Peitong Duan

About Me

I am a fourth year PhD student in EECS at UC Berkeley, advised by Bjoern Hartmann. My research lies at the intersection of human computer interaction and AI. Specifically, I am interested in AI-enhanced tools for UI design.

Previously, I received my Bachelors and Masters in computer science from MIT, and then worked as a software engineer at Google. After that, I spent one year at Intel as an AI research resident, mentored by Casimir Wierzynski. Then, I returned to Google to work on text input research, advised by Shumin Zhai. During my PhD, I have interned at Apple AI/ML, advised by Jeff Nichols. I'm currently a student researcher at Google DeepMind, advised by Yang Li.

Publications

Papers

Generating Automatic Feedback on UI Mockups with Large Language Models
Peitong Duan, Jeremy Warner, Yang Li, Bjoern Hartmann
ACM Conference on Human Factors in Computing Systems (CHI) 2024
Paper | Talk | Video Preview | Preprint

Optimizing User Interface Layouts via Gradient Descent
Peitong Duan, Casimir Wierzynski, Lama Nachman
ACM Conference on Human Factors in Computing Systems (CHI) 2020
Paper | Talk | Video Preview | Preprint

Beagle: Automated Extraction and Interpretation of Visualizations from the Web
Leilani Battle, Peitong Duan, Zachery Miranda, Dana Mukusheva, Remco Chang, Michael Stonebraker
ACM Conference on Human Factors in Computing Systems (CHI) 2018
Paper

Demos

Towards Generating UI Design Feedback with LLMs
Peitong Duan, Jeremy Warner, Bjoern Hartmann
ACM Symposium on User Interface Software and Technology (UIST) 2023
Demo Paper

Workshops

Towards Semantically-Aware UI Design Tools: Design, Implementation, and Evaluation of Semantic Grouping Guidelines
Peitong Duan, Bjoern Hartmann, Karina Nguyen, Yang Li, Marti Hearst, Meredith Ringel Morris
ICML Artificial Intelligence & Human Computer Interaction Workshop (ICML AI&HCI Workshop) 2023
Workshop Paper