Yaohui Wang
Research Scientist at Shanghai AI Laboratory
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYaohui Wang is a research scientist at Shanghai AI Laboratory with 11 years of experience focused on large-scale deep generative models for video, image, and 3D generation. He earned a PhD from Inria where his thesis on generating human videos benefited from a diverse jury and advisors across academia and industry. Yaohui combines strong theoretical grounding in machine learning and computer vision with practical model-building at scale, driving video generation efforts at a leading AI lab. His background spans engineering foundations in microelectronics and applied mathematics to advanced AI research, reflecting a rare cross-disciplinary fluency. He is comfortable translating PhD-level research into production-capable models and has collaborated with industrial partners during internships at Dassault Systèmes and QuantCube. Colleagues describe him as a researcher who blends rigorous experimentation with a focus on scalable generative systems.
11 years of coding experience
Doctor of Philosophy - PhD Machine Learning and Computer Vision, Doctor of Philosophy - PhD Machine Learning and Computer Vision at InriaM2 Artificial Intelligence (ex, M2 AIC), M2 Artificial Intelligence (ex, M2 AIC) at Université Paris-SaclayBachelor of Engineering - BE Microelectronics Engineering, Bachelor of Engineering - BE Microelectronics Engineering at Xidian UniversityDiplôme d'Ingénieur Computer Science and Applied Mathematics, Diplôme d'Ingénieur Computer Science and Applied Mathematics at ensIIESuzhou High School
Github Skills (24)
animator10
re-identification10
animate10
contrastive-learning10
temporal9
generative-adversarial-network9
super-resolution9
diffusion-models9
computer-vision8
video-processing8
stable-diffusion7
deep-learning6
pytorch6
refinement5
action-recognition5
Programming languages (2)
Github contributions (5)
Vchitect/LaVie
Sep 2023 - Nov 2024
[IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
Contributions:56 PRs, 73 pushes, 52 branches in 1 year 1 month
diffusion-models
wyhsirius/g3an-project
Jun 2020 - Feb 2021
[CVPR 2020] G3AN: Disentangling Appearance and Motion for Video Generation
Contributions:42 commits, 55 pushes, 1 branch in 7 months
video-generation
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.