Xinyue Liu

xinyue.png

Hi! I am a master student at Carnegie Mellon University (LTI, Master of Computational Data Science), advised by Daphne Ippolito.

My research interests lie in three topics:

  • Enhance the ability of LLMs to follow diverse writing styles
  • Understand how parameter-efficient fine-tuning (e.g. LoRA) steers the direction of LLM training
  • Improve LLMs through advanced tool-using capabilities

Prior to CMU, I graduated as the Outstanding Graduate of Beijing from Beijing University of Posts and Telecommunications with a B.E. in Computer Science.

news

Jul 15, 2024 Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning has been accepted to the 17th International Natural Language Generation Conference (INLG). Check out our demo here.
Jun 03, 2024 Internship at Walmart Global Tech. Developed Product2Vec for better assortment planning.