Lucas Degeorge
PhD Student
Ecole polytechnique & Ecole des Ponts
I am a PhD student in Computer Vision at VISTA (Ecole polytechnique) and IMAGINE (Ecole des Ponts) labs, under the supervision of Vicky Kalogeiton and David Picard.
My main research interest lies in multi-modal generative models. I am currently working on text-to-image generation.
News
2025
-
Dec 02
I am attending EurIPS 2025 to present our work at the Workshop on Principles of Generative Modeling (PriGM)
-
Oct 29
Our new work MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency is online. Check it out!
-
Oct 08
We release the dataset used in the paper How far can we go with ImageNet for text-to-image generation?. Download them on HuggingFace and use them!
2024
-
Nov 01
I started my PhD at VISTA (Ecole polytechnique) and IMAGINE (Ecole des Ponts) labs.
-
Sep 29
I attended ECCV 2024 in Milano.
Publications
You can also find my work on Google Scholar.
2025
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
arXiv preprint, 2025
[Project Page] [Paper]
How far can we go with ImageNet for text-to-image generation?
arXiv preprint, 2025
[Project Page] [Paper] [Code] [Model] [Dataset]
One-step Diffusion Models with Bregman Density Ratio Matching
EurIPS 2025 Workshop on Principles of Generative Modeling (PriGM), 2025
[Paper]