avatar

Zunnan Xu

M.Eng Student
Tsinghua University
xuzn3 At qq.com


About Me

Hi, I am a student at Tsinghua University. Currently, my research focus on multi-modal learning and generative models. I have broad interests and am always open to explore new and meaningful topics. As my tech expertise deepened, I now focus less on paper quantity and more on rethinking problems and offering simple, effective solutions.

Research Interests

My research topic includes vision-language understanding and video/3D generation.

Project

  1. Arxiv
    HunyuanVideo: A Systematic Framework For Large Video Generative Models
    Hunyuan Foundation Model Team: Zunnan Xu (Core Contributor)
    Arxiv, 2024.
    PDF Code Project Page

Publications

  1. ICCV
    Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
    Zunnan Xu, Zhihong Chen, Yong Zhang, Yibing Song, Xiang Wan, Guanbin Li
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    PDF Code Project Page

  2. NeurIPS
    MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
    Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang, Xiu Li
    Advances in Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code Project Page

  3. CVPR
    HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
    Zunnan Xu, Zhentao Yu, Zixiang Zhou, Jun Zhou, Xiaoyu Jin, Fa-Ting Hong, Xiaozhong Ji, Junwei Zhu, Chengfei Cai, Shiyu Tang, Qin Lin, Xiu Li, Qinglin Lu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    PDF Code Project Page

Services