CS547 Human-Computer Interaction Seminar   (Seminar on People, Computers, and Design)

Fridays 11:30am-12:30pm PT · Gates B3 · Open to the public
Next
Polo Chau
Georgia Tech
Visual and Algorithmic Interpretation for Responsible AI
January 16, 2026

The Polo Club of Data Science builds visual and algorithmic tools that make sense of AI behaviors and risks. Our Safe AI work reveals AI vulnerabilities and innovates countermeasures. We pioneer the LLM Safety Landscape, uncovering a universal 'safety basin' outside of which LLM safety collapses. We state-of-the-art Dynamic Safety Shaping (DSS) method pinpoints safe vs. unsafe text segments to preserve alignment during fine-tuning. Our complementary interpretable AI research creates interactive visual systems that help people probe models and their vulnerabilities. We present the first 'interpretation meets safety' EMNLP survey that surfaces key gaps, and we build tools to close them. LLM Attributor traces generations back to the responsible training data; WizMap enables scalable, on-device exploration of large AI embeddings; ConceptAttention (top 1%, ICML'25) visualizes arbitrary text concepts in generated images and videos without training; ComplicitSplat exposes emerging threats in 3D Gaussian Splatting. Finally, our AI Explainers (Transformer Explainer, Diffusion Explainer, CNN Explainer, GAN Lab, ManimML) have reached over 1 million learners in 200+ countries.

Duen Horng (Polo) Chau is a Professor at Georgia Tech’s School of Computational Science and Engineering, holding a Machine Learning (ML) Ph.D. from Carnegie Mellon University (Dissertation Award, Honorable Mention). He co-directs the MS Analytics program. He was the Director of Industry Relations at The Institute for Data Engineering and Science, and the Associate Director of Corporate Relations at the Center for Machine Learning. His research bridges ML and visualization, creating scalable interpretable tools that enhance human understanding of large-scale data and complex ML models. He received 19 best paper/poster/demo type awards and published 200+ refereed articles. He received many faculty awards (Google, Meta, Intel), the GT-wide Senior Faculty Outstanding Undergraduate Research Mentor Award, and the Dean’s Award for Faculty (group) for establishing GT’s AI leadership for the College of Computing. His work has been deployed by Google, Microsoft, Meta, Nvidia, NASA, ADP, NortonLifeLock, and Atlanta Fire Rescue Department. His students won PhD fellowships (Google, Apple, IBM, JPMorgan, NASA, NSF). He teaches 1,000+ students each semester. His work has been covered by popular media: The Wall Street Journal, Wired, MIT Technology Review, Fortune, MSNBC, USA Today, Los Angeles Times, The Washington Post, Engadget, Gizmodo.