updated 3 public sources
Multimodal InteractionMultimodal AgentsMultimodal PretrainingEfficient Model Architecture

Current frame

Principal Researcher focused on multimodal interaction, multimodal agents, and vision-language pretraining.

Extended note

Zilong Huang is a computer vision and multimodal AI researcher currently serving as a principal researcher at Tencent Singapore. His official homepage states that he previously worked at ByteDance and that he earned both his Ph.D. (2020) and B.E. (2015) from Huazhong University of Science and Technology, with a 2018-2019 visiting period at the University of Illinois Urbana-Champaign. His listed research interests include multimodal interaction, multimodal agents, multimodal pretraining, and efficient model architecture.