Jeong Woo Lee

Jeong Woo Lee

I will join the University of California, Irvine as a Master of Computer Science student in Fall 2026. I completed my B.S. in Electronics and Electrical Engineering at Dongguk University, where I am currently an undergraduate research assistant at ML-Lab, advised by Prof. Jihie Kim. My research focuses on reasoning over structured and visual data — table reasoning and chart/document understanding for LLMs and VLMs. Feel free to reach out via GitHub or email.

Jeong Woo Lee

Education

University of California, Irvine
Master of Computer Science (MCS) · Irvine, CA
Dongguk University
B.S. in Electronics and Electrical Engineering (GPA 4.15/4.5, Rank 16/156) · Seoul, KR
Tech University of Korea
B.S. coursework in Embedded Systems (GPA 4.08/4.5) · Gyeonggi, KR

Experience

ML-Lab, Dongguk University — Undergraduate Research Assistant
Advisor: Prof. Jihie Kim · Seoul, KR

Researched table and chart reasoning for LLMs and VLMs, building the TabBridge and VisDoT frameworks and co-authoring five papers, including an ACL Workshop Best Paper Award.

Publications

  1. Jeongwoo Lee, Eunsoo Lee, Jihie Kim. “TabBridge: Bridging Structure and Context for Accurate Table Reasoning.” ACL Workshop, 2026Best Paper Award.
  2. Eunsoo Lee, Jeongwoo Lee, Minki Hong, Jangho Choi, Jihie Kim. “VisDoT: Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought.” EACL Findings, 2026.
  3. Jeongwoo Lee, Yongbin Kim, Jihie Kim. “Comparative Insights into Open-source and Closed-source LLMs for Complex Table Question Answering.” ISIS, 2025.
  4. Jeongwoo Lee, Eunsoo Lee, Jihie Kim. “Table Interpretation using Least-to-Most Prompting for LLMs.” KICS, 2025.
  5. Jeongwoo Lee, Eunsoo Lee, Minki Hong, Jihie Kim. “LLM-based Table Data Inference using Data Augmentation and Few-Shot Prompting.” HCLT, 2024.

Projects

E-MOJI — Personalized AI Emoji Web Service
Leader & Full-Stack Developer · Seoul, KR

Led full-stack development integrating a React frontend with a Django backend, and deployed the service on AWS EC2 with Prometheus-Grafana monitoring.

ReBike — Smart Waste Detection Website
Front-end Developer · Seoul, KR

Built the front-end in React (migrated JavaScript to TypeScript) and integrated a custom-trained YOLOv5 model for real-time detection.

Awards & Honors

  • Best Paper Award — ACL Workshop, 2026 (TabBridge)
  • TA Scholarship — Dongguk University, 2025
  • Academic Excellence Award — Dongguk University (2 semesters) & Tech University of Korea (3 semesters)
  • Top 10 Finalist, Techeer — 2022
  • Gold Award — TU Startup Competition, Silicon Valley Summer Bootcamp, Embedded Systems Competition for Freshman