Mehdi Cherti

Postdoc at Jülich Supercomputing Centre (JSC), Germany

I received my PhD in Machine Learning from Université Paris Saclay in 2018 followed by a Postdoc at Mines ParisTech. Currently, I am a postdoctoral researcher at Jülich Supercomputing Center (JSC), within the Scalable Learning and Multi-Purpose AI (SLAMPAI) Lab. I am also part of the LAION team.

My research focuses on deep generative models and how to use them to learn representations that can help to design genuinely novel and useful objects, with various applications to computational creativity and scientific domains.

I am also generally interested in learning 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.

News

Feb 27, 2023 Our “Reproducible scaling laws for contrastive language-image learning” paper was accepted to CVPR 2023! In the repo, we open-source all the models and we will provide soon as well all details about pre-training and evaluation details for reproducibility.
Nov 21, 2022 Our “LAION-5B: An open large-scale dataset for training next generation image-text models” received an Outstanding paper award On NeurIPS Datasets and Benchmarks track.
Oct 13, 2022 Our “LAION-5B: An open large-scale dataset for training next generation image-text models” (announcement page, arXiv, poster ) paper was accepted at NeurIPS 2022 Datasets and Benchmarks track.
Jul 1, 2022 Effect of large-scale pre-training on full and few-shot transfer learning for natural and medical images
Jun 9, 2021 New preprint Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images, where we conduct large-scale pre-training on large source datasets of either natural (ImageNet-21k/1k) or medical chest X-Ray images and compare full and few-shot transfer using different target datasets from both natural and medical imaging domains. Code is available here.

Selected publications

  1. Reproducible scaling laws for contrastive language-image learning
    Cherti, Mehdi, Beaumont, Romain, Wightman, Ross, Wortsman, Mitchell, Ilharco, Gabriel, Gordon, Cade, Schuhmann, Christoph, Schmidt, Ludwig, and Jitsev, Jenia
    arXiv preprint arXiv:2212.07143 2022
    PDF
  2. LAION-5B: An open large-scale dataset for training next generation image-text models
    Schuhmann, Christoph, Beaumont, Romain, Vencu, Richard, Gordon, Cade W, Wightman, Ross, Cherti, Mehdi, Coombes, Theo, Katta, Aarush, Mullis, Clayton, Wortsman, Mitchell, Schramowski, Patrick, Kundurthy, Srivatsa R, Crowson, Katherine, Schmidt, Ludwig, Kaczmarczyk, Robert, and Jitsev, Jenia
    In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track 2022
    PDF
  3. Effect of large-scale pre-training on full and few-shot transfer learning for natural and medical images
    Cherti, Mehdi, and Jitsev, Jenia
    arXiv preprint arXiv:2106.00116 2021
    PDF
  4. Optimization of classification and regression analysis of four monoclonal antibodies from Raman spectra using collaborative machine learning approach
    Le, Laetitia Minh Maı̈, Kégl, Balázs, Gramfort, Alexandre, Marini, Camille, Nguyen, David, Cherti, Mehdi, Tfaili, Sana, Tfayli, Ali, Baillet-Guffroy, Arlette, Prognon, Patrice, and others,
    Talanta 2018
    PDF
  5. The RAMP framework: from reproducibility to transparency in the design and optimization of scientific workflows
    Kégl, Balázs, Boucaud, Alexandre, Cherti, Mehdi, Kazakci, Akin, Gramfort, Alexandre, Lemaitre, Guillaume, Bossche, Joris, Benbouzid, Djalel, and Marini, Camille
    2018
    PDF
  6. Spurious samples in deep generative models: bug or feature?
    Kégl, Balázs, Cherti, Mehdi, and Kazakçı, Akın
    arXiv preprint arXiv:1810.01876 2018
    PDF
  7. Digits that are not: Generating new types through deep neural nets
    Kazakçı, Akın, Mehdi, Cherti, and Kégl, Balázs
    In Proceedings of the Seventh International Conference on Computational Creativity 2016
    PDF
  8. Out-of-class novelty generation: an experimental foundation
    Cherti, Mehdi, Kégl, Balázs, and Kazakçı, Akin
    In ICLR 2017 workshop
    PDF
  9. De novo drug design with deep generative models: an empirical study
    Cherti, Mehdi, Kégl, Balázs, and Kazakçı, Akın
    In ICLR 2017 workshop
    PDF