Research

The big question for my research is: how should we best prepare humans for the AI era? To this end, I design, build, and evaluate LLM applications to foster AI literacy, optimize human–AI task delegation, and support effective human–AI workflows, especially in programming and computing education. I conduct mixed-methods research to investigate how people collaborate and learn with AI systems, and design systems and frameworks to support training and evaluation of effective human–AI teams. I frame my work around the key research questions of what to teach, how to teach, and how to evaluate.

Jump to: Selected Projects · Publications · Invited Talks

Overview of my research: what to teach (pAIr, DSPM), how to teach (HypoCompass, ROPE, ImaginAItion), and how to evaluate (SPHERE, RECAP)

Publications

* equal contribution † mentoring · See also Google Scholar.

Preprints & In Submission

Conference & Journal Papers

Workshops, Posters & Doctoral Consortia

Invited Talks

  • Aug 2026The Impact of Expertise on AI-Assisted Work
    Microsoft
  • Spring 2026What to Teach and How to Teach Programming in the AI Era
    Penn, Cornell, Columbia, UMich, UChicago, UCI, UCSD, UC Berkeley, Stanford, UIUC, HKUST (Guangzhou), UW
  • Dec 2025Training Future-Proof Developers
    HKU, HKUST, ECNU
  • Dec 2025AI × Future of Work Series: Workforce Preparation on AI Literacy (Keynote)
    Plug and Play Tech Center
  • Oct 2025Training Requirement-Driven LLM Use for Prompt Programming
    Mila HCAI Seminar
  • Fall 2025Training the Use of LLMs on Programmatic Data Science for Non-Experts
    Bloomberg, University of Pittsburgh
  • Aug 2025Sister Conferences Best Paper Presentation
    IJCAI 2025, Montreal
  • Jun 2025IAALDE-Network Best Paper Presentation
    CSCL/ISLS 2025, Helsinki
  • Fall 2024Training for the Future: Preparing Students for Human–LLM Partnerships
    UMich, CMU, Pitt
  • Aug 2024Scaling Student Support: Online Question-Answering with LLM Tutors
    Google DeepMind