this, he obtained his B.Eng. from Nanjing University in 2023 with first-class honor, supervised by Professor Han-Jia Ye and Dr. Da-Wei Zhou in the LAMDA Group.

Currently, he works on diffusion acceleration. He is also interested in building innovative generative vision applications. He works closely with Dr. Zhaoyang Huang.

Github / Google Scholar

Talks

Preprint

Stable Consistency Tuning: Understanding and Improving Consistency Models

Fu-Yun Wang, Zhengyang Geng, Hongsheng Li
Deep Generative Model in Machine Learning: Theory, Principle and Efficacy. ICLR 2025 Workshop.
arXiv  •   GitHub

Publication

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

Fu-Yun Wang, Ling Yang, Zhaoyang Huang, Mengdi Wang, Hongsheng Li
Thirteenth International Conference on Learning Representations. ICLR 2025.
Understanding and extending rectification (reflow) to general diffusion models.
arXiv  •   GitHub  •   Poster

Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models

Fu-Yun Wang, Yunhao Shui, Jingtan Piao, Keqiang Sun, Hongsheng Li
Thirteenth International Conference on Learning Representations. ICLR 2025.
General, simple yet effective idea for strengthened diffusion preference optimization.
Paper  •   Poster

InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation

Zhixin Lai, Keqiang Sun, Fu-Yun Wang, Dhritiman Sagar, Erli Ding
Thirteenth International Conference on Learning Representations. ICLR 2025.
Industrial-level real-time portrait editor.
Paper

Phased Consistency Model

Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman, Dazhong Shen, Peng Gao, Michael Lingelbach, Keqiang Sun, Weikang Bian, Guanglu Song, Yu Liu, Xiaogang Wang, Hongsheng Li
Conference on Neural Information Processing Systems. NeurIPS 2024.
Few-step text-to-image and text-to-video generation.
Project Page  •   Github  •   Paper   •   Poster

OSV: One Step is Enough for High-Quality Image to Video Generation

Xiaofeng Mao*, Zhengkai Jiang*, Fu-Yun Wang*, Wenbing Zhu, Jiangning Zhang, Hao Chen, Mingmin Chi, Yabiao Wang
IEEE Conference on Computer Vision and Pattern Recognition.CVPR 2025.
arXiv

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

Weikang Bian, Zhaoyang Huang, Xiaoyu Shi, Yijin Li, Fu-Yun Wang, Hongsheng Li
IEEE Conference on Computer Vision and Pattern Recognition.CVPR 2025.
arXiv  •   Project Page

AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data

Fu-Yun Wang, Zhaoyang Huang, Weikang Bian, Xiaoyu Shi, Keqiang Sun, Guanglu Song, Yu Liu, Hongsheng Li
Special Interest Group on Computer Graphics and Interactive Techniques Asia. SIGGRAPH Asia 2024 Technical Communications.
Project Page  •   Github   •   arXiv

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

Fu-Yun Wang, Zhaoyang Huang, Qiang Ma, Xudong Lu, Weikang Bian, Yijin Li, Yu Liu, Hongsheng Li
European Conference on Computer Vision. ECCV 2024.
ECCV 2024 Oral Presentation
Project Page  •   Paper

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

Fu-Yun Wang, Xiaoshi Wu, Zhaoyang Huang, Xiaoyu Shi, Dazhong Shen, Guanglu Song, Yu Liu, Hongsheng Li
European Conference on Computer Vision. ECCV 2024.
Project Page  •   Paper  •   arXiv  •   GitHub

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Xiaoyu Shi*, Zhaoyang Huang*, Fu-Yun Wang*, Weikang Bian*, Dasong Li, Yi Zhang, Manyuan Zhang, Kachun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li
Special Interest Group on GRAPHics and Interactive Techniques.SIGGRAPH 2024.
SIGGRAPH 2024 Technical Papers Trailer
Project Page  •   GitHub  •   arXiv

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance

Dazhong Shen, Guanglu Song, Zeyue Xue, Fu-Yun Wang, Yu Liu,
IEEE Conference on Computer Vision and Pattern Recognition.CVPR 2024.
arXiv  •   GitHub

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
European Conference on Computer Vision. ECCV 2022.
Github  •   arXiv  •  

BEEF: Bi-Compatible Class-Incremental via Energy-Based Expansion and Fusion

Fu-Yun Wang, Da-Wei Zhou, Liu Liu, Han-Jia Ye, Yatao Bian, De-Chuan Zhan, Peilin Zhao
Eleventh International Conference on Learning Representations. ICLR 2023.
Github  •   Paper

FACT: Forward Compatible Few-Shot Class-Incremental Learning

Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, Shiliang Pu, De-Chuan Zhan
IEEE Conference on Computer Vision and Pattern Recognition.CVPR 2022.
Github  •   arXiv  •  

PyCIL: A Python Toolbox for Class-Incremental Learning

Da-Wei Zhou*, Fu-Yun Wang*, Han-Jia Ye, De-Chuan Zhan
SCIENCE CHINA Information Sciences. SCIS.
Github  •   arXiv  •   Media   •  

Awards & Honor

  • 2023 HKPFS (Hong Kong PhD Fellowship Scheme)
  • 2023 Outstanding Graduate of Nanjing University
  • 2023 Outstanding Undergraduate Thesis of Nanjing University
  • 2022 Sensetime Scholarship
  • 2022 Huawei Scholarship
  • 2021 National Scholarship

Sevices

    Reviewer of TPAMI, TCSVT, PRL, CVPR 2023, NeurIPS 2023, ICLR 2024, CVPR 2024, ICML 2024, ECCV 2024, BMVC 2024, ICLR 2025, CVPR 2025