About

Imad Eddine MAROUF

I am a PhD student at the Institut Polytechnique de Paris, specializing in the continual learning of deep learning models and parameter-efficient training methods. Under the supervision of Dr. Stéphane Lathuilière and Dr. Enzo Tartaglione at the LTCI Laboratory, Télécom Paris, my research explores efficient training approaches for large models and the application of continual learning to vision-language models.

Previously, I interned at the Computer Vision Center (CVC) in Barcelona, working on continual learning for vision-language models under Prof. Joost van de Weijer.

Alongside research, I co-founded CurriboxAI, an AI-powered B2B SaaS platform for personalized curriculum generation — because I believe the real test of ideas is whether they survive contact with the market.

Outside the lab, I compete in SwimRun and endurance races. The discipline of training for the long game maps perfectly onto research: slow compounding, trust the process, keep moving.

Research Focus

2022–

Continual Learning

Stability-plasticity trade-off · Parameter-efficient methods · Vision-language models

2023–

Vision-Language Models

Continual VQA · Attention mechanisms · Cross-modal reasoning

2023–

Parameter-Efficient Fine-Tuning

Adapters · LoRA · Compression · ViT fine-tuning

Education

2021–

PhD — Machine Learning & Continual Learning

Institut Polytechnique de Paris · Télécom Paris

2019–21

MSc — Data & AI

Institut Polytechnique de Paris

2016–19

BSc — Computer Science & Electronics

Sorbonne Université, Paris