Bang An

Email  /  CV  /  Google Scholar  /  GitHub  /  Twitter

Hi, I'm Bang!

I am a fifth-year PhD candidate in Computer Science at University of Maryland. I'm very fortunate to be advised by Prof. Furong Huang and work on Machine Learning as a member of UMIACS. Before coming to UMD, I was a research staff member at IBM Research China. I received my bachelor’s degree from Northeastern University (China) and my master’s degree from Tsinghua University.

My research focuses on Responsible AI. I am particularly interested in understanding and improving the safety, alignment, robustness, fairness, and interpretability of Generative AI. I believe that reliable machine learning is a critical element in enabling AI to better serve and support humanity.

News
Preprints
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Yuancheng Xu, Udari Madhushani Sehwag, Alec Koppel, Sicheng Zhu, Bang An, Furong Huang, Sumitra Ganesh
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
Selected Publications
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
Bang An*, Sicheng Zhu*, Ruiyi Zhang, Michael-Andrei Panaitescu-Liess, Yuancheng Xu, Furong Huang
COLM 2024. [Website] [Code] [Dataset]
AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models
Sicheng Zhu, Ruiyi Zhang, Bang An, Gang Wu, Joe Barrow, Zichao Wang, Furong Huang, Ani Nenkova, Tong Sun
COLM 2024. [Website] [Code] [Media Coverage]
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
Yuhang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An, Wei Ai, Furong Huang
ACL 2024.
WAVES: Benchmarking the Robustness of Image Watermarks
Bang An*, Mucong Ding*, Tahseen Rabbani*, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang
ICML 2024. [Website] [Code]
Position: On the Possibilities of AI-Generated Text Detection
Souradip Chakraborty*, Amrit Singh Bedi*, Sicheng Zhu, Bang An, Dinesh Manocha, Furong Huang
ICML 2024.
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
Bang An*, Sicheng Zhu*, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang
ICLR 2024. [Code]
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Mucong Ding, Bang An, Yuancheng Xu, Anirudh Satheesh, Furong Huang
ICLR 2024.
Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
Sicheng Zhu, Bang An, Furong Huang, Sanghyun Hong.
ICML 2023. [Code]
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
Bang An, Zora Che, Mucong Ding, Furong Huang.
NeurIPS 2022. [Code]
Understanding the Generalization Benefit of Model Invariance from a Data Perspective
Sicheng Zhu*, Bang An*, Furong Huang.
NeurIPS 2021. [Code]
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference
Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu and Changyou Chen
EMNLP 2020. [Code]
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
Zhenyi Wang, Xiaoyang Wang, Bang An, Dong Yu, Changyou Chen
ACL 2020.
Awards
  • COLM 2024 DEI Travel Scholarship
  • Outstanding Graduate Assistant Award of UMD (top 2%), 2023.
  • NeurIPS 2022 Travel Award
Services
  • Reviewer: ICML 2022, NeurIPS 2022, ICML 2023, NeurIPS 2023, ICLR 2024, NAACL 2024
  • Organizer: NeurIPS 2024 Competition, Erasing the Invisible: A Stress-Test Challenge for Image Watermarks.