Victor Besnier
Research Scientist - Deep Learning at Valeo
Prague, Prague, France
Summary
👤
Senior🎓
Top SchoolVictor Besnier is a research scientist specializing in computer vision and deep learning with eight years of experience focused on image and video generation, real-time model deployment, and safety-critical perception for autonomous vehicles. Based at Valeo in Prague, he advances SOTA methods—Diffusion Models, Masked Non-Autoregressive Transformers and GANs—publishing at ICCV, CVPR and ICIP and bridging academic rigor from his École des Ponts PhD with hands-on embedded deployment. His PhD work on out-of-distribution detection for segmentation underpins practical reliability improvements for real-time automotive systems. Victor combines generative modeling expertise with latency-aware engineering to deliver diverse, high-quality outputs that meet inference-speed constraints. He brings a track record of turning GAN and diffusion research into production-oriented solutions for safety-critical contexts.
8 years of coding experience
Master, Computer Science, Mention Bien, Master, Computer Science, Mention Bien at Université Pierre et Marie CurieDoctorat, Artificial Intelligence, Doctorat, Artificial Intelligence at École des Ponts ParisTechProgramming languages (2)
Github contributions (5)
llvictorll/AS
Dec 2018 - Oct 2023
Contributions:14 pushes, 1 branch in 4 years 10 months
valeoai/Halton-MaskGIT
Oct 2023 - Mar 2025
Contributions:1 review, 2 PRs, 10 pushes in 1 year 5 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.