Gaspard Beaudouin

I am currently a Research Scientist Intern at Mistral AI on the Multimodal team, working on Vision Encoder. I am also a Master’s student in Mathematics, Computer Vision and Machine Learning at ENS Paris-Saclay (MVA Master), since September 2025. I completed my undergraduate studies at École nationale des ponts et chaussées in the Mathematics and Computer Science department.

My research interests focus on generative modelling, World Models, flow matching, Representation Learning (JEPA, SSL for videos ..), VLMs and reasoning. I have worked on machine learning with Large Language Models during an internship at Sinequa, more precisely about training for agentic/tool calling abilities (SFT and DPO). I conducted research on flow matching at Harvard AI and Robotics Lab, supervised by Prof. Mengyu Wang.

I am the first author of Delta Rectified Flow Sampling for Text-to-Image Editing, accepted at CVPR 2026. I also co-authored SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing, accepted at NeurIPS 2025. Thanks to Minghan Li, Sung-Hoon Yoon, Jaeyon Kim and Mengyu Wang for their incredible collaboration. I also co-authored PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception, accepted at ICLR 2026, with Kaichen Zhou.

You can find my code and projects on GitHub.