Ziyue Zeng

Ziyue Zeng

Ph.D. Student

Waseda University

Biography

Ziyue Zeng is a Ph.D. student at Katto Laboratory, Waseda University, advised by Prof. Jiro Katto, and a Research Intern at the CG Lab of Huawei Tokyo Da Vinci Research Institute. His research focuses on generative compression, which uses pretrained generative models as decoders to reconstruct images and videos at ultra-low bitrates, and on understanding compressed representations. His recent work, GVCC, a zero-shot video codec built on pretrained video generative models, will appear at NeurIPS 2026.

He received his M.S. from Watanabe Laboratory, Waseda University, where he also worked on diffusion-based frame interpolation and deepfake detection, and his B.S. in Artificial Intelligence from Chongqing University.

CV: English · 中文

Interests
  • Generative Compression
  • Compressed Representation Understanding
  • Diffusion-based Deepfake Detection
  • Video Generation & Frame Interpolation
  • Audio-driven 3D Talking Heads (3DGS)
Education
  • Ph.D. in Fundamental Science and Engineering (Katto Lab), 2026–present

    Waseda University

  • M.S. in Fundamental Science and Engineering (Watanabe Lab), 2024–2026

    Waseda University

  • B.S. in Artificial Intelligence, 2020–2024

    Chongqing University

News

  • Sep 2026 GVCC was accepted to NeurIPS 2026. [arXiv] [Code]
  • Sep 2026 Started the Ph.D. program at Katto Laboratory, Waseda University.
  • Aug 2026 GVCCTurbo is out on arXiv. [arXiv]
  • Aug 2026 A co-authored paper received the MIRU 2026 Interactive Presentation Award.
  • Jun 2026 Joined the CG Lab of Huawei Tokyo Da Vinci Research Institute as a Research Intern.
  • Mar 2026 FRS was published at IEVC 2026.
  • Dec 2025 TSG was presented as an oral paper at ACM MMAsia 2025.
  • Sep 2025 Bi-AGMI received the Oral Presentation Award at IEEE GCCE 2025.

Publications

All papers, newest first. Filter by type on the publications page.
Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe
NeurIPS 2026 (to appear)
Ziyue Zeng, Dingjie Peng, Xun Su, Hiroshi Watanabe
arXiv:2608.03517, 2026
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
MIRU 2026 (in Japanese) Interactive Presentation Award
Ziyue Zeng, Yui Tatsumi, Hiroshi Watanabe
IEVC 2026
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
IEEE ICCE 2026
Ziyue Zeng, Yupei Guo, Haoyuan Liu, Dingjie Peng, Hiroshi Watanabe
ACM MMAsia 2025 Oral
Ziyue Zeng, Yui Tatsumi, Hiroshi Watanabe
IEEE GCCE 2025 Oral Presentation Award
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
IEEE GCCE 2025 Oral Presentation Award
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
IEEE MMSP 2025
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
MIRU 2025 (in Japanese)
Ziyue Zeng, Fuyuan Xiao
Computational and Applied Mathematics, 2024
Ziyue Zeng, Fuyuan Xiao
Chaos, Solitons & Fractals, 2023

Experience

 
 
 
 
 
Ph.D. Student (Katto Laboratory)
September 2026 – Present Tokyo, Japan
  • Research on generative compression and compressed representation understanding
 
 
 
 
 
Research Intern (CG Lab)
June 2026 – Present Tokyo, Japan
 
 
 
 
 
Research Assistant
April 2025 – April 2026 Tokyo, Japan
  • Applied diffusion-based frame interpolation to video compression and transmission
  • Proposed Bi-AGMI, bidirectional attention-gated keyframe interpolation with diffusion models (IEEE GCCE 2025, Oral Presentation Award)
  • Proposed FRS, motion-aware video segmentation for generative video coding (IEVC 2026)
 
 
 
 
 
Master’s Student (Watanabe Laboratory)
September 2024 – July 2026 Tokyo, Japan
  • Proposed GVCC, zero-shot video compression with a pretrained video generative model as the decoder (NeurIPS 2026), and its rate–compute scheduler GVCCTurbo
  • Proposed TSG, a universal synthesized image detector built on pretrained diffusion features (ACM MMAsia 2025, Oral)
  • Co-authored five papers on scalable image and video coding for humans and machines
  • Collaborated on large-motion frame interpolation with Stable Video Diffusion and ControlNet
 
 
 
 
 
Research Assistant
September 2021 – June 2024 Chongqing, China
  • Research on evidence theory and information fusion
  • Two first-author journal articles (Chaos, Solitons & Fractals; Computational and Applied Mathematics)

Contact

Feel free to reach out by email about research or collaboration.