Publications
* denotes equal contribution. † denotes equal advising.
M3Risk: Assessing the Helpfulness of MLLMs for Malicious Intent-Driven Misuse
Chung Peng Lee, Ryo Hachiuma, Hayoung Jung, Yusuke Hirota†, Aleksandra Korolova†
In Submission
Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization
Yung-Chin Chen, Chung Peng Lee, Ze-Wei Liou, Naveen Verma
EMNLP Findings 2026
WorldBench: A Challenging and Visually Diverse Multimodal Benchmark
Yida Yin*, Harish Krishnakumar*, Chung Peng Lee, Boya Zeng, Wenhao Chai, Shengbang Tong, Wenhu Chen, Hu Xu, Xingyu Fu, Gabriel Herbert Sarch, Aleksandra Korolova, Zhuang Liu
Preprint
The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
Max Springer, Chung Peng Lee, Blossom Metevier, Jane Castleman, Bohdan Turbal, Hayoung Jung, Zeyu Shen, Aleksandra Korolova
NeurIPS 2026
How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets
Chung Peng Lee, Rachel Hong, Harry H. Jiang, Aster Plotnik, William Agnew, Jamie Morgenstern
Oral in AAAI (AI for Societal Impact Track) 2026, Oral in NeurIPS RegML Workshop 2025
Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
Yiwei Yang*, Chung Peng Lee*, Shangbin Feng, Dora Zhao, Bingbing Wen, Anthony Liu, Yulia Tsvetkov, Bill Howe
NeurIPS Datasets and Benchmarks 2025
Fairness Through Partial Awareness: Evaluation of the Addition of Demographic Information for Bias Mitigation Methods
Chung Peng Lee, Rachel Hong, Jamie Morgenstern
ICML Next Generation of AI Safety Workshop 2024