Follow
Zhun Deng
Zhun Deng
Incoming Assistant Professor, CS@UNC Chapel Hill; Postdoc, Columbia University
Verified email at columbia.edu - Homepage
Title
Cited by
Cited by
Year
How does mixup help with robustness and generalization?
L Zhang, Z Deng, K Kawaguchi, A Ghorbani, J Zou
arXiv preprint arXiv:2010.04819, 2020
2692020
Analyzing and mitigating object hallucination in large vision-language models
Y Zhou, C Cui, J Yoon, L Zhang, Z Deng, C Finn, M Bansal, H Yao
arXiv preprint arXiv:2310.00754, 2023
1552023
An unconstrained layer-peeled perspective on neural collapse
W Ji, Y Lu, Y Zhang, Z Deng, WJ Su
arXiv preprint arXiv:2110.02796, 2021
812021
When and how mixup improves calibration
L Zhang, Z Deng, K Kawaguchi, J Zou
International Conference on Machine Learning, 26135-26160, 2022
652022
Adversarial training helps transfer learning via better representations
Z Deng, L Zhang, K Vodrahalli, K Kawaguchi, JY Zou
Advances in Neural Information Processing Systems 34, 25179-25191, 2021
552021
How does information bottleneck help deep learning?
K Kawaguchi, Z Deng, X Ji, J Huang
International Conference on Machine Learning, 16049-16096, 2023
522023
Toward better generalization bounds with locally elastic stability
Z Deng, H He, W Su
International Conference on Machine Learning, 2590-2600, 2021
402021
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
362023
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
292023
Improving adversarial robustness via unlabeled out-of-domain data
Z Deng, L Zhang, A Ghorbani, J Zou
International Conference on Artificial Intelligence and Statistics, 2845-2853, 2021
272021
Decision-aware conditional gans for time series data
H Sun, Z Deng, H Chen, D Parkes
Proceedings of the Fourth ACM International Conference on AI in Finance, 36-45, 2023
242023
Robustness implies generalization via data-dependent generalization bounds
K Kawaguchi, Z Deng, K Luh, J Huang
International conference on machine learning, 10866-10894, 2022
242022
Happymap: A generalized multi-calibration method
Z Deng, C Dwork, L Zhang
arXiv preprint arXiv:2303.04379, 2023
232023
Representation via representations: Domain generalization via adversarially learned invariant representations
Z Deng, F Ding, C Dwork, R Hong, G Parmigiani, P Patil, P Sur
arXiv preprint arXiv:2006.11478, 2020
232020
Learning and forgetting unsafe examples in large language models
J Zhao, Z Deng, D Madras, J Zou, M Ren
arXiv preprint arXiv:2312.12736, 2023
212023
Last-layer fairness fine-tuning is simple and effective for neural networks
Y Mao, Z Deng, H Yao, T Ye, K Kawaguchi, J Zou
arXiv preprint arXiv:2304.03935, 2023
172023
Fifa: Making fairness more generalizable in classifiers trained on imbalanced data
Z Deng, J Zhang, L Zhang, T Ye, Y Coley, WJ Su, J Zou
arXiv preprint arXiv:2206.02792, 2022
172022
Interpreting robust optimization via adversarial influence functions
Z Deng, C Dwork, J Wang, L Zhang
International Conference on Machine Learning, 2464-2473, 2020
162020
Scaffolding sets
M Burhanpurkar, Z Deng, C Dwork, L Zhang
arXiv preprint arXiv:2111.03135, 2021
142021
Reinforcement learning with stepwise fairness constraints
Z Deng, H Sun, ZS Wu, L Zhang, DC Parkes
arXiv preprint arXiv:2211.03994, 2022
132022
The system can't perform the operation now. Try again later.
Articles 1–20