Projects

Diffusion Explainer

Learning Stable Diffusion through Interactive Visual Design

Diffusion Explainer is the first interactive visualization tool that explains how Stable Diffusion transforms text prompts into images. It tightly integrates a visual overview of Stable Diffusion’s complex components with detailed explanations of their underlying operations.

DiffusionDB

Text-to-image Prompt Dataset Based on Stable Diffusion

DiffusionDB is the first large-scale text-to-image prompt dataset containing 14 million images generated by Stable Diffusion. It provides exciting research opportunities in evaluating generative models, detecting deepfakes, and designing interaction tools.

AI through Symbiosis

Symbiotic AI: Order Picking and Ambient Sensing

We present a practical use case of egocentric Symbiotic AI in order picking, where ambient sensing is used without explicit supervision to train an agent which can then help the user improve task speed and accuracy.

Argo Scholar

Visual Exploration of Research Literature

Argo Lite is an interactive literature exploration visualization system that runs in your web browsers. It allows researchers to incrementally visualize Literature Networks with interactive force-directed layout and save and publish via URLs.

Argo Lite

In-Browser Interactive Graph Visualization

Argo Lite is a novel open-source in-browser interactive Graph Exploration and Visualization tool. It enables researchers to incrementally explore graph data in browser and conveniently share their interactive visualizations via URLs and embedded widgets.

CardiacAR

Mobile AR for Cardiovascular Surgical Planning

CardiacAR is an iOS Augmented Reality application that enables users to perform interactive surgical planning on mobile devices, offering omni-directional slicing of patients’ 3D heart models and virtual annotation to assist planning.

Universal Drone Controller

Controlling UAVs via Hand Genstures

Universal Drone Controller is a new input method of controlling and monitoring UAVs based on Leap Motion hand gesture recognition, eliminating the need for an external remote controller.

Publications

Symbiotic Artificial Intelligence: Order Picking and Ambient Sensing

Zhe Ming Chng, Calix Tang, Darshan Krishnaswamy, Haoyang Yang, Shivang Chopra, Jon G Womack, Thad Starner | Workshop, ICASSP 2023

Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion

Accepted to VISxAI Workshop
Seongmin Lee, Ben Hoover, Hendrik Strobelt, Zijie J. Wang, Anthony Peng, Austin Wright, Kevin Li, Haekyu Park, Alex Yang, Polo Chau | Poster, IEEE VIS 2023

Diffusion Explainer: Interactive Visual Learning for Stable Diffusion

Seongmin Lee, Ben Hoover, Hendrik Strobelt, Zijie J. Wang, Anthony Peng, Austin Wright, Kevin Li, Haekyu Park, Alex Yang, Polo Chau | Demo, CVPR 2023

DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

Best Paper Honorable Mention
Trending on GitHub (1K+ Stars)and Hugging Face (1.5M+ Downloads)
Zijie J. Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, Polo Chau | Paper, ACL 2023

Evaluating Cardiovascular Surgical Planning in Mobile Augmented Reality

Collaboration with Duke University and Children's Healthcare of Atlanta @ Emory University
Haoyang Yang, Pratham Darrpan Mehta, Jonathan Leo, Zhiyan Zhou, Megan Dass, Anish Upadhayay, Timothy C. Slesnick, Fawwaz Shaw, Amanda Randles, Polo Chau | Poster, IEEE VIS 2022

Evaluation of Argo Scholar with Observational Study

Deployed for CSE 6242: Data and Visual Analytics at Georgia Tech
Kevin Li, Haoyang Yang, Evan Montoya, Anish Upadhayay, Zhiyan Zhou, Jon Saad-Falcon, Polo Chau | Poster, IEEE VIS 2022

Visual Exploration of Literature with Argo Scholar

Deployed for CSE 6242: Data and Visual Analytics at Georgia Tech
Kevin Li, Haoyang Yang, Evan Montoya, Anish Upadhayay, Zhiyan Zhou, Jon Saad-Falcon, Polo Chau | Demo, ACM CIKM 2022

Interactive Cardiovascular Surgical Planning via Augmented Reality

Collaboration with Children's Healthcare of Atlanta at Emory University
Jonathan Leo, Zhiyan Zhou, Haoyang Yang, Megan Dass, Anish Upadhayay, Timothy C. Slesnick, Fawwaz Shaw, Polo Chau | Poster, Asian CHI 2021

Argo Scholar: Interactive Visual Exploration of Literature in Browsers

Best Poster Honorable Mention
Kevin Li, Haoyang Yang, Anish Upadhayay, Zhiyan Zhou, Jon Saad-Falcon, Polo Chau | Poster, IEEE VIS 2021

Education

Georgia Institute of Technology

College of Computing

Atlanta, GA

Doctor of Philosophy, Computer Science

August 2024 - Present

Master of Science, Computer Science

August 2022 - May 2023

Specialization: Computational Perception and Robotics
Bachelor of Science, Computer Science

August 2019 - May 2022

Graduated with Highest Honors
Concentration: Devices, Intelligence | Minor: Japanese
Activities and societies: Billiards @ Georgia Tech (Co-Founder & Vice President), RoboJacket

Stanford Pre-Collegiate Studies

Artificial Intelligence for Robots

Stanford, CA

Summer 2018

  • Research program for Event-driven Programming, Finite State Machine, Robot AI, and Motion Planning

Experience

Georgia Institute of Technology

School of Interactive Computing

Atlanta, GA

Graduate Research Assistant

August 2024 - Present

Research Advisor:

Goldman Sachs

Asset and Wealth Management

Dallas, TX

Software Engineer
June 2023 - July 2024
Software Engineer Summer Analyst
June 2022 - August 2022

Georgia Institute of Technology

School of Computational Science and Engineering

Atlanta, GA

Graduate Research and Teaching Assistant

August 2022 - May 2023

Research Advisor: Teaching: Awards:
  • Donald V. Jackson Fellowship (Outstanding First Year Master's Student)
  • ACL 2023 Best Paper Award, Honorable Mention (DiffusionDB)
Undergraduate Research Assistant

September 2020 - May 2022

Research Advisor: Awards:
  • IEEE VIS 2021 Best Poster Award, Honorable Mention (Argo Scholar)
Back to top