Jie Yang 杨杰

I am a Senior Researcher at WeChat Vision, Tencent, working on multimodal foundation models. My research interest covers the full training stack — from large-scale pretraining to post-training optimization for models that perceive, reason, and act across image, video, audio, and language.

I received my Ph.D. from The Chinese University of Hong Kong, Shenzhen, advised by Prof. Ruimao Zhang and Prof. Zhen Li. During my Ph.D. (2021–2025), I worked toward intelligent agents that can collaborate with humans in dynamic environments, exploring three closely connected directions: (1) human-centric visual understanding and reasoning, with a focus on interpreting human states, behaviors, and intentions (e.g., ED-Pose, X-Pose); (2) multi-modal scene perception, integrating diverse modalities to make sense of complex real-world scenes (e.g., MP-HOI, Magic-HOI); and (3) behavior planning and decision-making, enabling agents to act upon what they perceive and understand (e.g., F-HOI, InteractAnything, VIKI-R).