Andrew Bai

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 10

Top Topics

Top Venues

Trans. Mach. Learn. Res.

Publications

Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh
Defending LLMs against Jailbreaking Attacks via Backtranslation. ACL (Findings) (2024)
Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh
Defending LLMs against Jailbreaking Attacks via Backtranslation. CoRR (2024)
Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation. Trans. Mach. Learn. Res. 2024 (2024)
Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation. CoRR (2024)
Jack He, Jianxing Zhao, Andrew Bai, Cho-Jui Hsieh
Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models. CoRR (2024)
Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh, Ankur Taly
Which Pretrain Samples to Rehearse when Finetuning Pretrained Models? CoRR (2024)
Andrew Bai, Chih-Kuan Yeh, Neil Y. C. Lin, Pradeep Kumar Ravikumar, Cho-Jui Hsieh
Concept Gradient: Concept-based Interpretation Without Linear Assumption. ICLR (2023)
Andrew Bai, Cho-Jui Hsieh, Wendy Chi-wen Kan, Hsuan-Tien Lin
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection. CoRR (2022)
Andrew Bai, Chih-Kuan Yeh, Pradeep Ravikumar, Neil Y. C. Lin, Cho-Jui Hsieh
Concept Gradient: Concept-based Interpretation Without Linear Assumption. CoRR (2022)
Xinhe Chen, Kai Wu, Andrew Bai, Cornelius M. Masuku, Jacques Niederberger, Fábio S. Liporace, Lorenz T. Biegler
Real-time refinery optimization with reduced-order fluidized catalytic cracker model and surrogate-based trust region filter method. Comput. Chem. Eng. 153 (2021)