News

  • 2026.06 Successfully concluded the GigaWorld Track of the GigaBrain Challenge (CVPR 2026 Workshop). link
  • 2025.07 Two papers accepted to CVPR 2025 (HumanDreamer, SpeeD).
  • 2024.07 One paper accepted to ECCV 2024 (InfoGrowth).
  • 2024.05 Open-Sora has been released.

Selected Work

  • A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
    CVPR 2025
    A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
    Kai Wang, Mingjia Shi, Yukun Zhou, et al.
    A plug-and-play, architecture-agnostic approach that achieves 3× acceleration across diffusion architectures, datasets, and tasks.
    ProjectCodePaper
  • Dataset Growth
    ECCV 2024
    Dataset Growth
    Ziheng Qin, Zhaopan Xu, Yukun Zhou, et al.
    Improves data quality and efficiency on both single-modal and multi-modal tasks with an efficient, scalable design.
    CodePaper
  • GigaWorld-0: World Models as Data Engine to Empower Embodied AI
    Technical Report
    GigaWorld-0: World Models as Data Engine to Empower Embodied AI
    GigaAI
    A unified world model framework designed explicitly as a data engine for Vision-Language-Action learning. Responsible for training and evaluating the video foundation model, downstream fine-tuning, and inference acceleration.
    ProjectCodePaperModel
  • Open-Sora: Democratizing Efficient Video Production for All
    Open-Source Project
    Open-Sora: Democratizing Efficient Video Production for All
    HPC-AI Tech
    An open-source video generation model with full training, inference, data preparation code and model weights. Project participant as an intern at Luchen Technology.
    CodePaperModel

Education

  • B.Eng., Xidian University, 2025