Hi! I’m Guohao, a Computing and Information Science Ph.D. student studying Maching Learning in the School of Information at the Rochester Institute of Technology (RIT), advised by Zhiqiang Tao. My research primarily centers on data-centric approaches for vision-language models, emphasizing the understanding of robust general vision-language alignment and adaptation to downstream tasks. This includes uncertainty estimation, preference optimization, and elimination of hallucination to enhance the robustness of large vision-language models.

My research

I am drawn to simplicity, strive to understand things deeply, and enjoy building practical systems. Currently, I am fascinated by multi-modal foundation models like GPT-4o and CLIP, which can be adapted to a wide range of downstream tasks. My focus is on understanding how these models work, and improving their reasoning ability and robustness with self-questioning, preference optimization and evidential knowledge.

My background and history

I received my B.S. from the College of Engineering at Michigan State University in 2018, and M.S. from the Department of Computer Science and Engineering at Santa Clara University in 2021. Between my undergraduate and graduate studies, I was a SDE at Robotrak, focusing on traditional and Machine Learning algorithm design and implementation.