Elara
  • Home
  • Research
  • Projects
  • CV
  • Home
  • Research
  • Projects
  • CV
GitHubLinkedInInstagramORCIDBlueskyRSS Feed

© 2025 Elara Liu | All rights reserved.

Themed by EnjuFolio · Crafted by Elara Liu

Research

Selected research projects and works-in-progress, ordered by year.

  • 2025

  • Designing With Caregivers: Power, Involvement, and Relations in Health-Related HCI

    Jun Zhu, Zhuoran Liu, Hee Rin Lee·CHI 2027

    Status: In preparation•Role: Co-author

    Advised by: Dr. Hee Rin Lee (Michigan State University)

    HCI health research often focuses on the patient, treating caregivers as background infrastructure rather than active users. This systematic review analyzes how caregivers are recruited, represented, and designed for across the HCI corpus. By mapping patterns of power, clinical authority, and interdependence, we articulate how current methods obscure the relational nature of care and offer a framework for more equitable caregiver involvement.

  • Coach-Style LLM Assistant for Safe Lab Automation on the Jubilee Platform

    Zhuoran Liu, Danli Luo, Karan Ahuja, Nadya Peek·CHI 2027

    Status: In preparation•Role: Co-lead author

    Advised by: Dr. Nadya Peek (University of Washington)

    I am developing a coach-style LLM assistant that turns wet-lab researchers’ plain-English goals into safe Jubilee automation code. By bridging verified APIs with documentation-grounded logic, the system runs dry-run simulations and safety checks before execution, supporting a mixed-initiative workflow that balances automation with human oversight.

  • Smartwatch IMU foundation model for human activity recognition

    Aidan Bradshaw, Zhuoran Liu, Riku Arakawa, Arnav Choudhry, Xin Liu, Karan Ahuja·ICML 2026

    Status: In preparation•Role: Co-author

    Advised by: Dr. Karan Ahuja (Northwestern University)

    I am co-developing a smartwatch IMU foundation model that aggregates and harmonizes multiple datasets, then pretrains self-supervised sequence models and tests them under leave-one-dataset and unseen-device protocols, aiming for a generalizable, well-documented model and recipe that transfers across devices, populations, and everyday conditions.

  • Not All Places Are The Same: Computationally Surfacing Regional Experience Differences from Online Reviews

    Zhuoran Liu, Medini Chopra, Haoqi Zhang·ICWSM 2026

    Status: In preparation•Role: Lead author

    Advised by: Dr. Haoqi Zhang (Northwestern University)

    I led an HCI/NLP project that uses Yelp reviews and guidebook priors to model how the same place categories afford different experiences across U.S. regions. The work surfaces "regional experiential signatures"—like king cake, picon punch, or tax-free outlet shopping—that current category-based recommenders flatten.

    Link

  • Cultural Underpinnings of Stress Relief: Exploring Cross-Cultural Coping Strategies

    Zhuoran Liu, Siren Wang, Talia Ben-Naim, Yilin Zhang

    Role: Team Lead

    Advised by: Dr. Nabil I Alshurafa (Northwestern University)

    I co-led a mixed-methods study of culturally diverse college students that links how they cope with stress to cultural upbringing and personality, combining surveys and text analysis to show when “Eastern vs. Western” narratives hold and when convenience and hybrid practices better explain real-world coping.

    Link

  • 2024

  • Mapping the Role of Wearable and mHealth Technologies in Stress: A Scoping Review

    Zhuoran Liu

    Role: Lead author

    Advised by: Dr. Nabil I Alshurafa (Northwestern University)

    I conducted a PRISMA-ScR scoping review of 42 studies using wearables, mHealth apps, and telemedicine for stress, mapping sensors, biomarkers, and scales to show where the field converges (HRV-focused pilots) and where evidence is thin (hormones, telemedicine, diverse populations) for future interventions.

  • 2023

  • Explainable AI–Driven Integration of Health and Sleep Metrics for Enhanced Cardiovascular Risk Prediction

    Zhuoran Liu·ICS Honor Program (UCI)

    Status: Completed•Role: Individual undergraduate researcher

    Advised by: Dr. Mohammad Moshirpour (University of California, Irvine)

    I led an honors thesis that builds an interpretable ML model combining standard cardiovascular risk factors with sleep quality, duration, and efficiency, using regularized logistic regression and SHAP explanations to show how sleep shapes predicted risk and improves identification of high-risk individuals.