Gordon Guocheng Qian is a Staff Researcher at ByteDance, where he works on post-training of Seedance video generation models. Previously, he was a Senior Research Scientist at Snap Inc., where he worked on video generation pretraining and post-training and served as tech lead for personalized generation, filing six patents and shipping three research innovations to Snapchat products (Dreams, EasyLens, and AI Lens), impacting 900M+ monthly active users. He earned his Ph.D. in Computer Science from KAUST, advised by Prof. Bernard Ghanem. He has authored 20+ top-tier publications with 4,000+ citations. His representative works include PointNeXt (NeurIPS, 1.2K+ citations, 1K+ GitHub stars), Magic123 (ICLR, 450+ citations, 1.6K+ GitHub stars), and Omni-ID (CVPR, product integrated, patent filed). His research interests include streamable and unified multimodal understanding and generation. He serves as an Area Chair for ICLR and NeurIPS.
If you are interested in working on image and video generative models with me, please reach out at gordonqian2017 [at] gmail.com