Clément Chadebec
Research Scientist at Stability AI
I am a research scientist at Stability AI working on Deep Generative Models. I have a Ph.D in applied mathematics and machine learning focusing on generative models at INRIA. In particular, I worked on Variational Autoencoders (VAE) and was mostly interested in providing interesting and relevant modellings of their latent space. I also maintain Python libraries trying to democratize those models. Find more on github.
news
| Oct 4, 2023 | I am joining Stability AI as a research scientist. Let’s push the capabilities of generative models 🚀 |
|---|---|
| Jun 29, 2023 | Very happy to annouce that I have successfully defended my PhD thesis! 🥳 Thank you to all the members of the jury and Stéphanie for this amazingly enriching journey! ⛵ |
| Mar 1, 2023 | Thank you G-research for inviting me to present some advances in Variational Autoencoders and how to train them using Pythae! (Slides) |
| Nov 3, 2022 | Thank you IBM Journal Club for inviting me to present my latest NeurIPS papers bringing a geometric perspective on VAEs! (Slides) |
| Sep 16, 2022 | Our paper “Pythae: Unifying Generative Autoencoders in Python – A Benchmarking Use Case” is accepted to NeurIPS 2022! |
| Sep 14, 2022 | Our paper “A Geometric Perspective on Variational Autoencoders” is accepted to NeurIPS 2022! |
| Jul 13, 2022 | Our paper “An Image Feature Mapping Model for Continuous Longitudinal Data Completion and Generation of Synthetic Patient Trajectories” is accepted to DGM4MICCAI Workshop. |
| Jul 1, 2022 | Our paper “Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder” is accepted to IEEE TPAMI! |
| Jun 17, 2022 | After 8 months of long coding nights ☕️ we finally officially release Pythae 🥳, a python library unifying generative autoencoder implementations including vaegan 🥗, vqvae or RAEs. Check out our github repo. |
| Nov 15, 2021 | Thank you so much MIA for inviting me today to present our work on geometry-based VAEs and data augmentation. Thanks again for these great and inspiring discussions! |