Ganggui Ding (丁港归)

Ph.D. Student in Generative AI and Computer Vision

prof_pic.jpg

Taken in Nevşehir

Hello! I am Ganggui Ding, a Ph.D. student at the CAD&CG Lab, College of Computer Science and Technology, Zhejiang University, supervised by Prof. Chunhua Shen and Hao Chen. My research focuses on image and video generation and efficient reasoning for foundation models.

I am currently a Qingyun Program (青云计划) Research Intern with the Game AI Engine team at Tencent IEG, working with Yazhen Yuan on efficient generative frame synthesis for games. In 2025, I was a Research Intern at Huawei 2012 Laboratories, mentored by Dr. Xiaogang Xu, where I worked on generation-based video frame interpolation.

Email / CV / Google Scholar / Github

news

Aug 11, 2026 One paper was published in IEEE TMM! :sparkles:
Jul 07, 2026 One paper was accepted by ICML 2026! :sparkles:
Jul 05, 2026 One paper was accepted by ACL 2026! :sparkles:
May 04, 2026 One paper was accepted by ICASSP 2026 — Oral Presentation! :trophy:
Dec 26, 2025 One paper was published in IJCV! :sparkles:

selected publications

  1. ICML
    speedvfi_thumbnail.png
    SpeedVFI: One-step Diffusion for Efficient Video Frame Interpolation
    Ganggui Ding*, Xiaogang Xu*, Hao Chen, and Chunhua Shen
    In Proceedings of the 43rd International Conference on Machine Learning, 2026
    HTML PDF
  2. ICASSP
    fcvfi_thumbnail.png
    FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation
    Ganggui Ding, Hao Chen, and Xiaogang Xu
    In 2026 IEEE International Conference on Acoustics, Speech and Signal Processing, 2026 Oral Presentation
    DOI arXiv PDF
  3. IJCV
    freercustom_thumbnail.png
    FreerCustom: Training-Free Multi-Concept Customization for Image and Video Generation
    Canyu Zhao*, Ganggui Ding*, Wen Wang*, Zhen Yang, Zide Liu, and 2 more authors
    International Journal of Computer Vision, 2026
    DOI HTML Code
  4. ACL
    mti_thumbnail.png
    Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
    Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, and 2 more authors
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, 2026
    DOI arXiv HTML PDF Code
  5. TMM
    map_thumbnail.png
    MAP: Matting Any Portrait with Depth Priors and Synthetic Data
    Kangyang Xie, Yongtao Ge, Binbin Yang, Chengxiang Fan, Ganggui Ding, and 6 more authors
    IEEE Transactions on Multimedia, 2026
    DOI HTML
  6. AAAI
    channelmerging_thumbnail.png
    Channel Merging: Preserving Specialization for Merged Experts
    Mingyang Zhang, Jing Liu, Ganggui Ding, Linlin Ou, Xinyi Yu, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2025 Oral Presentation
    DOI arXiv HTML PDF
  7. ICCVW
    textsr_thumbnail.png
    Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios
    Chenglu Pan, Xiaogang Xu, Ganggui Ding, Yunke Zhang, Wenbo Li, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2025
    DOI arXiv HTML PDF
  8. CVPR
    freecustom_thumbnail.png
    FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
    Ganggui Ding*, Canyu Zhao*, Wen Wang*, Zhen Yang, Zide Liu, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
    arXiv HTML PDF Code Website
  9. ICLR
    oir_thumbnail.png
    Object-Aware Inversion and Reassembly for Image Editing
    Zhen Yang, Ganggui Ding, Wen Wang, Hao Chen, Bohan Zhuang, and 1 more author
    In International Conference on Learning Representations, 2024
    arXiv HTML PDF Code Website