Xinyi Wang
Postdoctoral Researcher at Princeton University
New Jersey, United States
Summary
👤
Senior🎓
Top SchoolXinyi Wang is a postdoctoral researcher at Princeton University with eight years of experience studying pretraining and reasoning behaviors of large language models. She earned a PhD in Computer Science from UC Santa Barbara, where her work dissected in-context learning, reasoning, and memorization phenomena in LMs. Xinyi has industry research experience from internships at IBM and Microsoft, focusing on how pretraining data and novel prompting mechanisms (e.g., planning tokens) affect chain-of-thought reasoning. Based in New Jersey, she blends rigorous theoretical study with practical experimentation to improve model capabilities and robustness. Notably, her background in both applied mathematics and CS across UCLA, HKUST, and UCSB underpins a quantitative approach to probing model behavior that favors interpretable, data-driven interventions.
8 years of coding experience
5 years of employment as a software developer
High School Diploma, High School Diploma at Beijing No.4 High SchoolDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at UC Santa BarbaraUniversity of California, Los AngelesHong Kong University of Science and Technology (HKUST)
Chinese, English
Github Skills (15)
generalization7
testing4
nlp3
benchmark3
tensorflow2
machine-learning2
inference2
deep-learning2
pytorch2
transformers1
modality1
representations1
transformer1
bert1
encoder1
Programming languages (3)
Github contributions (5)
WANGXinyiLinda/adaptive-count-ception
May 2019 - Sep 2019
Contributions:5 commits, 3 pushes, 1 branch in 4 months
WANGXinyiLinda/Deep-Q-Learning-Bitcoin-Trading-Agent
Dec 2018 - Dec 2018
Contributions:13 commits, 9 pushes, 1 branch in 8 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.