Scholar
Wenlong Ji
Google Scholar ID: UW2Ji5MAAAAJ
Stanford University
Citations & Impact
Citations
448
H-index
9
i10-index
9
Publications
17
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- An Overview of Large Language Models for Statisticians. Submitted.
- Predictions as surrogates: Revisiting surrogate outcomes in the age of AI. Submitted.
- Scaling Laws for the Value of Individual Data Points in Machine Learning. (ICML 2024).
- Model-Agnostic Covariate-Assisted Inference on Partially Identified Causal Effects. arXiv preprint arXiv:2310.08115, 2023. Submitted.
- Understanding multimodal contrastive learning and incorporating unpaired data. (AISTATS 2023).
- Importance Tempering: Group Robustness for Overparameterized Models. arXiv preprint arXiv:2209.08745, 2022. Under review.
- The Power of Contrast for Feature Learning: A Theoretical Analysis. (JMLR 2023).
- An Unconstrained Layer Peeled Perspective on Neural Collapse. (ICLR 2022).
Research Experience
- Conducted multiple research projects during his PhD, covering large language models, predictions as surrogates, scaling laws for the value of individual data points, covariate-assisted inference, and more.
Education
- PhD student at the Department of Statistics, Stanford University, advised by Prof. Lihua Lei; Bachelor's degree from the School of Mathematical Sciences at Peking University, worked with Prof. Bin Dong, Prof. Weijie Su, Prof. Linjun Zhang, and Prof. James Zou.
Background
- Broadly interested in statistics, machine learning, and economics, focusing on establishing the theoretical foundation and developing statistical tools for real-world problems.
