Nicolas Michel
JSPS Post Doctoral Fellow at CVM, The University of Tokyo.
Tokyo, Japan. nicolasmichel1203@gmail.com nicolas@cvm.t.u-tokyo.ac.jp
Hello there ![]()
Congrats for finding this website amongst all my homonyms. I am a Post Doctoral Researcher at The University of Tokyo, in the Computer Vision and Media Lab, under the supervision of Professor Yamasaki. I was awarded a grant of 2 years from the Japan Society for the Promotion of Science.
My scientific interests lie in Deep Learning and Computer Vision. More specifically Online Continual Learning, Representation Learning, Knowledge Distillation, Prompt Learning. You can find out all my publications on my Google Scholar. You can also find me on Linkedin and GitHub.
My recent work focuses on how to leverage the ever-growing introduction of foundation models in a continuous manner.
News
| Feb 24, 2026 | Our paper titled “Continual Distillation of Teachers from Different Domains” got accepted at CVPR2026! See you in Denver! The final version of this paper will be released soon. |
|---|---|
| Nov 15, 2025 | Two paper got accepted at NeurIPS workshops! One is about a newly defined paradigm of Continual Distillation at will be presented at the CCFM workshop. The other one is a theoretical work linking representation learning on the hypersphere and cross-entropy based loss. This will be presented at the NeurReps workshop. |
| Sep 27, 2024 | I will start a PostDoc position in November 2024 at the University of Tokyo, in the Computer Vision and Media Lab, under the supervision of Professor Yamasaki. Thank you again for welcoming me! |
| Sep 27, 2024 | Our paper titled “Dealing with Synthetic Data Contamination in Online Continual Learning” has been accepted at the NeurIPS 2024! |
| Sep 15, 2024 | I will defend my PhD thesis “Online Continuous Image Classification with Memory-based Methods: Application to YouTube data” at ESIEE Paris on the 15th of October, 2024! |
Selected publications
- Continual Distillation of Teachers from Different DomainsIn The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2026
-
Rethinking Momentum Knowledge Distillation in Online Continual LearningIn The Forty-first International Conference on Machine Learning (ICML) , 2024 -
Improving Plasticity in Online Continual Learning via Collaborative LearningIn The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024 -
Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual LearningIn The 38th Annual AAAI Conference on Artificial Intelligence (AAAI) , 2024