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 understanding and adaptation to downstream tasks. This includes uncertainty, reinforcement learning, and elimination of hallucination to enhance the robustness of deep generative model.

My research

I am drawn to simplicity, strive to understand things deeply, and enjoy building practical systems. Currently, I am fascinated by foundation models like GPT-4, CLIP, and DALL-E. These models, trained on extensive data using self-supervision at an immense scale, can be adapted to a wide range of downstream tasks. Foundation models represent a paradigm shift in AI development and human-AI interaction. My focus is on understanding how these models work, and improving their intelligence and robustness with multi-modal information.

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.