Imad Eddine Marouf

I'm an AI researcher working on continual learning: how pretrained models can keep adapting to new tasks without forgetting what they already know. I recently completed my PhD at Télécom Paris, advised by Stéphane Lathuilière and Enzo Tartaglione. During the PhD I was a student researcher on Google DeepMind's Gemma team, working on data mixtures for pre-training, and a visiting researcher at the Computer Vision Center in Barcelona, hosted by Joost van de Weijer.

I also write about research and what I learn along the way, including from building CurriboxAI. I'm open to research roles on LLM and vision-language model training: .

Portrait of Imad Eddine Marouf

News

  • Defended my PhD at Télécom Paris.
  • DMC was accepted at NeurIPS 2026.
  • Joined Google DeepMind's Gemma team as a student researcher.
  • QUAD was accepted at ICCV 2025.
  • PLASTIC was accepted at CoLLAs 2025.
Show older
  • Presented CoFiMA as an oral at ECCV 2024 in Milan.
  • Started a research visit at the Computer Vision Center in Barcelona, with Joost van de Weijer.
  • Presented MiMi at WACV 2024.

Publications

Research →