
Ryan Louie
rylouie@cs.stanford.edu
Computer Science Department
Stanford University
I am a postdoc in Stanford's Computer Science department, affiliated with the Stanford NLP and HCI groups and advised by Diyi Yang and Emma Brunskill. I received my PhD from Northwestern's Technology and Social Behavior program, where I worked closely with Prof. Haoqi Zhang and Darren Gergle on Human-AI Interaction and Social Computing research topics. Prior to that, I received my B.S. in Robotics from Olin College of Engineering.
My research advances human-centered AI approaches to create systems that assist in activities that promote personal well-being. I have built human-AI systems help train novice counselors to effectively support patients (mental health), empower novice composers to create music that expressively communicates their ideas or emotions (creativity), and enable friends to connect via collective experiences across distance (social connection). Motivated by these application domains, I invent technical methods for improving how humans can customize and collaborate with AI. This involves making it easier for humans to communicate their goals (eliciting intentions, tasks, feedback) and for AI systems to meaningfully align with them (steering, fine-tuning, adapting). I then conduct experimental studies and real-world deployments to understand how design choices in a human-AI system impact human behavior and user experience.
I am on the job market in Fall 2025! Please contact me about any full-time opportunities in the academic and industry market in the areas of Human-Centered AI and LLMs for Mental Health.
Research Areas
Mental Health with LLM Skill Training: Starting in my postdoc, my research inquiry has focused on creating LLM-powered systems for mental health and well-being. The global mental health crisis currently suffers from a demand-capacity problem, in which 1 in 8 people worldwide live with a mental disorder, and the demand for mental health services far exceeds supply. This demands innovative approaches to scale high-quality care. There are many contexts where help seekers need human support, yet effective training for human counselors is lacking or not scalable. To address this, I have developed CARE, an AI powered platform for psychotherapy skills training, where novice counselors can practice role-playing with simulated patients and receive tailored feedback from AI mentors. To ensure LLMs produce realistic patient simulations and faithful feedback, my work contributes novel tools and techniques for customizing LLMs for counseling training—with a focus on human-AI collaboration pipelines to elicit knowledge from mental health experts and optimize LLM outputs to be aligned with domain-feedback. My work uses experimental methods—including randomized trials with 90+ counselors and micro-randomized trials in psychotherapy classrooms—to understand how LLM-simulated practice can upskill and enhance educational activities.

.
Under review at CHI 2026.

.
EMNLP 2024 Main.

.
ACL 2024 Main.
Frameworks for Human-AI Systems and Evaluation

.
Doctoral dissertation, Northwestern University.
Creativity with Generative AI

.
Workshop on Generative AI and HCI, CHI 2024.

.
IUI 2022.
Social Connection via Context-Aware AI

.
CHI 2022.

.
CSCW 2020.