Research

Pretrained models are usually adapted once, then frozen. I work on what comes after: adapting them to new tasks and data without erasing what they already know. I mostly use continual learning, model merging and parameter-efficient fine-tuning, on vision and vision-language models. More recently I've worked on data mixtures for LLM pre-training.

Code is on GitHub, and the full list is on Google Scholar.

PhD thesis · 2026

Beyond Fine-Tuning: Continual Adaptation of Pretrained Vision Models

Télécom Paris, Institut Polytechnique de Paris · Advised by Stéphane Lathuilière & Enzo Tartaglione

Papers

Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models

Imad Eddine Marouf, Khalid Oublal, Enzo Tartaglione, Stéphane Lathuilière

NeurIPS 2026 arXiv Code

Summary — DMC

Prompt learning pulls CLIP toward the classes it was trained on, while generalizing to new classes needs it to stay close to its zero-shot features. Both goals compete for the same prompt. DMC gives each goal its own prompt and merges them at test time, at the cost of a single prompt. Evaluated on 11 datasets.

Weighted Ensemble Models Are Strong Continual Learners

Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière

ECCV 2024 · Oral Paper arXiv Code

Summary — CoFiMA

CoFiMA averages model weights across tasks, weighting each parameter by its Fisher information. A simple way to balance keeping old knowledge with learning new tasks.

Service & teaching

  • Reviewer for CVPR, NeurIPS, ECCV, IEEE TMM and IEEE TNNLS
  • Teaching assistant: Deep Learning, Linear Models, Large-Scale ML (Télécom Paris)
  • An Arabic-language YouTube channel explaining AI research