Marc Lafon

PhD Student in Deep Learning at Cnam Paris - AI/ML Consultant

prof_pic.jpg

Office 37.0E.36

2 rue Conté

Paris, France

I am a PhD student in Deep Learning at Le Cnam in the Machine Learning team advised by Prof. Nicolas Thome and Clément Rambour. The focus of my PhD is on the efficient adaptation of deep learning foundation models with a particular interest in improving their robustness. Lately, I have focused on improving the trade-off between accuracy and robustness for few-shot learning methods, e.g. prompt learning, of vision-language foundation models like CLIP.

news

Jun 15, 2025 Our work on failure prediction of vision-language models has been accepted at ICCV 2025 :star: !
Oct 15, 2024 Our work on spatio-temporal encodings for Transformers on dynamic graphs has been accepted at NeurIPS 2024 :smiley: !
Jun 12, 2024 Our work on few-shot adaptation of vision-language models through prompt learning has been accepted at ECCV 2024 :sparkles: :tada: !
Apr 22, 2023 Our work on out-of-distribution detection using energy-based models has been accepted at ICML 2023 :tada: !

selected publications

  1. ICCV
    ViLU: Learning Vision-Language Uncertainties for Failure Prediction
    Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez, and 6 more authors
    International Conference on Computer Vision (ICCV 2025), 2025
  2. ECCV
    GalLoP: Learning Global and Local Prompts for Vision-Language Models
    Marc Lafon, Elias Ramzi, Clément Rambour, and 2 more authors
    Proceedings of the 18th European Conference on Computer Vision, Milan, Italy, 2024, 2024
  3. ICML
    Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection
    Marc Lafon, Elias Ramzi, Clément Rambour, and 1 more author
    Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023, 2023
  4. ICML
    Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition
    Charles Corbière, Marc Lafon, Nicolas Thome, and 2 more authors
    ICML Workshop on Uncertainty and Robustness in Deep Learning, 2021