About Me

I am an undergraduate at the University of Michigan and Shanghai Jiao Tong University, studying Computer Science and Electronic and Computer Engineering.

My research explored how interaction feedback could improve AI-generated interfaces and support people and web agents. At Purdue University, I worked with Dr. Jason Wu on using interaction traces and feedback to improve generative UIs, contributing to RELIEF. I also worked with Dr. Yue Jiang and Dr. Ben Greenman at the University of Utah on detecting accessibility navigation failures, and with Prof. Honglak Lee at the University of Michigan on adapting web agents to evolving websites.

CV (PDF) · Email

Research Interests

Human–Computer Interaction (HCI), Generative UI, Computer-use Agents, and Human–AI Interaction.

Selected Publications

Figure 2 from the A11yLTLNav paper: pressing Enter on Add to List opens a dialog, but keyboard focus stays on the trigger instead of entering the dialog.

A11yLTLNav: Automatic Detection of Accessibility Navigation Failures

Chenming Ge, Kewen Peng, Chengyang Shi, Ben Greenman, Yue Jiang

arXiv, 2026. Submitted to CHI 2027. First author.

PDF Project Page

RELIEF's four-step workflow: generate an interface, collect feedback, revise the interface, and fine-tune the generation model using revised traces.

Revision-Based Learning from Interactive Experience and Feedback

Jiawen Li, Chenming Ge, Alice Gao, Rishab Vempati, Yi-Hao Peng, Jason Wu

Manuscript, 2026. Submitted to NAACL 2027.

PDF

Research Experience

Research Assistant, University of Utah · May – Sep 2026
Advisors: Dr. Yue Jiang and Dr. Ben Greenman

I developed A11yLTLNav, a property-based checker for accessibility navigation failures encountered by blind and low-vision users interacting with generated interfaces.

arXiv · Project Page

RELIEF: Revision-Based Learning from Interactive Experience and Feedback

Research Assistant, Purdue University · May – Oct 2026
Advisor: Dr. Jason Wu

I investigated how user interaction traces provided implicit feedback for improving the usability of generated interfaces. This work contributed to RELIEF, which used feedback-guided interface revisions to construct supervision for fine-tuning code generation models.

Paper (PDF) · Publication Details

WebCoEvo: Adversarial Co-Evolution for Web Agents

Research Assistant, University of Michigan · Mar – Jun 2026
Advisor: Prof. Honglak Lee

I developed WebCoEvo, an adversarial co-evolution framework that helped web agents adapt to changing websites by learning generalizable reflection rules from their failures.

More Projects →

Contact

You can reach me at gecm@umich.edu. My CV includes education and additional research details.