Hippolyte Gisserot-Boukhlef

PhD Candidate in AI & Research Scientist

pp.jpg

I am a second-year PhD student in artificial intelligence at CentraleSupélec, Université Paris-Saclay, conducting research in collaboration with the Artefact Research Center through a CIFRE partnership.

In today’s rapidly evolving NLP landscape, where generative models often fall short of addressing all challenges and remain highly resource-intensive, my research centers on the role of embeddings and effective representation learning. I investigate the entire pipeline, from pretraining strategies to downstream evaluation, with the aim of identifying the key factors that truly drive model performance.

Feel free to explore my website to learn more about my research, publications, and ongoing projects. Don’t hesitate to get in touch!

news

Jul 08, 2025 Our paper, EuroBERT: Scaling Multilingual Encoders for European Languages is accepted to COLM 2025.
Jul 02, 2025 We release Should We Still Pretrain Encoders with Masked Language Modeling?, a large-scale study comparing causal and bidirectional pretraining objectives for text representation learning.
Jun 23, 2025 EuroBERT is nominated for the 2025 Datacraft Awards in the AI and Society category.

selected publications

  1. llamavsbert.png
    Should We Still Pretrain Encoders with Masked Language Modeling?
    Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Manuel Faysse, and 5 more authors
    2025
  2. eurobert.png
    EuroBERT: Scaling Multilingual Encoders for European Languages
    Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves, and 16 more authors
    2025