Han (Felix) Yan

Hi, I am Han (Felix) Yan (严涵), a fourth year undergraduate student studying at the The Chinese University of Hong Kong, Shenzhen. I'm an incoming CS PhD student at New York University (NYU) Courant Institute School of Mathematics, Computing, and Data Science in Fall 2026. I was also an exchange student at the University of Notre Dame. I am fortunated to be advised by Prof. Jianwei Huang at the NCEL lab, Prof. Meng Jiang at the DM² lab and Prof. Benyou Wang at the CUHKSZ Freedom AI lab.

My research interest lies in GenAI (e.g. MLLM/LLM/) Safety, AI Privacy, Trustworthy AI, CoT, Reinforcement Learning Reward Model and etc. Currently, I am exploring CoT and RL Reward Model Design.

Please feel free to drop me an Email for any form of communication or collaboration!

Email  /  Google Scholar  /  Github  /  LinkedIn  / 

We propose a unified framework that enforces dual-space smoothness in representation and parameter spaces to improve robustness and balance unlearning metrics.

We propose an approach that diversifies grid representations and includes a rigorous evaluation process using multi-modal large language models (MLLMs) to ensure output consistency.

We propose a large language model-assisted workflow for small-scale synthetic power grid generation, verification, and visualization.

• I've always been surrounded by wonderful friends, collaborators, and advisors, and I try to maintain an optimistic outlook. If you're having a tough time and would like someone to talk to, feel free to reach out!
• I like pop music and reading science fiction. The Three-Body Problem is my favorite science fiction series.

Template courtesy: Jon Barron.