![](/project/external-project/featured_hu3d03a01dcc18bc5be0e67db3d8d209a6_329522_e8d7aa972ff635568626abd3fafb0ebe.webp)
![Changcheng Fu](/authors/admin/avatar_hu191a0a16c6033e6eeb02af874254b2b5_191744_270x270_fill_q75_lanczos_center.jpg)
Changcheng Fu
Ph.D. Student at University of Southern California
Hi, I’m Changcheng, a first-year Ph.D. advised by Prof. Ram Nevatia at the University of Southern California. I’m broadly interested in Computer Vision where my current research mainly focuses on leveraging large language models(LLMs) in solving different downstream vision tasks. My long-term goal is to learn how multimodalities input and LLMs can help in building more robust and generalizable computational models, which can achieve reliable performance inferencing on out-of-distribution data and can be easily transferable on downstream tasks.