Jason Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jason Wu has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Jeffrey P. Bigham
Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, USA
9 shared publications - Jeffrey Nichols
Apple
6 shared publications - Yi-Hao Peng
Carnegie Mellon University, Pittsburgh, USA
6 shared publications - Amanda Swearngin
Apple
3 shared publications - Yue Jiang
Kahlert School of Computing, University of Utah, Salt Lake City, Utah, USA
3 shared publications - Alan Leung
Apple, Seattle, Washington, USA
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
A Demonstration of Lightweight Generative UI Personalization
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessA Demonstration of Lightweight Generative UI Personalization
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Demonstration of MANA: Multi-perspective Alignment of NPC Agents
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessDemonstration of MANA: Multi-perspective Alignment of NPC Agents
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Demonstration of General Accessibility Models: Learning Accessibility Needs from Everyday Computer Use
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessDemonstration of General Accessibility Models: Learning Accessibility Needs from Everyday Computer Use
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Improving User Interface Generation Models from Designer Feedback
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessImproving User Interface Generation Models from Designer Feedback
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Facilitating Longitudinal Interaction Studies of AI Systems
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessFacilitating Longitudinal Interaction Studies of AI Systems
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
SQUIRE: Interactive UI Authoring via Slot QUery Intermediate REpresentations
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessSQUIRE: Interactive UI Authoring via Slot QUery Intermediate REpresentations
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessCodeA11y: Making AI Coding Assistants Useful for Accessible Web Development
- 3 November 2024
- Published by Springer Nature
- p. 466-485
DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
- 3 November 2024
- Published by Springer Nature
- p. 466-485
DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
- Open Access
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
UIClip: A Data-driven Model for Assessing User Interface Design
User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a UI given its screenshot and natural language description. To train UIClip, we used a combination of automated crawling, synthetic augmentation, and human ratings to construct a large-scale dataset of UIs, collated by description and ranked by design quality. Through training on the dataset, UIClip implicitly learns properties of good and bad designs by i) assigning a numerical score that represents a UI design’s relevance and quality and ii) providing design suggestions. In an evaluation that compared the outputs of UIClip and other baselines to UIs rated by 12 human designers, we found that UIClip achieved the highest agreement with ground-truth rankings. Finally, we present three example applications that demonstrate how UIClip can facilitate downstream applications that rely on instantaneous assessment of UI design quality: i) UI code generation, ii) UI design tips generation, and iii) quality-aware UI example search.
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessUIClip: A Data-driven Model for Assessing User Interface Design
User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a UI given its screenshot and natural language description. To train UIClip, we used a combination of automated crawling, synthetic augmentation, and human ratings to construct a large-scale dataset of UIs, collated by description and ranked by design quality. Through training on the dataset, UIClip implicitly learns properties of good and bad designs by i) assigning a numerical score that represents a UI design’s relevance and quality and ii) providing design suggestions. In an evaluation that compared the outputs of UIClip and other baselines to UIs rated by 12 human designers, we found that UIClip achieved the highest agreement with ground-truth rankings. Finally, we present three example applications that demonstrate how UIClip can facilitate downstream applications that rely on instantaneous assessment of UI design quality: i) UI code generation, ii) UI design tips generation, and iii) quality-aware UI example search.
- Open Access
DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with target labels using code generation. Our method allows people to create datasets with built-in labels and train models with a small number of human-annotated examples. We demonstrate performance improvements in three tasks for understanding slides and UIs: recognizing visual elements, describing visual content, and classifying visual content types.
Open AccessDreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with target labels using code generation. Our method allows people to create datasets with built-in labels and train models with a small number of human-annotated examples. We demonstrate performance improvements in three tasks for understanding slides and UIs: recognizing visual elements, describing visual content, and classifying visual content types.