Quentin Bammey is a researcher and an Assistant Professor at Télécom Paris, within LTCI, IDS, and the Images team, and a Hi! PARIS Fellow.

His research focuses on 3D reconstruction and generation, generative models, image processing, multimedia forensics, and reproducible research. He is known for introducing the concept of Positional Learning, a technique used to reveal, mimic, and analyze hidden frequency components in images, with applications in forgery detection and AI-generated image detection.

Before joining Télécom Paris, he worked at EPFL’s Image and Visual Representation Lab and at École Normale Supérieure Paris-Saclay, Université Paris-Saclay, Centre Borelli, and CNRS. He obtained his PhD in applied mathematics in 2021. Some of his image forensics methods are integrated into the InVID-WeVerify verification plugin for fact-checkers, recognized by the Poynter Institute as one of the most powerful tools for spotting misinformation online. He is also strongly involved in open science and reproducible research through the IPOL journal and demo system. He is the co-founder and main organizer of the IPOL MLBriefs workshop and hackathon, launched in 2022. Between 2022 and 2024, he also contributed to the coordination and development of the BrevetAI platform, designed to support hands-on AI training and public outreach as part of the SaclAI-School program at Université Paris-Saclay.