Zilong Huang is a research scientist with 12 years of experience specializing in computer vision and multimodal deep learning, currently leading large vision model and multimodal model research at TikTok. He has a strong track record of publishing and shipping research—developing Mobile Transformer variants (CVPR22, ICLR23, IJCV25) and NeRF/Text-to-Motion systems—and has taken algorithms from paper to product in Tencent’s Virtual Human and video-call features. Zilong holds a PhD in Information and Communication Engineering from Huazhong University of Science and Technology and was a visiting PhD at UIUC, reflecting a solid academic foundation combined with applied impact. He built training pipelines such as Seed-ViT and contributed to state-of-the-art monocular depth and face-parsing challenge wins, demonstrating both engineering rigor and competitive research performance. Based in Singapore, he blends deep model research with production-focused engineering, often optimizing for mobile and real-time deployment scenarios.
12 years of coding experience
2 years of employment as a software developer
博士, 信息与通信工程, 博士, 信息与通信工程 at 华中科技大学
Visiting Ph.D. Student, ECE, Visiting Ph.D. Student, ECE at 美国伊利诺伊大学香槟分校
Finance Charts with Canvas(developed by es6,webpack)
Contributions:22 commits, 13 pushes, 1 branch in 3 months
chartscanvasjavascriptes6-webpackes6
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.