Ao Li (李奡)

Hi! I am a first-year master at Tsinghua University, majoring in Artificial Intelligence. Now I am doing research advised by Prof. Yansong Tang and Prof. Jiwen Lu at THU-IVG Lab. I received my B.S. degree in Artificial Intelligence from Beijing Normal University in 2024. Before that, I worked as an intern in BNU-IVC Lab advised by Prof. Yongzhen Huang and Prof. Saihui Hou, doing research in the field of gait recognition.

My research interests lie in the fields of Human-Robot Interaction. My current research focuses on human mesh recovery and human-object interaction.

Email  /  Github

profile photo

Education

dise Tsinghua University, 2024.09 - Now
  • M.S. degree in Artificial Intelligence
  • Shenzhen International Graduate School
  • dise Beijing Normal University, 2020.09 - 2024.06
  • B.S. degree in Artificial Intelligence
  • School of Artificial Intelligence
  • Industrial Experience

    dise Tencent Robotics-X, Shenzhen, China. 2025.05 - Now.
  • Project: Human Understanding and Human-Robot Interaction.
  • Work with Dr. Yonggen Ling
  • News

  • 2025-01: 1 paper about Human-Object Interaction Reconstruction was accepted on ICCV 2025 .
  • 2025-01: 1 paper about Efficient Image Enhancement was accepted on ICLR 2025 .
  • 2024-06: Invited as a Spotlight Presenter at "MANGO" workshop in CVPR 2024.
  • 2024-04: We are happy that our work, FlowIE, has been nominated as an oral in CVPR 2024!
  • 2024-02: 2 papers about Human Mesh Recovery and Image Enhancement were accepted on CVPR 2024 !
  • Recent Selected Publications

    (*Equal Contribution, #Corresponding Author)

    dise ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion
    Ao Li, Jinpeng Liu, Yixuan Zhu, Yansong Tang
    IEEE International Conference on Computer Vision (ICCV),2025
    Comming Soon

    We propose ScoreHOI, a framework for human-object interaction reconstruction via score-guided diffusion to enhance the physical plausibility.

    dise InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
    Yixuan Zhu, Haolin Wang, Ao Li, Wenliang Zhao,Yansong Tang, Jingxuan Niu, Lei Chen, Jie Zhou, Jiwen Lu
    The Thirteenth International Conference on Learning Representations (ICLR),2025
    [Paper]

    We propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps.

    dise DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
    Yixuan Zhu*, Ao Li*, Yansong Tang#, Wenliang Zhao, Jie Zhou, Jiwen Lu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    [arXiv] [Code] [Project Page]

    We propose a new method to exploit diffusion priors for human mesh recovery (HMR) in occlusion and crowded scenarios.

    dise FlowIE: Efficient Image Enhancement via Rectified Flow
    Yixuan Zhu, Wenliang Zhao, Ao Li, Yansong Tang#, Jie Zhou, Jiwen Lu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    Oral Presentation
    [arXiv] [Code]

    We proposed a unified framework for various efficient image enhancement tasks with generative diffusion priors.

    Selected Honors and Awards

  • Outstanding Bachelor Graduate of Beijing, 2024.
  • Potential Star Award - Meituan 2nd Low-Altitude Economy UAV Management Challenge (Innovation Track), 2024.