Mehdi Cherti

Postdoc at Jülich Supercomputing Centre (JSC) / LAION team, Germany

I received my PhD in Machine Learning from Université Paris Saclay in 2018. Currently, I am a postdoctoral researcher at Jülich Supercomputing Center (JSC) and part of the LAION team.

I am interested in large scale training, generative models, models that can learn efficiently (transfer learning, few-shot learning, meta-learning) and generalize out of their training distribution (OOD generalization), enabling broader and more robust applicability.


Selected Publications

Reproducible scaling laws for contrastive language-image learning

Mehdi Cherti, Romain Beaumon, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, Jenia Jitsev

CVPR 2023

Code / Poster / Slides / Video

LAION-5B: An open large-scale dataset for training next generation image-text models

Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, Jenia Jitsev

NeurIPS 2022 Datasets and Benchmarks track ( Outstanding paper award)

OpenReview / Poster / Video

Effect of large-scale pre-training on full and few-shot transfer learning for natural and medical images

Mehdi Cherti, Jenia Jitsev

Short version: Medical Imaging Meets NeurIPS 2021 Workshop
Long version: IJCNN 2021

Code / Poster

Out-of-class novelty generation

Mehdi Cherti, Balázs Kégl, Akın Kazakçı

ICLR 2017 workshop

Code / Web / Poster

De novo drug design with deep generative models: an empirical study

Mehdi Cherti, Balázs Kégl, Akın Kazakçı

ICLR 2017 workshop


This page was built using the Academic Project Page Template.
This website is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.