Andrew Bai

21 papers A* 1Journal 18Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
LoL: Longer than Longer, Scaling Video Generation to Hour.
CoRR
Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh
2026 J jnl
Reward-Forcing: Autoregressive Video Generation with Reward Feedback.
CoRR
Jingran Zhang, Ning Li, Yuanhao Ban, Andrew Bai, Justin Cui
2025 — conf
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning.
NAACL (Findings)
Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh, Ankur Taly
2025 J jnl
Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models.
CoRR
Andrew Bai, Justin Cui, Ruochen Wang, Cho-Jui Hsieh
2025 J jnl
Exploring Expert Failures Improves LLM Agent Tuning.
CoRR
Li-Cheng Lan, Andrew Bai, Minhao Cheng, Cho-Jui Hsieh, Tianyi Zhou
2025 J jnl
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation.
CoRR
Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh
2025 J jnl
Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy.
CoRR
Kai-Wen K. Yang, Andrew Bai, Alexandra Bermudez, Yunqi Hong, Zoe Latham, Iris Sloan, Michael Liu, Vishrut Goyal, Cho-Jui Hsieh, Neil Y. C. Lin
2025 J jnl
Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs.
CoRR
Yunqi Hong, Sohyun An, Andrew Bai, Neil Y. C. Lin, Cho-Jui Hsieh
2025 J jnl
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models.
CoRR
Tong Xie, Andrew Bai, Yuanhao Ban, Yunqi Hong, Haoyu Li, Cho-Jui Hsieh
2024 J jnl
CLUE: Concept-Level Uncertainty Estimation for Large Language Models.
CoRR
Yu-Hsiang Wang, Andrew Bai, Che-Ping Tsai, Cho-Jui Hsieh
2024 J jnl
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation.
CoRR
Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh
2024 J jnl
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation.
Trans. Mach. Learn. Res.
Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh
2024 — conf
Defending LLMs against Jailbreaking Attacks via Backtranslation.
ACL (Findings)
Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh
2024 J jnl
Defending LLMs against Jailbreaking Attacks via Backtranslation.
CoRR
Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh
2024 J jnl
Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models.
CoRR
Jack He, Jianxing Zhao, Andrew Bai, Cho-Jui Hsieh
2024 J jnl
On the loss of context-awareness in general instruction fine-tuning.
CoRR
Yihan Wang, Andrew Bai, Nanyun Peng, Cho-Jui Hsieh
2024 J jnl
Which Pretrain Samples to Rehearse when Finetuning Pretrained Models?
CoRR
Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh, Ankur Taly
2023 A* conf
Concept Gradient: Concept-based Interpretation Without Linear Assumption.
ICLR
Andrew Bai, Chih-Kuan Yeh, Neil Y. C. Lin, Pradeep Kumar Ravikumar, Cho-Jui Hsieh
2022 J jnl
Concept Gradient: Concept-based Interpretation Without Linear Assumption.
CoRR
Andrew Bai, Chih-Kuan Yeh, Pradeep Ravikumar, Neil Y. C. Lin, Cho-Jui Hsieh
2022 J jnl
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection.
CoRR
Andrew Bai, Cho-Jui Hsieh, Wendy Chi-wen Kan, Hsuan-Tien Lin
2021 J jnl
Real-time refinery optimization with reduced-order fluidized catalytic cracker model and surrogate-based trust region filter method.
Comput. Chem. Eng.
Xinhe Chen, Kai Wu, Andrew Bai, Cornelius M. Masuku, Jacques Niederberger, Fábio S. Liporace, Lorenz T. Biegler