Hello, my name is Gyubok (pronounced KYOO-bok). I am currently completing my Ph.D. at KAIST AI under the supervision of Edward Choi. Starting this fall, I will be joining SB Intuitions (SoftBank) as a research scientist working on AI-driven drug discovery. I'll be based in Tokyo, so feel free to reach out if you'd like to grab coffee!

Research interests:

• LLM agents for large-scale clinical data (electronic health records)

• LLM agents for protein design

• Foundation models for cell biology (single-cell and bulk data)

Publications (*: Equal contribution)

• Multi Expert Integrated Algorithm for Kidney Biopsy Triage [PDF]

Hae-Ryong Yun, Nak-Hoon Son, Gyubok Lee, Hyung Woo Kim, Hyoungnae Kim, Tae Ik Chang, Jung Tak Park, Seung Hyeok Han, Shin-Wook Kang, Tae-Hyun Yoo

npj Digital Medicine 2026

• From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents [PDF]

Gyubok Lee, Woosog Chay, Heeyoung Kwak, Yeong Hwa Kim, Haanju Yoo, Oksoon Jeong, Meong Hi Son, Edward Choi

ICLR 2026

• FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering [PDF]

Gyubok Lee*, Elea Bach*, Eric Yang, Tom Pollard, Alistair Johnson, Edward Choi, Yugang Jia, Jong Ha Lee

ML4H 2025 Proceedings

• SCARE: A Benchmark for SQL Correction and Question Answerability Classification for Reliable EHR Question Answering [PDF]

Gyubok Lee*, Woosog Chay*, Edward Choi

ML4H 2025 Proceedings

• EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records [PDF]

Yeonsu Kwon*, Jiho Kim*, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi

NeurIPS 2024 Datasets and Benchmarks (Spotlight)

• EHR-SeqSQL: A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records [PDF]

Jaehee Ryu*, Seonhee Cho*, Gyubok Lee, Edward Choi

ACL 2024 Findings

• Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes [PDF]

Sunjun Kweon, Junu Kim, Jiyoun Kim, Sujeong Im, Eunbyeol Cho, Seongsu Bae, Jungwoo Oh, Gyubok Lee, Jong Hak Moon, Seng Chan You, Seungjin Baek, Chang Hoon Han, Yoon Bin Jung, Yohan Jo, Edward Choi

ACL 2024 Findings

• EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images [PDF]

Seongsu Bae*, Daeun Kyung*, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi

NeurIPS 2023 Datasets and Benchmarks

• ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram [PDF]

Jungwoo Oh, Gyubok Lee, Seongsu Bae, Joon-myoung Kwon, Edward Choi

NeurIPS 2023 Datasets and Benchmarks

• Exploration into Translation-Equivariant Image Quantization [PDF]

Woncheol Shin, Gyubok Lee, Jiyoung Lee, Eunyi Lyou, Joonseok Lee, Edward Choi

ICASSP 2023 (Oral, Top 3% recognition)

• EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records [PDF]

Gyubok Lee, Hyeonji Hwang, Seongsu Bae, Yeonsu Kwon, Woncheol Shin, Seongjun Yang, Minjoon Seo, Jong-Yeup Kim, Edward Choi

NeurIPS 2022 Datasets and Benchmarks

• Machine Learning Improves the Prediction Rate of Non-Curative Resection of Endoscopic Submucosal Dissection in Patients with Early Gastric Cancer [PDF]

Hae-Ryong Yun, Da Hyun Jung, Cheal Wung Huh, Gyubok Lee, Nak-Hoon Son, Jie-Hyun Kim, Young Hoon Youn, Jun Chul Park, Sung Kwan Shin, Sang Kil Lee, Yong Chan Lee

Cancers 2022 (IF: 6.575)

• Erythropoiesis Stimulating Agent Recommendation Model Using Recurrent Neural Networks for Patient with Kidney Failure with Replacement Therapy [PDF]

Hae-Ryong Yun*, Gyubok Lee*, Myeong Jun Jeon, Hyung Woo Kim, Young Su Joo, Hyoungnae Kim, Tae Ik Chang, Jung Tak Park, Seung Hyeok Han, Shin-Wook Kang, Wooju Kim, Tae-Hyun Yoo

Computers in Biology and Medicine 2021 (IF: 6.698)

• Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction [PDF]

Gyubok Lee*, Seongjun Yang*, Edward Choi

ACL 2021 (Oral)

• Diverse and Admissible Trajectory Forecasting Through Multimodal Context Understanding [PDF]

Seong Hyeon Park, Gyubok Lee, Manoj Bhat*, Jimin Seo*, Minseok Kang, Jonathan Francis, Ashwin Jadhav, Paul Pu Liang, Louis-Philippe Morency

ECCV 2020

• Unsupervised learning approach for network intrusion detection system using autoencoders [PDF]

Hyunseung Choi, Mintae Kim, Gyubok Lee, Wooju Kim

Journal of Supercomputing 2019 (IF: 2.469)

Workshops & Preprints (*: Equal contribution)

• Natural-Language-Guided Generator-Agnostic Shortlisting for Protein Binder Design [PDF]

Gyubok Lee, Kiwoong Yoo, Jimin Seo, Kyunghoon Hur, Edward Choi

ICML 2026 Workshop on Generative and Agentic AI for Biology

• Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling [PDF]

Kyunghoon Hur , Eunjung Jeon, Hyun Woo Kim, Gyubok Lee, Seongjun Yang

ICML 2026 AI for Science Workshop

• VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design [PDF]

Hyunjin Seo, Hongjoon Ahn, Jimin Park, Sungjun Han, Gyubok Lee, Soojung Yang, Joseph S Brown, Leo Chen, Gina El Nesr, Feyisayo Eweje, Sarah Gurev, Hyejin Lee, Cheng-Hao Liu, Junlang Liu, Zhihui Qi, Jason Yang, Gyu Rie Lee, Sungsoo Ahn, Jamin Shin, Sangwon Jung

arXiv preprint, 2026

• Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records [PDF]

Gyubok Lee, Sunjun Kweon, Seongsu Bae, Edward Choi

NAACL 2024 Clinical NLP Workshop (Oral) - Organizer, Shared Task on Reliable Text-to-SQL Modeling on EHRs

• Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL [PDF]

Yongjin Yang*, Sihyeon Kim*, SangMook Kim*, Gyubok Lee, Se-Young Yun, Edward Choi

ICLR 2024 Data Problems for Foundation Models (DPFM) Workshop

• TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring [PDF]

Gyubok Lee, Woosog Chay, Seonhee Cho, Edward Choi

arXiv preprint, 2024

Education

• Korea Advanced Institute of Science and Technology (KAIST) (2020.09 - 2026.08, Expected)

Ph.D. in Artificial Intelligence (Advisor: Edward Choi)

Area: Natural Language Processing and Machine Learning for Healthcare

• Yonsei University (2018.03 - 2020.08)

M.S. in Industrial Engineering - Data Science Track (Advisor: Wooju Kim)

Thesis: Improving Domain-Specific Neural Machine Translation by Leveraging In-Domain Monolingual Data

• Carnegie Mellon University (2019.08 - 2020.02)

Visiting student at Language Technologies Institute (Advisor: John Kang and Jaime Carbonell)

• University of Wisconsin–Madison (2010.09 - 2016.12)

B.B.A. in Actuarial Science

Work Experience

• Trillion Labs, Seoul, South Korea (2025.11 - 2026.05)

Research Intern, Technical Staff

Building multiscale biomedical foundation models spanning molecules, proteins, omics, biomedical knowledge, and clinical evidence.

• NAVER Cloud, Seongnam, South Korea (2024.10 - 2025.04)

Research Intern, Healthcare AI Team

Constructing benchmarks to build and evaluate conversational LLM agents in question answering over publicly accessible electronic health record databases (MIMIC-IV Demo and eICU Demo).

• Amazon, Sunnyvale, United States (2022.07 - 2023.01)

Applied Scientist Intern, Alexa AI - Natural Understanding Team

Improving zero-shot generalization of task-oriented dialog systems to new domains and tasks via instruction tuning and utterance–dialog act contrastive learning.