I am an AI reserach engineer at Panocular AI, working on developing, training and evaluation vision-language models. Prior to that, I was a research scientist and a member of the Decision Making team of the Tuebingen AI center from Mai 1, 2021 to April 30, 2024. I obtained my PhD at the CREATIS laboratory under the supervision of Carole Lartizien and Ievgen Redko.

I am reachable at sofiane.myLastName[At]gmail.com (my first name has a different spelling on my e-mail).

Publications

• Meta Learning in Bandits within shared affine Subspaces, AISTATS 2024 (2nd author)
• Hypothesis Transfer in Bandits by Weighted Models, ECML PKDD 2022 (2nd author)
• Contributions to unsupervised domain adaptation : Similarity functions, optimal transport and theoretical guarantees
• Margin-aware Adversarial Domain Adaptation with Optimal Transport, ICML 2020
• A Swiss Army Knife for Minimax Optimal Transport, ICML 2020
• Analyse théorique de l’apprentissage avec des fonctions de similarités pour l’adaptation de domaine, CAp 2018 (France)
• On learning a large margin classifier for domain adaptation based on similarity functions, CAp 2019 (France)
• Revisiting (\epsilon, \gamma, \tau)-similarity learning for domain adaptation, NeurIPS 2018

Preprints

• Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization, arXiv preprint, 2022.

Reviewing:

• ICML 2021
• Neurips 2021: Outstanding Reviewer (Top 8% of reviewers).
• ICLR 2022
• Neurips 2023: Outstanding Reviewer (Top 8% of reviewers).
• TMLR

Some useful links:

A list of links that I found were useful during my PhD years: tools, GitHub repositories, dataset download links …