updated 2 public sources
report_authormultimodal_foundation_modelsvision_language_modelsgenerative_ai

Current frame

Research Scientist at ByteDance Seed working on multimodal foundation models, vision-language models, and generative AI.

Extended note

Yanwei Li is a research scientist at ByteDance Seed in San Jose focused on multimodal foundation models, vision-language models, and generative AI. His homepage states that he obtained his PhD from The Chinese University of Hong Kong (CUHK) under the supervision of Jiaya Jia. Before joining ByteDance Seed, he spent time as a research intern at NVIDIA Research and MEGVII, with work spanning multimodal perception and 2D/3D perception.