Seongsu Bae
seongsu@kaist.ac.kr
Live as if you were to die tomorrow. Learn as if you were to live forever.
mahatma gandhi
I am currently in my third year as a Ph.D. candidate in Artificial Intelligence at KAIST AI, under the guidance of Professor Edward Choi. My research spans across natural language processing, healthcare AI, and multi-modal learning. My specific aim is to develop sophisticated AI systems that not only understand human language but can also assist in complex decision-making processes. I am currently working on a project about the multi-turn problem-solving ability of AI.
Current projectS
🔥Evaluating and Developing Multi-Turn Problem-Solving Ability for AI
Research Focus: Large Language Models, Evaluation, Reinforcement Learning
🔥Clinical Note Assistant in Hospitals
Research Focus: Speech-to-Text, Large Language Models, Evaluation, Domain-Specific AI
Work Experience
Research Intern at Microsoft Research Asia, Beijing, China (2022/10-2023/04)
Research Topic: Text-to-Image Generation, Multi-modal Question Answering
Advisor: Eric Chang and Lei Ji
Publications
2025
- PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
Daeun Kyung, Hyunseung Chung, Seongsu Bae, Jiho Kim, Jae Ho Sohn, Taerim Kim, Soo Kyung Kim, Edward Choi
Proc. of Neural Information Processing Systems (NeurIPS) 2025 Datasets and Benchmarks (Spotlight)
[Paper] [Code]
- AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
Qingqiu Li, Zihang Cui, Seongsu Bae, Jilan Xu, Runtian Yuan, Yuejie Zhang, Rui Feng, Quanli Shen, Xiaobo Zhang, Junjun He, Shujun Wang
Proc. of Neural Information Processing Systems (NeurIPS) 2025
[Paper] [Code]
2024
- Deep Learning-Based Landmark Detection Model for Multiple Foot Deformity Classification: A Dual-Center Study
Su Ji Lee, Hangyul Yoon, Seongsu Bae, Inyoung Paik, Jong Hak Moon, Seongeun Park, Chan Woong Jang, Jung Hyun Park, Edward Choi, Eunho Yang, Ji Cheol Shin
Yeonsei Medical Journal
- EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
Yeonsu Kwon*, Jiho Kim*, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi
Proc. of Neural Information Processing Systems (NeurIPS) 2024 Datasets and Benchmarks (Spotlight)
[Paper] [Code]
- Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records
Gyubok Lee, Sunjun Kweon, Seongsu Bae, Edward Choi
Proc. Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 2024 Clinical NLP Workshop – EHRSQL 2024 Shared Task (Oral)
- Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes
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
Findings in Association for Computational Linguistics (ACL) 2024
[Paper] [Code]
2023
- 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
Proc. of Neural Information Processing Systems (NeurIPS) 2023 Datasets and Benchmarks
[Paper] [Code(ehrxqa)] [Code(mimic-cxr-vqa)]
- ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
Jungwoo Oh, Gyubok Lee, Seongsu Bae, Joon-myoung Kwon, Edward Choi
Proc. of Neural Information Processing Systems (NeurIPS) 2023 Datasets and Benchmarks
[Paper] [Code]
- KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization
Gangwoo Kim, Hajung Kim, Lei Ji, Seongsu Bae, Chanhwi Kim, Mujeen Sung, Hyunjae Kim, Kun Yan, Eric Chang, Jaewoo Kang
The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
[Paper]
2022
- EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
Gyubok Lee, Hyeonji Hwang, Seongsu Bae, Yeonsu Kwon, Woncheol Shin, Seongjun Yang, Minjoon Seo, Jong-Yeup Kim, Edward Choi
Proc. of Neural Information Processing Systems (NeurIPS) 2022 Datasets and Benchmarks
[Paper] [Code]
- Graph-Text Multi-Modal Pre-training for Medical Representation Learning
Sungjin Park, Seongsu Bae, Jiho Kim, Tackeun Kim, Edward Choi
Proc. of Health, Inference, and Learning (CHIL) 2022
[Paper] [Code]
- Uncertainty-Aware Text-to-Program for Question Answering on Structured Electronic Health Records
Daeyoung Kim, Seongsu Bae, Seungho Kim, Edward Choi
Proc. of Health, Inference, and Learning (CHIL) 2022
[Paper] [Code]
2021
- Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture
Seongsu Bae, Daeyoung Kim, Jiho Kim, Edward Choi
Proc. of Machine Learning for Health (ML4H) 2021 (Oral Spotlight)
[Paper]
Services
Reviewer
- 2024: CVPR, CHIL, NeurIPS D&B, ACL ARR (Feb, April, June), COLM, JMIR
- 2023: ML4H, CHIL, NeurIPS D&B, EMNLP
- 2022: CVPR, CHIL, NeurIPS D&B
Invited Talks
- 03/2025: Weights & Biases Korea
Title: Quantitative/Qualitative Evaluation for Trustworthy AI: Evaluation and Benchmark
- 02/2024: Stanford MedAI
Title: EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images [Youtube]
- 09/2023: Microsoft Research (MSR)
Title: EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images