PeopleofSuperintelligence

Researcher

Duen Horng (Polo) Chau

Also known as Polo Chau

Duen Horng (Polo) Chau is a professor and associate chair in Georgia Tech's School of Computational Science and Engineering whose work uses interactive visual tools to explain AI models. After earning a B.Eng. at the Chinese University of Hong Kong in 2004, he completed master's degrees in human-computer interaction and machine learning and a 2012 machine learning PhD at Carnegie Mellon University before joining Georgia Tech as an assistant professor. With collaborators, he coauthored browser-based and enterprise visual analytics systems for deep learning, including ActiVis in 2017, GAN Lab in 2018 and CNN Explainer in 2020. At Georgia Tech, he won the College of Computing's Outstanding Mid-Career Faculty Research Award in 2022, received an ACL Best Paper Honorable Mention for DiffusionDB in 2023, became a full professor in August 2024, and coauthored ConceptAttention and dynamic safety shaping work in 2025. He served as a Visiting Professor and Research Scientist at Apple from August 2025 to July 2026 and took on the associate chair role at Georgia Tech in August 2026.

Timeline

  1. 2004–2012

    Degrees and joining Georgia Tech

    Chau earns a B.Eng. in information engineering with honors from the Chinese University of Hong Kong in 2004, followed at Carnegie Mellon University by a Master of Human-Computer Interaction in August 2005 and an MS in machine learning in May 2010. He completes a PhD in machine learning at Carnegie Mellon in August 2012 and joins Georgia Tech's School of Computational Science and Engineering as an assistant professor. His 2012 dissertation, Data Mining Meets HCI: Making Sense of Large Graphs, receives honorable mention in CMU's School of Computer Science Dissertation Award.

  2. 2017

    Visualizing industrial-scale networks

    In 2017, with Minsuk Kahng, Pierre Y. Andrews and Aditya Kalro, he coauthors ActiVis, an interactive system for exploring industry-scale deep neural networks. Facebook deploys it on its machine-learning platform, where users inspect model architectures, neuron activations and results.

  3. 2018

    Making GANs explorable

    In 2018, with Minsuk Kahng, Nikhil Thorat, Fernanda Viégas and Martin Wattenberg, he coauthors GAN Lab, an interactive tool for non-experts to train and examine generative adversarial networks. It visualizes the model's training process in a web browser.

  4. 2020

    CNN Explainer for beginners

    In 2020, with his coauthors, he introduces CNN Explainer, a browser-based visualization that helps non-experts inspect how convolutional neural networks transform images into predictions. The tool connects a model overview with dynamic explanations of layers and mathematical operations.

  5. 2022–2024

    DiffusionDB and full professorship

    Georgia Tech's College of Computing gives him its Outstanding Mid-Career Faculty Research Award in 2022. In 2023, he receives an ACL Best Paper Honorable Mention for DiffusionDB and Georgia Tech's Senior Faculty Outstanding Undergraduate Research Mentor Award. He becomes a full professor in Georgia Tech's School of Computational Science and Engineering in August 2024.

  6. 2025

    ConceptAttention and LLM safety

    In 2025, he coauthors ConceptAttention, which uses diffusion-transformer attention to locate text-described concepts in images without additional training. Also in 2025, he coauthors Shape it Up! Restoring LLM Safety during Finetuning, which proposes dynamic safety shaping to reduce fine-tuning risks for large language models.

  7. August 2025–July 2026

    Visiting Apple

    From August 2025 to July 2026, he serves as a Visiting Professor and Research Scientist at Apple.

  8. Since August 2026

    Associate chair at Georgia Tech

    In August 2026, he becomes associate chair of Georgia Tech's School of Computational Science and Engineering. He is a professor in the school.

Career

  1. Since 2012Georgia Institute of TechnologyAssistant Professor, Associate Chair
  2. 2025–2026AppleVisiting Professor and Research Scientist

Education

  1. 2012Carnegie Mellon UniversityPhD
  2. 2004Chinese University of Hong KongB.Eng.

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Georgia Institute of Technology. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Georgia Institute of Technology. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes Georgia Institute of Technology. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.
  4. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Georgia Institute of Technology. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Duen Horng (Polo) Chau yet. Send us a free-licensed photo.

  1. Duen Horng "Polo" Chau - Georgia Tech, College of Computing poloclub.github.io. Checked 22 October 2026.
  2. Polo Chau - Carnegie Mellon Database Group db.cs.cmu.edu. Checked 22 October 2026.
  3. Best Paper Awards ml.cmu.edu. Checked 22 October 2026.
  4. ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models arxiv.org. Checked 22 October 2026.
  5. GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation arxiv.org. Checked 22 October 2026.
  6. CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization arxiv.org. Checked 22 October 2026.
  7. ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features arxiv.org. Checked 22 October 2026.
  8. Shape it Up! Restoring LLM Safety during Finetuning arxiv.org. Checked 22 October 2026.
  9. CSE Leadership Transition Comes as School Continues Rapid Growth cse.gatech.edu. Checked 22 October 2026.
  10. Duen Horng (Polo) Chau cse.gatech.edu. Checked 22 October 2026.