CV
Research Interests
Human–Computer Interaction (HCI), Generative UI, Computer-use Agents, and Human–AI Interaction.
Education
University of Michigan, Ann Arbor · Aug 2025 – May 2027 (expected)
B.S.E. in Computer Science · GPA: 3.86/4.00
Shanghai Jiao Tong University · Aug 2023 – Aug 2027 (expected)
B.Eng. in Electronic and Computer Engineering
Publications
A11yLTLNav: Automatic Detection of Accessibility Navigation Failures
Chenming Ge, Kewen Peng, Chengyang Shi, Ben Greenman, Yue Jiang
arXiv:2609.17959, 2026. Submitted to CHI 2027. First author.
Detects accessibility problems during web interaction, such as lost keyboard focus and missing feedback after an action. Human reviewers confirmed 274 of 309 reports (88.7% precision) on 31 generated websites.
Revision-Based Learning from Interactive Experience and Feedback (RELIEF)
Jiawen Li, Chenming Ge, Alice Gao, Rishab Vempati, Yi-Hao Peng, Jason Wu
Manuscript, 2026. Submitted to NAACL 2027.
RELIEF turns feedback-guided revisions of generated interfaces into training supervision for code generation models. We collected 355 interaction recordings and accompanying feedback from 24 users across 200 generated websites; critiques inferred from human interaction recordings led to the largest observed usability improvements across the two models tested.
Paper (PDF) · Research Experience
Research Experience
A11yLTLNav: Automatic Detection of Accessibility Navigation Failures
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.
- Formalized common accessibility failures from prior user studies as Linear Temporal Logic (LTL) properties and tested them on randomly generated website interaction traces.
- Built a comparison web agent that detected accessibility failures through screen-reader feedback and keyboard-only interaction.
- Evaluated the checker on 31 generated websites; human reviewers confirmed 274 of 309 reports (88.7% precision).
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.
- Built a pipeline to generate websites, collect task interaction traces in a user study, diagnose usability problems, and automatically repair websites using the resulting critiques.
- Explored fine-tuning UI generation models using websites revised with usability critiques. RELIEF reconstructed the corresponding generation traces for supervised fine-tuning.
- Explored computer-use agents and coding agents as baselines for simulating user behavior and providing usability feedback.
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.
- Paired a coding-agent-driven website version generator with a web agent to study adaptation to evolving interfaces.
- Extracted generalizable meta-level reflection rules from agent failure modes, improving performance by 19.6% over an ExpeL baseline.
- Worked on a knowledge-graph pipeline to automatically identify tasks affected by website version changes.
- Containerized multiple website versions with Docker using BrowserGym and AgentLab.
Earlier work is available under More Projects.
Skills
- Frameworks & platforms: PyTorch, Hugging Face, CUDA, Docker, Linux, React, Vue, Vite, OpenAI SDK
- Programming: Python, C/C++, Java, Rust, HTML/CSS/JavaScript, TypeScript, SQL, MATLAB
- Tools: Figma, Illustrator, Remotion, MATLAB, Codex, Claude Code, SolidWorks, LabVIEW