Yong Lin 

Ph.D. Student

Department of Computer Science and Engineering
Hong Kong University of Science and Technology
Hong Kong

[Google Scholar] [Github]
E-mail: ylindf [at] connect [dot] ust [dot] hk

Short Bio

I am a final year CSE PhD student in Prof. Tong Zhang's group at the Hong Kong University of Science and Technology (HKUST). My research is generously supported by Apple AI/ML PhD fellowship and Hong Kong PhD fellowship .

[Pre-PhD] Prior to my PhD studies, I worked as a Senior Machine Learning Engineer at Alibaba (a prominent company similar to Amazon in China), where I witnessed the remarkable capabilities of machine learning while being aware of the inherent instability of deep models in industrial applications.

[My PhD Research] During my primary PhD study, I focused on enhancing the trustworthiness of deep models, including (1) out-of-distribution (OOD) generalization, such as enabling an autonomous driving system trained on city roads to navigate country roads, and (2) alignment of AI systems, such as aligning Large Language Models (LLMs) to prioritize traits like helpfulness, harmlessness, and honesty. I developed theoretically grounded methods with strong empirical results on foundation models. More recently, I have a keen interest in Reinforcement Learning with Human Preference (RLHF).

Selected Papers

(* denotes equal contribution.)

Selected Awards

Experiences