Minglei Shi 史明磊

I am a fourth-year undergruate student in the Department of Automation at Tsinghua University, advised by Prof. Jiwen Lu and Prof. Jie Zhou. I am broadly interested in computer vision and deep learning. My current research focuses on efficient AI and generative models.

Email  /  Github

profile photo

News

  • 2024-09: FlowTurbo is accepted to NeurIPS 2024. A nice academic journey with Wenliang Zhao.
  • 2024-06: One Paper is accepted to Particuology. A memorable srt with Zirui Xia and Quan Zou.

    • Publications

    * equal contribution

    		FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
    Wenliang Zhao*, Minglei Shi*, Xumin Yu, Jie Zhou, Jiwen Lu,
    NeurIPS, 2024
    project page / arXiv

    We propose a framework called FlowTurbo to accelerate the sampling of flow-based models while still enhancing the sampling quality.

    		Voidage correction method for DEM study of 3D pebble flows in a bed of cycloidal base
    Zirui Xia, Minglei Shi, Quan Zou,Nan Gui, Xingtuan Yang, Jiyuan Tu, Shengyao Jiang
    Particuology
    ScienceDirect

    A method of voidage correction for DEM-based simulation is proposed.

    Honors and Awards

  • 2024 Zheng Weimin Scholarship, Tsinghua University
  • 2023 Wang Dazhong Scholarship, Tsinghua University
  • 2023 Five-star Volunteer of Tsinghua University
  • 2023 Excellent League Member of Tsinghua University
  • 2023 1st prize in Software Design Competition of Tsinghua University
  • 2022 Excellent Comprehensive Scholarship of Tsinghua University
  • 2022 Outstanding Individual in Social Practice of Tsinghua University
  • 2021 He Dongchang Scholarship, Tsinghua University