Khuê Lê

In Vietnamese: Lê Hữu Điền Khuê.

I am currently an independent researcher, working on deep learning and optimization. If you previously contacted me via my old institutional email addresses, please resend your emails to [email protected].

From June 2020 to May 2023, I was a postdoctoral researcher at the THOTH team of Inria Grenoble, working under Karteek Alahari. From April 2018 to February 2020, I led the AI team of Qopius, a computer vision startup based in Paris (acquired by Trax in February 2020). Prior to that, I obtained a PhD in Computer Science from CentraleSupélec, Université Paris-Saclay, where I was advised by Nikos Paragios.


  • PhD in Computer Science, 2018

    CentraleSupélec & Inria

  • MSc in Applied Mathematics, 2014

    CentraleSupélec & ENS Paris-Saclay

  • MSc in Computer Science, 2012

    École Polytechnique de Tours

  • MSc (Diplôme d'Ingénieur) in Electrical Engineering, 2012

    INSA Centre Val de Loire

  • Specialized Class in Mathematics, 2007

    Quốc-Học Huế High School for the Gifted, Vietnam


Jun 1, 2023 I will serve as an Area Chair for BMVC 2023.
Apr 22, 2022 I was selected as a Highlighted Reviewer of ICLR 2022 (formally Outstanding Reviewer Award).
Oct 26, 2021 Initial release of CRF–a library for dense CRFs. Stay tuned for our semantic segmentation code.
Sep 28, 2021 Our work on regularized Frank-Wolfe for MAP inference has been accepted at NeurIPS 2021.
Jun 25, 2021 I served as an Area Chair for BMVC 2021 (British Machine Vision Conference).

Selected publications

  1. NeurIPS
    Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond
    Đ.Khuê Lê-Huu, Karteek Alahari
    In Advances in Neural Information Processing Systems 2021
  2. CVPR
    Continuous Relaxation of MAP Inference: A Nonconvex Perspective
    Đ.Khuê Lê-Huu, Nikos Paragios
    In IEEE Conference on Computer Vision and Pattern Recognition 2018
  3. CVPR
    Alternating Direction Graph Matching
    Đ.Khuê Lê-Huu, Nikos Paragios
    In IEEE Conference on Computer Vision and Pattern Recognition 2017