About Me

I am a builder passionate about advancing human-AI collaboration to improve our productivity and creativity. I love studying how people work and building solutions to help them work better. I am currently a machine learning engineer at Adobe, where I build and evaluate agentic systems for data analytics products.

I completed my Ph.D. in Computer Science at Northwestern University, advised by Matthew Kay. Back in my Ph.D. days, I built adaptive, scalable, and human-centered AI systems for data visualization and education. I also worked across fields and institutions to explore my interdisciplinary interests: I co-directed EAAMO Bridges; I built mortality estimation models at the Max Planck Institute for Demographic Research; I developed statistical methods for disparity estimation at Stanford's RegLab; I built machine learning solutions for the 988 Lifeline as a Data Science for Social Good fellow at Carnegie Mellon University.

Experience

• Machine Learning Engineer 2025 – present
  Adobe Inc. · Customer Experience Orchestration
  Designing and developing agentic systems for Adobe Customer Journey Analytics (B2B product). Co-leading the evaluation strategy and reporting for Data Insights Agent. Developed an AI-based data storytelling solution that is in production (demoed to CEO and filed for patent). Built an classifier for routing AI agents that is in production.
  Data Storytelling Data Insights Agent
• Ph.D. Researcher and Engineer 2020 – 2025
  Northwestern University
  Also at: Carnegie Mellon · Stanford · Max Planck Institute · UMD · UChicago
  Designed and developed adaptive, scalable, and human-centered AI systems for data visualization and education. Published 7 full papers at top-tier HCI and data visualization conferences.
  Publications
  ▸ See details (5 selected experiences)
  • Visiting Ph.D. Researcher 2024 – 2025
    University of Maryland · FIGX Lab
    Developed an interactive AI-powered system for educational assessment authoring. Led a team of 10+ undergraduate students. Full paper accepted to CHI 2026.
    Ripplet
  • Social Data Science Researcher 2024
    Max Planck Institute for Demographic Research
    Built statistical models to estimate age-specific mortality in a data-scarce context. Coauthored a paper accepted to PAA 2025.
    PAA Poster
  • Graduate Fellow 2023
    Stanford University · RegLab
    Designed statistical sampling techniques to estimate racial disparity when data is scarce. Analyzed a healthcare dataset with ~7M Americans' records.
  • Data Science Fellow 2022
    Carnegie Mellon University · DSSG
    Built a machine learning system to improve call routing of the 988 Lifeline, which serves ~2M callers per year.
    Code
  • Research Intern 2022
    University of Chicago · Consortium on School Research
    Built statistical models on Chicago Public Schools data to predict students' graduation rates.

Selected Publications

• Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers' Workflows
  Yuan Cui, Annabel Goldman, Jovy Zhou, Xiaolin Liu, Clarissa Shieh, Joshua Yao, Mia Cheng, Matthew Kay, Fumeng Yang
  ACM CHI ACM Conference on Human Factors in Computing Systems (CHI), 2026
  Paper Demo Software
• AVEC: An Assessment of Visual Encoding Ability in Visualization Construction
  Lily W. Ge, Yuan Cui, Matthew Kay
  ACM CHI ACM Conference on Human Factors in Computing Systems (CHI), 2025
  Paper Software
• Promises and Pitfalls: Using Large Language Models to Generate Visualization Items
  Yuan Cui, Lily W. Ge, Yiren Ding, Lane Harrison, Fumeng Yang, Matthew Kay
  IEEE VIS IEEE Visualization Conference (VIS), 2024
  Paper
• Adaptive Assessment of Visualization Literacy
  Yuan Cui, Lily W. Ge, Yiren Ding, Fumeng Yang, Lane Harrison, Matthew Kay
  IEEE VIS IEEE Visualization Conference (VIS), 2023
  Paper Demo Code
• CALVI: Critical Thinking Assessment for Literacy in Visualizations
  Lily W. Ge, Yuan Cui, Matthew Kay
  ACM CHI ACM Conference on Human Factors in Computing Systems (CHI), 2023
  Paper

News