Follow
Wenlong Ji
Wenlong Ji
Verified email at stanford.edu - Homepage
Title
Cited by
Cited by
Year
An unconstrained layer-peeled perspective on neural collapse
W Ji, Y Lu, Y Zhang, Z Deng, WJ Su
arXiv preprint arXiv:2110.02796, 2021
542021
The power of contrast for feature learning: A theoretical analysis
W Ji, Z Deng, R Nakada, J Zou, L Zhang
Journal of Machine Learning Research 24 (330), 1-78, 2023
272023
Understanding multimodal contrastive learning and incorporating unpaired data
R Nakada, HI Gulluk, Z Deng, W Ji, J Zou, L Zhang
International Conference on Artificial Intelligence and Statistics, 4348-4380, 2023
102023
Importance tempering: Group robustness for overparameterized models
Y Lu, W Ji, Z Izzo, L Ying
arXiv preprint arXiv:2209.08745, 2022
42022
Model-Agnostic Covariate-Assisted Inference on Partially Identified Causal Effects
W Ji, L Lei, A Spector
arXiv preprint arXiv:2310.08115, 2023
2023
How Gradient Descent Separates Data with Neural Collapse: A Layer-Peeled Perspective
W Ji, Y Lu, Y Zhang, Z Deng, WJ Su
2021
The system can't perform the operation now. Try again later.
Articles 1–6