publications

2025

  1. arXiv
    opensora_teaser.png
    Open-sora 2.0: Training a commercial-level video generation model in $200 k
    Xiangyu Peng, Zangwei Zheng, Chenhui Shen, and 8 more authors
    arXiv preprint arXiv:2503.09642, 2025
    HTML Code
  2. ICCV
    PhotoDoodle_teaser.png
    Arteditor: Learning customized instructional image editor from few-shot examples
    Shijie Huang, Yiren Song, Yuxuan Zhang, and 3 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
    HTML Code
  3. arXiv
    Z-image_teaser.png
    Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
    Huanqia Cai, Sihan Cao, Ruoyi Du, and 8 more authors
    arXiv preprint arXiv:2511.22699, 2025
    HTML Code
  4. arXiv
    liveavatar_teaser.png
    Live avatar: Streaming real-time audio-driven avatar generation with infinite length
    Yubo Huang, Hailong Guo, Fangtai Wu, and 8 more authors
    arXiv preprint arXiv:2512.04677, 2025
    HTML Code

2024

  1. SIGGRAPH Asia
    processpainter_teaser.png
    ProcessPainter: Learning to draw from sequence data
    Yiren Song, Shijie Huang, Chen Yao, and 5 more authors
    In SIGGRAPH Asia 2024 Conference Papers, 2024
    HTML Code