Hi, I am Xinyi Lu, a third-year PhD student at University of Michigan, advised by Prof. Xu Wang. Before that, I got my B.S degree from both University of Michigan (majoring in Computer Science), and Shanghai Jiao Tong University (majoring in Electrical and Computer Engineering).
I'm interested in AI in Education. My work focuses on designing AI tools and human-AI interactions to facilitate experts in creating educational content, which ultimately supports students in developing expertise for complex and challenging tasks. To achieve this, I design and develop AI assistance that follows effective learning practices, and aligns with and augments human experts' cognitive processes, while preserving user agency, grounded in the following questions:
- How can we help human experts externalize and transfer their tacit knowledge to students (through educational contents) and to AI systems (through input)?
- How to design AI assistance and human-AI interactions that blend into experts natural workflow, augmenting rather than disrupting their process?
To design and evaluate these innovations, I apply both qualitative lab studies and large-scale classroom studies.
News
| July, 2025 | I will present our work on exploring LLM-Generated feedback on knowledge-intensive essays at AIED 2025 |
| April, 2025 | I will present Generative Student at NCME Annual Meeting and attend CHI 2025 |
| July, 2024 | I will present Generative Student at L@S 2024 in Atlanta |
| August, 2023 | Graduated from SJTU and UMich 🎓 |
| April, 2023 | ReadingQuizMaker won Best Paper Honorable Mention Awards at CHI 2023 🏆 |
| April, 2023 | I will present ReadingQuizMaker at CHI 2023 in Hamburg |
Selected Publications
Xinyi Lu, Aditya Mahesh*, Zejia Shen*, Mitchell Dudley, Larissa Sano, Xu Wang
AIED'2025
Paper
Xinyue Chen, Nathan Yap, Xinyi Lu, Aylin Gunal, Xu Wang
CSCW'2025
Paper
Xinyi Lu, Xu Wang
Learning@Scale'2024
Paper
Hosted Workshops
Steven Moore, Anjali Singh, Xinyi Lu, Hyoungwook Jin, Hassan Khosravi, Paul Denny, Christopher Brooks, Xu Wang, Juho Kim, John Stamper
Learning@Scale'2024, Learning@Scale'2025
Website
Projects
We use explore different RL-based AI Agents that are short-sighted, moderate, and far-sighted on game strategies, and compared their performance on a simulated environment of the Board Game, Manila.
Report
This is a party game of cats' and dogs' rivalry created with Unity game engin. Players play as a cat and a dog and build their own game map to seize the flag and claim victory. With an intuitive block-building system, players can design and customize their own unique game maps, complete with obstacles, traps, and other challenges.
Game