Gül Varol is a permanent researcher in the IMAGINE team at École Nationale des Ponts et Chaussées. Previously, she was a postdoctoral researcher at the University of Oxford (VGG). She obtained her PhD from the WILLOW team of Inria Paris and Ecole Normale Superieure (ENS). Her thesis received PhD awards from ELLIS and AFRIF. She regularly serves as an Area Chair at major computer vision conferences, and has served as a Program Chair at ECCV’24. Her research interests cover vision and language applications, including video representation learning, human motion synthesis, and sign languages.

Her Hi! PARIS fellowship project, TRAINR, focuses on developing AI systems that can support and enhance human motor learning.

The project aims to build an interactive AI trainer capable of guiding users in improving their movements over time. Using only video input, the system will deliver personalized, multimodal feedback through visual cues, language instructions, and haptic signals, selecting the most effective way to correct a motion. By leveraging advances in generative models, human motion modeling, and large language models, TRAINR will move beyond rule-based approaches to offer adaptive, user-specific coaching. The project targets applications across physiotherapy, sports, dance, music, and health, with the goal of making high-quality movement training more accessible and continuous.

Learn more about her project here.