About
I am a research scientist at Meta. I obtained my PhD from the Department of Statistics, University of Wisconsin-Madison. My research interests mainly lie in interpretability and applications of large language models (LLM). I was fortunate to be advised by Professor Karl Rohe and Professor Frederic Sala.
I earned MS in Computer Science and MS in Statistics from the University of Wisconsin–Madison, and a BS in Statistics from Zhejiang University. During my master's studies, I had the privilege of working with Dr. Sebastian Raschka, with whom I co-authored Chapter 16: Transformers—Improving Natural Language Processing with Attention Mechanisms in his book Machine Learning with PyTorch and Scikit-Learn.
My full CV can be found here.
Work Experience
Meta
ML Engineer intern, 2024 summer
Built an unified typeahead ranker for Meta AI suggestions and keywords. Introduced Meta AI engagemented-based features into Meta AI ranker. Led an in-depth study on user reformulation for Meta AI search.
Amazon AGI
Applied scientist intern, 2023 summer
Built a vector search system for multi-modal data including text, image and video. Proposed a two-stage LLM-augmented search method to enable search by user preference.
Amazon Alexa AI
Applied scientist intern, 2022 summer
Built a transformer-based multi-task learning model for label automation and label recommendation.
Publications
“From Many Voices to One: Statistically Principled Aggregation of LLM Judges”
J. Zhao, C. Shin, T.-H. Huang, S. Namburi and F. Sala
In NeurIPS workshop: Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling, 2025.
“OTTER: Effortless Label Distribution Adaptation of Zero-shot Models”
C. Shin, J. Zhao, S. Cromp, H. Vishwakarma, and F. Sala
In Neural Information Processing Systems (NeurIPS), 2024.
“MoRe Fine-Tuning with 10x Fewer Parameters”
W. Tan, N. Roberts, T.-H. Huang, J. Zhao, J. Cooper, S. Guo, C. Duan, and F. Sala
In ICML Workshop: Efficient Systems for Foundation Models II, 2024.
“Geometry-Aware Adaptation for Pretrained Models”
N. Roberts, X. Li, D. Adila, S. Cromp, T. Huang, J. Zhao, and F. Sala
In Neural Information Processing Systems (NeurIPS), 2023.
“Chapter 16: Transformers–Improving Natural Language Processing with Attention Mechanisms, Machine Learning with PyTorch and Scikit-Learn”
S. Raschka, J. Zhao
Birmingham, UK: Packt Publishing, 2022. ISBN: 978-1801819312.
Teaching Experience
STAT 371: Introductory Applied Statistics for the Life Sciences
20 Fall - 21 Summer
STAT 451: Introduction to Machine learning and Statistical Pattern Classification
21 Fall - 24 Spring