Jason Wu

I’m a Research Scientist in the Human-Centered Machine Intelligence group at Apple. I previously earned my PhD from the Carnegie Mellon Human-Computer Interaction Institute, advised by Professor Jeffrey Bigham. My PhD research was supported by the NSF Graduate Research Fellowship.

Before I joined CMU, I graduated from Georgia Institute of Technology in 2018 with a B.S. in Computer Science. There, I worked at the GT Ubicomp Lab and the Contextual Computing Group.

My research applies computational modeling to understand and improve how humans interact with computers.

✨

I am joining Purdue CS as an assistant professor starting Spring 2026. I am looking to work with highly motivated students. Please contact me if you are interested! Apply by following the Purdue CS graduate admissions process.

featured projects

How can we encode expertise from HCI experts like designers into reward models and use them to improve AI?

UIClip

UIClip is a data-driven model that scores the design quality of user interfaces.

UICoder

Finetuning Large Language Models (LLMs) to generate higher quality UIs through automated compiler and VLM design feedback.

Reinforcement Learning from Designer Feedback

Developing workflows and reward models that encode professional designers' expertise.

How can machines understand user interfaces and make the more accessible to both humans and other programs?

WebUI

A dataset that links web semantics with UI structure for better understanding models.

Screen Parsing

Reverse engineers UI models from screenshots to recover hierarchy and semantics.

Never-ending Learning of User Interfaces

An agent that continually learns UI semantics by interacting with real apps.

How can we build intelligent tools to build more usable and accessible interfaces?

FrameKit

Authoring adaptive interfaces through keyframe-driven workflows for designers.

SQUIRE

Interactive UI authoring powered by slot query intermediate representations.

Towards Automated Accessibility Report Generation for Mobile Apps

Automated crawling and detection of accessibility issues in apps.

How can we build systems that detect and respond to user context?

Automatic Class Discovery for One-Shot Acoustic Classifiers

An audio-based activity recognition system that adapts its detection classes based on user interactions.

When Can Accessibility Help?

Using sensors and user interactions to predict and recommend useful accessibility features to people who could benefit.

Reflow

User-specific interaction models trained from calibration data produce personalized adaptations of app layouts.

news

Sep 26, 2025	I am attending UIST 2025 in Busan, Korea! Please check out the workshop on longitudinal evaluations of AI systems that I helped organize and SQUIRE. I’d love to talk to any prospective students and collaborators!
Sep 22, 2025	I am joining Purdue CS as an assistant professor starting Spring 2026. I am looking to work with highly motivated students. Boiler Up!
Sep 30, 2024	Thrilled to share that I’ve been promoted from “senior intern” to Research Scientist at Apple! I’ve loved working with the Human-Centered Machine Intelligence group on HCI, UI modeling, and accessibility during my PhD. Excited for what’s next!
Jun 27, 2024	Back to Pittsburgh where I passed my PhD dissertation defense! My dissertation, Computational Understanding of User Interfaces would not have been possible without all the amazing support I’ve gotten throughout my PhD.
Jun 16, 2024	First time attending NAACL 2024 in Mexico City, Mexico. Amazing city and perfect place to present our work on finetuning LLMs to produce higher-quality UI designs, UICoder.