Angela Chen is an innovator, creator, and entrepreneur with a PhD in Human-AI Interaction from Carnegie Mellon University. Her work pioneers human-centered AI technology to

deepen interpersonal connection.

With a background in statistics, AI, robotics, and HCI, she brings scientific rigor and scalable engineering to uncover insights into the complex web of social interaction.

Education

Carnegie Mellon University

Ph.D. in Robotics at the School of Computer Science, Specialized in Human-AI Interaction

Dissertation: Behavioral Modeling of Interpersonal Dynamics as Controllable Agentic Systems: Empirically-grounded Adaptive Virtual Patients for Psychotherapy Training (teaser)

Generative AI in Healthcare Fellow @ Carnegie Mellon University Center for Machine Learning and Health

Teaching assistant for Human-Robot Interaction‍ ‍

Reviewer for top-tier international conferences: CHI, UIST, CSCW, NeurIPS, AAAI, CHIL, FAccT, HAI

University of Illinois at Urbana-Champaign

Master of Science in Statistics

Bachelor of Science in Statistics

Computational Genomics Fellow @ National Center for Supercomputing Applications

Recent Publications and Projects

  • Simulating Multi-party Interaction in Psychotherapy

    The First Known Multi-agent Framework for Training Couples Therapists

    Learn More

  • Behaviorally-adaptive LLM-Based Virtual Patients for Psychotherapy Training

    Making the Consequences of a Therapist’s Choice Visible

    Learn More

  • Empirical Modeling of Therapist–Client Dynamics Using LLM-Based Assessments

    Based on 2,000 Hours Clinical Psychotherapy Transcripts

    Learn More

  • Foundation Models for Healthcare

    Adapting Frozen Univariate Time Series Foundation Models for Multivariate Healthcare Time Series

    Learn More

  • Time Series Foundation Models

    Generalized Prompt Tuning: How to Use a Frozen Pre-Trained Univariate Time Series Foundation Model for Multivariate Time Series Prediction

    Learn More

  • Trustworthy AI Design Specifications

    Evaluating a Machine Learning Model’s Trustworthiness via Data-driven Design Specifications

    Learn More

  • Human-Robot Trust Design

    ”Do it my way!”: Impact of Customizations on Trust Perceptions in Human-Robot Collaboration

    Learn More

  • Home Robot System Design

    AquaBot: Assistive Drinking Robot for the Mobility-impaired

    Learn More

Her previous research explored genetic contributions to various traits using statistical modeling:

Chen, A., & Lipka, A. (2016). The use of targeted marker subsets to account for population structure and relatedness in genome-wide association studies of maize (Zea mays L.). G3: Genes, Genomes, Genetics, 6(8), 2365-2374.

Chen, A., Ge, W., Metcalf, W., Jakobsson, E., Mainzer, L., & Lipka, A. (2019). An assessment of true and false positive detection rates of stepwise epistatic model selection as a function of sample size and number of markers. Heredity, 122(5), 660-671.