Last update - 23/11/26
Visiting Student Researcher @ Allen Institute for AI (Mosaic Team), Seattle.
Undergrad @ Seoul National University (Electrical & Computer Engineering). Seoul.
Ex- ML Engineer @ Hyperconnect (acquired by Match Group for $1.7B). Seoul.
My goal is to build AI systems that collaborate with people to make decisions when solving real-world problems, including scientific research, education, and mental health support. To achieve this mission, I am particularly interested in enhancing AI systems to be more user-friendly as I firmly believe the technology should focus on people using AI systems. Methodologically, my recent interest lies in scalable methods, including learning without human supervision (weakly supervised learning — CHAMPAGNE), learning through interaction, and evaluating models with the assistance of other AI models (building a benchmark — NormLens).
Previously, I worked on research and engineering at Hyperconnect (acquired by Match Group for $1.7B), solving product-related problems (PC Softmax & LADE) and build social chatbot product (DRESS, PDP, CORGE, G2R, Attentron) to solve people’s loneliness.
I like workouts in the gym and singing music. p.s. I participated in building a product (GYMWORK) to assist people with their workout routines!
|Oct 8, 2023||Our recent work on defeasible visual-grounded commonsense norms is accepted to EMNLP 2023 and will be presented in oral session!|
|Mar 20, 2023||Our work done in collaboration with AI2 is online! And this paper got accepted to ICCV 2023!|
|Oct 6, 2022||One paper, which I participated as a first author, is accepted to EMNLP 22 Findings!|
|Sep 20, 2022||I am really grateful to start research collaboration with AI2 hosted by Youngjae and advised by Yejin!|
|Apr 8, 2022||One paper, which I participated as a first author, is accepted to NAACL 2022!|
EMNLPReading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense NormsIn Conference on Empirical Methods in Natural Language Processing (EMNLP, Oral Presentation) 2023
ICCVCHAMPAGNE: Learning Real-world Conversation from Large-Scale Web VideosIn International Conference on Computer Vision (ICCV) 2023
EMNLPMeasuring and Improving Semantic Diversity of Dialogue GenerationIn Conference on Empirical Methods in Natural Language Processing (EMNLP Findings) 2022
NAACLMeet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few UtterancesIn Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Short) 2022
ACL WorkshopUnderstanding and Improving the Exemplar-based Generation for Open-domain ConversationIn 4th NLP for Conversational AI (Oral, Outstanding Paper), Annual Meeting of the Association for Computational Linguistics (ACL) 2022