- BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents
- Proxona: Supporting Creators' Sensemaking and Ideation with LLM-Powered Audience Personas
- Beyond Swipes and Scores: Investigating Practices, Challenges and User-Centered Values in Online Dating Algorithms
- Creator-friendly Algorithms: Behaviors, Challenges, and Design Opportunities in Algorithmic Platforms
- Stylette: Styling the Web with Natural Language
- Winder: Linking Speech and Visual Objects to Support Communication in Asynchronous Collaboration
- ProtoChat: Supporting the Conversation Design Process with Crowd Feedback
- Investigating How People Perceive AI-Generated Responses in Social Q&A
- Using LLMs to Investigate Correlations of Conversational Follow-up Queries with User Satisfaction
- Designing for AI-Powered Social Computing Systems
- Moderating Customer Inquiries and Responses to Alleviate Stress and Reduce Emotional Dissonance of Customer Service Representatives
- How Does Netflix “Understand” Me?: Exploring End-user Needs to Design Human-centered Explanations
- Leveraging the Crowd to Support the Conversation Design Process
Research Experience
Research projects include Generative Proxies, which are interactive, data-grounded representations of users’ diverse perspectives and goals, distilled from existing user data with LLMs. This enables understanding of intended users’ needs without synchronous user sessions and makes that understanding immediately usable for task completion, such as ideation (Proxona), evaluation (BloomIntent), and rapid prototyping (work-in-progress).
Education
Ph.D. student at KAIST, working with Prof. Juho Kim.
Background
Research interests: developing systems that simulate feedback to support users, focusing on understanding and supporting AI experiences (e.g., creator economy platforms) and delivering user-centered AI results (e.g., search, music recommendation). Looking for industry positions.
Miscellany
On the job market, interested in industry positions.