General Information
Details
My research group Polo Club of Data Science innovates at the intersection of machine learning and visualization to synthesize scalable, interactive, and trustworthy tools that amplify human’s ability to understand and interact with billion-scale data and machine learning models. Our research thrusts include: human-centered AI (interpretable and safe AI; adversarial ML), AI education; adversarial ML; large graph visualization and mining, cybersecurity and social good.
Machine learning, AI, visualization, HCI.
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety. Seongmin Lee, Aeree Cho, Grace C. Kim, ShengYun Peng, Mansi Phute, Duen Horng Chau. EMNLP, 2025 (Main Conference).
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features. Alec Helbling, Tuna Han Salih Meral, Ben Hoover, Pinar Yanardag, Duen Horng Chau. ICML, 2025.
RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering. Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling, Mansi Phute, Chao Zhang, Zsolt Kira, Willian Lunardi, Martin Andreoni, Wenke Lee, and Polo Chau. IJCAI, 2025.
Transformer Explainer: Interactive Learning of Text-Generative Models. Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Zijie J. Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau. Poster, IEEE VIS 2024.