Ke Wang

prof_pic.jpg
k.wang@epfl.ch

I am a PhD student at at EPFL (Swiss Federal Institute of Technology in Lausanne), under the supervision of Prof. Pascal Frossard. My research interests cover improving machine learning techniques in terms of efficiency, reliability and robustness.

Before starting my PhD, I completed my MSc in Electrical Engineering with specialization in Data Science and Systems from EPFL, and my BSc in Electronic Information Science and Technology from University of Electronic Science and Technology of China.

I was also an intern in Oracle Labs in 2022 and Chinese Academy of Sciences in 2019.

I am from Chengdu, Sichuan in Southwest China (where the pandas are from). In my free time, I like football, spicy food, running by Lake Geneva and skiing.

selected publications

  1. arxiv-logo.png
    LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
    Ke Wang* , Nikolaos Dimitriadis* , Alessandro Favero , and 3 more authors
    In In submission , 2024
  2. ICML-logo.svg
    Localizing Task Information for Improved Model Merging and Compression
    Ke Wang* , Nikolaos Dimitriadis* , Guillermo Ortiz-Jimenez , and 2 more authors
    In International Conference on Machine Learning (ICML) , 2024
  3. ICML-logo.svg
    Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels
    Ke Wang , Guillermo Ortiz-Jimenez , Rodolphe Jenatton , and 3 more authors
    In International Conference on Machine Learning (ICML) , 2024
  4. bmvc-logo.png
    CLAD: A Contrastive Learning based Approach for Background Debiasing
    Ke Wang , Harshitha Machiraju , Oh-Hyeon Choung , and 2 more authors
    In British Machine Vision Conference (BMVC) , 2022