Hi! I am

Zexuan Li

I am a second year Ph.D. student at University of Michigan School of Information advised by Eytan Adar. I work on designing and evaluating interactive systems for complex analytical workflows. I am particularly interested in how human-centered systems can support interpretation, collaboration, and sensemaking with AI.
I gradated from Carnegie Mellon University with a bachelor's degree in Human-Computer Interaction and Information Systems.

Publications

ACM HEALTH 2026

It's Not Just for Trust: Designing for Emerging Uses of Explainable AI in Clinical Decision-Making

Katelyn Morrison, Zexuan Li, Minsuk Kim, Chengqi (Malia) Hong, Jidapa Kraisangka, Priscilla Correa-Jaque, Charles Fauvel, Sandeep Sahay, Rebecca R. Vanderpool, Allen Everett, Shili Lin, Manreet Kanwar, Raymond Benza, Adam Perer

Iteratively prototyping explainable AI for an AI-powered clinical decision-support system with clinical stakeholders, uncovering four emerging uses beyond trust: exploring treatment options, reflecting on treatment plans, communicating with stakeholders, and supporting health education.

ACM DL

CHI 2025

Divisi: Interactive Search and Visualization for Scalable Exploratory Subgroup Analysis

Venkatesh Sivaraman, Zexuan Li, Adam Perer

An interactive notebook-based tool for exploratory subgroup analysis, featuring a novel approximate subgroup discovery algorithm and the Subgroup Map visualization.

ACM DL arXiv

Projects

PHORA

Research · Design · Development

Designed and implemented a Clinical Decision Support Tool (CDSS) with visual explainability features for AI-based risk prediction in Pulmonary Arterial Hypertension.

View study →

SurVis

UX Research · Design

A zoonotic disease reporting platform streamlining reporting, tracking, and communication for veterinarians.

Totem

UX Research · Design

A collaborative trip-planning browser extension for effective group planning with mood boards.