Xinyu Li 李昕雨

Email: xinyul2 [at] andrew [dot] cmu [dot] edu

prof_pic.jpg

Hello! I am a Ph.D. student at the Auton Lab in the School of Computer Science at Carnegie Mellon University, advised by Prof. Artur Dubrawski. Prior to pursuing my Ph.D., I obtained a B.S. in Computer Science (Information Security) from Shanghai Jiao Tong University, China and a Master of Information Systems Management (MISM) from Carnegie Mellon University.

My research centers on aligning foundation models with human preferences. Recently, I have been focusing on personalizing LLMs to align with individual user preferences and using AI feedback to align vision-language models for radiology report generation. Feel free to reach out to me if you are interested in my research and would like to collaborate!

news

Oct, 2024 Our Personalized RLHF work is accepted to NeurIPS 2024 Workshop on Adaptive Foundation Models.
Jun, 2024 I give an invited talk on our Personalized RLHF work at Mila RLHF reading group.
Jun, 2024 I start my internship at the Biomedical Imaging team at Microsoft Research Cambridge.
Mar, 2024 Our AAAI 2024 Spring Symposium on Clinical Foundation Models starts on March 25!

selected publications

  1. arXiv
    Personalized language modeling from personalized human feedback
    Xinyu Li, Zachary C Lipton, and Liu Leqi
    arXiv preprint arXiv:2402.05133, 2024
  2. Sensors
    Automated Assessment of Cardiovascular Sufficiency Using Non-Invasive Physiological Data
    Xinyu Li, Michael R Pinsky, and Artur Dubrawski
    Sensors, 2022
  3. IEEE JBHI
    Deep survival machines: Fully parametric survival regression and representation learning for censored data with competing risks
    Chirag Nagpal, Xinyu Li, and Artur Dubrawski
    IEEE Journal of Biomedical and Health Informatics, 2021
  4. MLHC
    Dynamically personalized detection of hemorrhage
    Chirag Nagpal, Xinyu Li, Michael R Pinsky, and Artur Dubrawski
    In Machine Learning for Healthcare Conference, 2019