Andrew Bai

According to our database, Andrew Bai authored at least 6 papers between 2021 and 2024.

Collaborative distances:

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

2024

Defending LLMs against Jailbreaking Attacks via Backtranslation.

Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh

CoRR, 2024

Which Pretrain Samples to Rehearse when Finetuning Pretrained Models?

Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh, Ankur Taly

CoRR, 2024

Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation.

Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh

CoRR, 2024

2023

Concept Gradient: Concept-based Interpretation Without Linear Assumption.

Andrew Bai, Chih-Kuan Yeh, Neil Y. C. Lin, Pradeep Kumar Ravikumar, Cho-Jui Hsieh

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Reducing Training Sample Memorization in GANs by Training with Memorization Rejection.

Andrew Bai, Cho-Jui Hsieh, Wendy Chi-wen Kan, Hsuan-Tien Lin

CoRR, 2022

2021

Real-time refinery optimization with reduced-order fluidized catalytic cracker model and surrogate-based trust region filter method.

Xinhe Chen, Kai Wu, Andrew Bai, Cornelius M. Masuku, Jacques Niederberger, Fábio S. Liporace, Lorenz T. Biegler

Comput. Chem. Eng., 2021