Seongsu Bae
Ph.D. Candidate @ KAIST AI
I'm interested in semantic interfaces — AI that expands what humans can understand and do, not just what it can automate. I build them for healthcare and study how to rigorously measure them. Advised by Edward Choi.
Life
Gallery →Seoul
Tokyo
NeurIPS
Jeju
Beijing
Lab
Selected Publications
All 14 →ListenCare: Encounter-Grounded Audio Question Answering for Long-Form Clinical Conversation Speech
Seongsu Bae*, Chaeeun Sim*, Sungbae Park, Edward Choi
KorMedMCQA-V: A Multimodal Benchmark for Evaluating Vision-Language Models on Korean Medical Licensing Exam
Byungjin Choi*, Seongsu Bae*, Sunjun Kweon, Edward Choi
EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
Seongsu Bae*, Daeun Kyung*, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi
Graph-Text Multi-Modal Pre-training for Medical Representation Learning
Sungjin Park, Seongsu Bae, Jiho Kim, Tackeun Kim, Edward Choi
Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture
Seongsu Bae, Daeyoung Kim, Jiho Kim, Edward Choi
Background
Microsoft Research Asia
Research Intern · Text-to-Image, Multi-modal QA
KAIST AI
Ph.D. Candidate · Edward Choi Lab
KAIST AI
M.S. · Edward Choi Lab
Talks
W&B Korea — Evaluation & Benchmark
2025Stanford MedAI — EHRXQAvideo
2024Microsoft Research — EHRXQA
2023