Runzhi Tian

According to our database, Runzhi Tian authored at least 4 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Adversarial Training May Induce Deteriorating Distributions.

Runzhi Tian, Yongyi Mao

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

Algorithmic Stability Based Generalization Bounds for Adversarial Training.

Runzhi Tian, Yongyi Mao

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2023

On robust overfitting: adversarial training induced distribution matters.

Runzhi Tian, Yongyi Mao

CoRR, 2023

2020

Learning VAE-LDA Models with Rounded Reparameterization Trick.

Runzhi Tian, Yongyi Mao, Richong Zhang

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020