Collaborative Social Technologies Lab

JeonggyuKang

I study how groups of people — and groups of language models — think together.

COLM 2026 (co-first author) · 1st Place — NASA Space Apps Seoul · ex-Samsung Electronics

Jeonggyu Kang
Position
M.S. Student, School of Computing, KAIST
Advisor
Prof. Joseph Seering
Research
Human-centered NLP, multi-agent systems, group interaction
Contact
jeonggyumarkk@kaist.ac.kr

I'm a first-year Master's student at KAIST's School of Computing, working with Prof. Joseph Seering in the Collaborative Social Technologies Lab. I work on human-centered NLP, multi-agent systems, and the computational analysis of group interaction. Most recently, I co-led TIDES, a longitudinal bilingual dataset for modeling multi-party social dynamics, accepted to COLM 2026 as co-first author.

01

News

  • 2026-07TIDES, a longitudinal bilingual dataset for multi-party social dynamics, accepted to COLM 2026 (co-first author)
  • 2026-03Started M.S. at KAIST School of Computing, Collaborative Social Technologies Lab
  • 2025-101st Place & Global Honorable Mention (worldwide) at NASA Space Apps Challenge Seoul 2025
  • 2025-09Joined KAIST CSTL Lab as Undergraduate Research Intern
  • 2024-08Started internship at Samsung Electronics, Device Solution Division
02

Featured

COLM 2026 · Publication

TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics

A corpus of real team meetings, annotated with speaker roles, developmental stages, and interaction-process categories. Co-first author.

12 teams · 104 meetings · 76K+ utterances

human-centered nlp · group dynamics · dataset

2025 · Project

Space Biology Knowledge Explorer

A knowledge graph and retrieval system for searching NASA space biology literature.

1st Place & Global Honorable Mention — NASA Space Apps

hackathon · knowledge graph · retrieval

03

Index

Research
Projects
CV