Hi, I’m Mengqi Yuan, an undergraduate student majoring in Computer Science at University of Science and Technology of China. I am currently an intern student in Secure Learning Lab (UIUC & UChicago), advised by Prof. Bo Li. Previously, I was fortunate to work with Prof. Fuli Feng and Prof. Xiangnan He in Lab for Data Science (USTC).

My current research interests lie in improving the generative ability, reliability, and trustworthiness of ML models (such as LLMs and VLMs). My work also closely relates to Agents, focusing on both theoretical and applied aspects.

I will be attending EMNLP 2024 in Miami. If you are interested in my work or related topics, please feel free to reach out for a chat!

Publications

^* Indicates Equal Contribution

• Direct Multi-Turn Preference Optimization for Language Agents [Paper] [Code]
  Wentao Shi* , Mengqi Yuan* , Junkang Wu , Qifan Wang , Fuli Feng
  EMNLP 2024 Main Conference