Simon Yu

I am an incoming PhD student at Northeastern University, advised by Weiyan Shi. I was a M.Res. and BSc student at the University of Edinburgh, also part of the EdinburghNLP, supervised by Jeff Pan. I am also fortuantely work closely with Pasquale Minervini and Jacques Fleuriot. I am part of the Cohere For AI community with working with Marzieh Fadaee. I have done research about instruction tuning, safety in retrieval and representation learning.

My research interests are lies in two directions: i) Safety Alignement: understanding the safety vulnerability in other aspects (i.e. Multilingual, Code-LLMs) and better align for safety purposes, and ii) Self-Evolving or Refinemnt of LLMs: how to make LLMs better adapt to the user’s preferences and being more generalizable.