Yifei Chen

I am currently a researcher at Tencent Hunyuan, where I work primarily on vision-language models. Previously, I was at Huawei, working on multimodal alignment and on-device vision algorithms.

I received my M.S. from UCLA and my B.S. from HKUST. My research interests span multimodal learning and agentic intelligence, with the broader goal of building multimodal AI systems that co-evolve with the world.