Ziyun Zeng

Department of Electrical & Computer Engineering, National University of Singapore
image

I am a third-year PhD student at Show Lab, National University of Singapore (NUS), advised by Prof. Mike Shou. Previously, I received my MEng degree at Tsinghua University (THU), under the supervision of Prof. Shu-Tao Xia. And I received my BEng degree at Sichuan University (SCU). My current research interests include Video Generation & Understanding, Visual Editing, Multi-modal Large Language Model, etc. Beyond these topics, I also published several papers regarding multimedia retrieval and visual hashing.

News

  • [2026.09] Two papers are accepted to NeurIPS 2026 (main and E&D tracks).
  • [2026.01] One paper is accepted to ICLR 2026.
  • [2025.02] One paper is accepted to CVPR 2025.
  • [2024.08] Join Show Lab @ NUS as a PhD candidate!
  • [2024.01] One paper is accepted to ICLR 2024.
  • [2024.01] One paper is accepted to IJCV.
  • [2023.12] One paper is accepted to Pattern Recognition Letters.
  • [2023.12] One paper is accepted to AAAI 2024.
  • [2023.07] One paper is accepted to ACM MM 2023.
  • [2023.02] One paper is accepted to CVPR 2023.
  • [2022.11] One paper is accepted to AAAI 2023.
  • [2022.10] Two papers are accepted to BMVC 2022 with one Oral presentation.
  • [2022.01] One paper is accepted to WWW 2022.
  • [2021.12] One paper is accepted to AAAI 2022 as an Oral presentation.
  • [2021.10] One paper is accepted to BMVC 2021.

Publications [Google Scholar]

✱ Equal Contribution      ✉ Corresponding Author
(Co-)First Author Works:
  • [2026] Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
    Ziyun Zeng, Yiqi Lin, Guoqiang Liang, Mike Zheng Shou✉
    NeurIPS E&D [Project] [Paper] [Code] GitHub stars
  • [2026] Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
    Ziyun Zeng, Junhao Zhang, Wei Li, Mike Zheng Shou✉
    ICLR [Project] [Paper] [Code] GitHub stars
  • [2025] LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
    Joya Chen✱, Ziyun Zeng✱, Yiqi Lin✱, Wei Li, Zejun Ma, Mike Zheng Shou✉
    CVPR [Project] [Paper] [Code] GitHub stars
  • [2024] Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
    Ziyun Zeng✱, Jinpeng Wang✱, Bin Chen✉, Tao Dai, Shu-Tao Xia, Zhi Wang
    Pattern Recognition Letters [Paper]
  • [2023] TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale
    Ziyun Zeng, Yixiao Ge, Zhan Tong, Xihui Liu, Shu-Tao Xia, Ying Shan
    Tech Report [Paper] [Code] GitHub stars
  • [2023] Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
    Ziyun Zeng✱, Yuying Ge✱, Xihui Liu, Bin Chen✉, Ping Luo, Shu-Tao Xia, Yixiao Ge✉
    CVPR [Paper] [Code] GitHub stars
  • [2022] Motion-Aware Graph Reasoning Hashing for Self-supervised Video Retrieval
    Ziyun Zeng, Jinpeng Wang, Bin Chen✉, Yuting Wang, Shu-Tao Xia
    BMVC [Paper]
Collaborations:
  • [2026] Long Video Instructional Editing in the Wild
    Yiqi Lin, Guoqiang Liang, Ziyun Zeng, Zechen Bai, Yanzhe Chen, Mike Zheng Shou✉
    NeurIPS [Project] [Paper] [Code]
  • [2026] Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
    Yiqi Lin, Guoqiang Liang, Ziyun Zeng, Zechen Bai, Yanzhe Chen, Mike Zheng Shou✉
    Tech Report [Project] [Paper] [Code] GitHub stars
  • [2024] Making LLaMA SEE and Draw with SEED Tokenizer
    Yuying Ge✱, Sijie Zhao✱, Ziyun Zeng, Yixiao Ge✉, Chen Li, Xintao Wang, Ying Shan
    ICLR [Project] [Paper][Code] GitHub stars
  • [2024] Hugs Bring Double Benefits: Unsupervised Cross-Modal Hashing with Multi-granularity Aligned Transformers
    Jinpeng Wang, Ziyun Zeng, Bin Chen✉, Yuting Wang, Dongliang Liao, Gongfu Li, Yiru Wang, Shu-Tao Xia
    IJCV [Paper]
  • [2024] GMMFormer: Gaussian-Mixture-Model based Transformer for Efficient Partially Relevant Video Retrieval
    Yuting Wang, Jinpeng Wang, Bin Chen✉, Ziyun Zeng, Shu-Tao Xia
    AAAI [Paper]
  • [2023] Planting a SEED of Vision in Large Language Model
    Yuying Ge✱, Yixiao Ge✱ ✉, Ziyun Zeng, Xintao Wang, Ying Shan
    Tech Report [Paper] [Code] GitHub stars
  • [2023] MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation
    Jinpeng Wang, Ziyun Zeng, Yunxiao Wang, Yuting Wang, Xingyu Lu, Tianxiang Li, Jun Yuan, Rui Zhang, Hai-Tao Zheng, Shu-Tao Xia
    ACM MM [Paper][Code] GitHub stars
  • [2023] Contrastive Masked Autoencoders for Self-Supervised Video Hashing
    Yuting Wang✱, Jinpeng Wang✱, Bin Chen✉, Ziyun Zeng, Shu-Tao Xia
    AAAI [Paper] [Code] GitHub stars
  • [2022] Hugs Are Better Than Handshakes: Unsupervised Cross-Modal Transformer Hashing with Multi-granularity Alignment
    Jinpeng Wang, Ziyun Zeng, Bin Chen✉, Yuting Wang, Dongliang Liao✉, Gongfu Li, Yiru Wang, Shu-Tao Xia
    BMVC (Oral) [Paper]
  • [2022] Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
    Jinpeng Wang, Bin Chen✉, Dongliang Liao✉, Ziyun Zeng, Gongfu Li, Shu-Tao Xia, Jin Xu
    WWW [Paper] [Code] GitHub stars
  • [2022] Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
    Jinpeng Wang, Ziyun Zeng, Bin Chen✉, Tao Dai, Shu-Tao Xia
    AAAI (Oral) [Paper] [Code] GitHub stars
  • [2021] SwinFGHash: Fine-grained Image Retrieval via Transformer-based Hashing Network
    Di Lu, Jinpeng Wang, Ziyun Zeng, Bin Chen✉, Shudeng Wu, Shu-Tao Xia
    BMVC [Paper]
蜀ICP备2021016490号-1