Diffusion Models

Modeling physical change for more realistic image editing

2 min read · Thu, Jul 16 2026

AI Computer Vision Diffusion Models machine learning

A new KAUST-led approach helps AI understand physical change, improving image edits involving light, motion and materials.

Mathematical Modeling of Two-Population Pedestrian Congestion

Noureddine Igbida, Full Professor, Applied Mathematics, Institut de Recherche XLIM, Université de Limoges

Nov 11, 16:00 - 17:00

B1 L3 R3426

Diffusion Models pedestrian dynamics numerical methods

This seminar introduces a novel class of cross-diffusion systems for pedestrian dynamics governed by internal energy minimization under congestion.

Abdelrahman Eldesokey

Postdoctoral Research Fellow

Computer Vision Diffusion Models Vision Foundation Models Multi-Modal Large Language Models

Abdelrahman Eldesokey is a Postdoctoral Fellow at KAUST, working on Generative AI and Computer Vision. His research focuses on diffusion models, multimodal large language models, and vision foundation models, aiming to make generative systems more controllable, interpretable, and reliable.