Summary
Zhuowei Chen is an AIGC researcher and engineer with 9 years of experience, currently driving data-centric multimodal video generation at ByteDance’s Intelligent Creation Laboratory. He specializes in building scalable, diverse pretraining datasets and alignment techniques that improve controllability in video-generation models, with recent work including Phantom, Phantom-Data, PuLID, and DreamIdentity. His papers have been featured as Oral/Spotlight presentations at top venues (ICCV, NeurIPS, ICLR, AAAI) and he regularly reviews for major conferences, reflecting deep academic rigor. In industry he has translated research into production features for Douyin, Doubao, CapCut, and TikTok, shipping ID-control and skin-consistency capabilities that moved core business metrics. Trained as a PhD from USTC, he combines strong experimental research with hands-on tech transfer, and is open to collaborations in multimodal video generation and dataset curation.
9 years of coding experience
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at University of Science and Technology of China
Bachelor of Engineering - BE, Bachelor of Engineering - BE at University of Electronic Science and Technology of China