Runtian Zhai's repositories
adversarial-robustness-unlabeled
Adversarially Robust Generalization Just Requires More Unlabeled Data
grw-vs-erm
Understanding why Generalized Reweighting Does Not Improve Over ERM
boosted_cvar
Boosted CVaR Classification (NeurIPS 2021)
RuntianZ.github.io
github.io
SQLproject
SQL projects
10708project
10708 Project
CelebaFiles
CelebA Dataset
cifar10_challenge
A challenge to explore adversarial robustness of neural networks on CIFAR10.
DinkyTrain
Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃
FeatureScatter
Feature Scattering Adversarial Training
NetworkTool
A tool for editing, analyzing and comparing websites
pretrained_models
For storing pretrained models
smoothing-adversarial
Code replicating the results of our "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers" paper
tiny-noise
Tiny noise pkl cloud storage.
VS-Loss
Label-Imbalanced and Group-Sensitive Classification under Overparameterization
wilds
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
YOPO-You-Only-Propagate-Once
Code for our paper: You Only Propagate Once: Painless Adversarial Training Using Maximal Principle