Melvin Sevi

Hi, I’m Melvin Sevi! I recently graduated from the Master of Research MVA (Mathematics, Vision, Apprentissage) at ENS Paris-Saclay. This program is highly regarded in Europe for its focus on rigorous research in machine learning. Before that, I studied Applied Mathematics and Computer Science at Sorbonne University, which inspired me to push the boundaries of what’s possible in machine learning.

I’m particularly interested in Diffusion Models, Language Models, and Multimodal Learning. Recently, I completed an internship with the Computer Vision & Learning Group at LMU Munich under Prof. Björn Ommer, where I contributed to a CVPR 2025 paper on text-to-image diffusion models. I’m excited to continue exploring opportunities in research, AI projects, and collaborations that combine machine learning with real-world applications.