🧑‍🔬 Celine Hudelot

🏛️ Affiliations

🔬CentraleSupélecGif-sur-Yvette · France2015–2026 · 80 papersEmployment since 2016 · Professeur des Universités, MICScurrent🎓Université Paris-SaclayGif-sur-Yvette · France2015–2026 · 68 paperscurrent🔬Mathématiques et Informatique pour la Complexité et les SystèmesGif-sur-Yvette · France2015–2026 · 56 paperscurrent🎓École Centrale ParisChâtenay-Malabry · France2007–2021 · 38 papers🎓SupélecGif-sur-Yvette · France2015–2021 · 7 papers🎓Télécom ParisPalaiseau · France2006–2008 · 4 papers🔬Centre National de la Recherche ScientifiqueParis · France2006–2008 · 3 papers🔬Institut national de recherche en sciences et technologies du numériqueLe Chesnay-Rocquencourt · France2004–2006 · 3 papers🔬Laboratoire Traitement et Communication de l’InformationPalaiseau · France2006–2008 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs (2024 · 35 citations)
   Logit-based knowledge distillation usually relies on KL divergence. This requires the teacher and the student to share one vocabulary, but LLM families rarely share tokenizers. As a result, practitioners mostly fall back on fine-tuning the student on text the teacher has generated. Drawing on optimal transport, the…
2. EuroBERT: Scaling Multilingual Encoders for European Languages (2025 · 34 citations)
   Bidirectional encoders still power most retrieval, classification and regression systems, but recent modeling progress has mostly gone into decoder-only LLMs.
3. ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios (2026 · 7 citations)
   Real-world retrieval-augmented generation must handle documents whose key content lives in tables, charts and images.
4. Interpreto: An Explainability Library for Transformers (2026)
   Explaining how Transformer language models reach their outputs matters for debugging, detecting bias and safety work.

All works

10 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. ColPali: Efficient Document Retrieval with Vision Language Models ↗arXiv:2407.01449 · no summary yetManuel Faysse et al.2024 · 96 citations
2. CroissantLLM: A Truly Bilingual French-English Language Model ↗arXiv:2402.00786 · no summary yetManuel Faysse et al.2024 · 59 citations
3. Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMsarXiv:2402.12030 · Transactions on Machine Learning Research, January 2025Nicolas Boizard, Kevin El Haddad, Celine Hudelot, et al.2024 · 35 citations
4. EuroBERT: Scaling Multilingual Encoders for European LanguagesarXiv:2503.05500Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves, et al.2025 · 34 citations
5. A French Corpus for Event Detection on Twitter ↗Proceedings of the Twelfth Language Resources and Evaluation Conference · no summary yetBéatrice Mazoyer et al.2020 · 16 citations
6. ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World ScenariosAnnual Meeting of the Association for Computational Linguistics (ACL)António Loison, Quentin Macé, Antoine Edy, et al.2026 · 7 citations
7. Classification automatique de données déséquilibrées et bruitées : application aux exercices de manuels scolaires ↗Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 4 : articles déjà soumis ou acceptés en conférence internationale · no summary yetElise Lincker et al.2023 · 1 citation
8. Interpreto: An Explainability Library for TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Antonin Poché, Thomas Mullor, Gabriele Sarti, et al.2026
9. MALIN : MAnuels scoLaires INclusifs ↗Actes de l'atelier Intelligence Artificielle générative et ÉDUcation : Enjeux, Défis et Perspectives de Recherche 2025 (IA-ÉDU) · no summary yetElise Lincker et al.2025
10. Projet ANR MALIN : MAnuels scoLaires INclusifs ↗Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 6 : projets · no summary yetOlivier Pons et al.2023

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Fanny Jourdan ×2
• Nicolas Boizard ×2
• André F. T. Martins
• Bo Liu
• Caio Corro
• Duarte M. Alves
• Gabriele Sarti
• Joao Alves
• Manuel Faysse
• Nicholas Asher
• Pierre Colombo

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
• Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 4 : articles déjà soumis ou acceptés en conférence internationale
• Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 6 : projets
• Actes de l'atelier Intelligence Artificielle générative et ÉDUcation : Enjeux, Défis et Perspectives de Recherche 2025 (IA-ÉDU)
• Proceedings of the Twelfth Language Resources and Evaluation Conference

🔗 Cited by

Papers of our library cite their works 220 times (of the 149,439 papers whose bibliographies we read); 52 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/celine-hudelot/