About Me 🤔

Hi, I'm Jinxi He (何锦熙). I come from Changsha, Hunan in China. Previously, I was an undergraduate at University of Rochester , supervised by Prof. Chenliang Xu and Prof. Dongmei Li on various research projects. I got my B.S. in Computer Science and B.A. in Psychology degrees here. I've had a wonderful time collaborating with PhD students in their lab, learning and growing alongside them throughout my academic journey. Meliora!

My research interests include Adversarial Machine Learning, Trustworthy AI, and Vision-Language Models (VLMs). I'm passionate about developing AI systems that are both innovative and reliable. I've also contributed to several works on Chain of Thought (CoT) reasoning and multimodal systems.
My current interests are expanding into two key areas: first, MLLM hallucination analysis under different situations and MLLMs safety; and second, robot learning that incorporates vision-language models (VLMs) for planning and manipulation tasks.
I remain committed to continuous learning and growth in this rapidly evolving field.

Outside of academics and research, I enjoy cooking traditional Chinese dishes from my hometown and experimenting with fusion cuisine. I'm also an avid badminton player and try to play at least twice a week to stay active. These activities help me maintain a healthy work-life balance and connect with friends from different backgrounds.