Seongyun Lee

Ph.D. Student at the KAIST AI

seongyun@kaist.ac.kr

About
Hello! I am a first-year Ph.D. Student at the KAIST AI, co-advised by Hyunwoo Kim and Minjoon Seo. Before that, I received my M.S. in Artificial Intelligence from KAIST AI and my B.S. in Computer Science from Korea University. My research aims to make evolving AI systems safe and aligned with human values as they face new challenges and risks. I’ve worked on multimodal learning, evaluation, hallucination mitigation, safety, and alignment and these days, I’m especially interested in tackling misalignment issues in agent systems.
Education

Korea Advanced Institute of Science and Technology (KAIST) Sep. 2025 - Present

Ph.D. Student (advisors: Hyunwoo Kim and Minjoon Seo)

Korea Advanced Institute of Science and Technology (KAIST) Mar. 2024 - Aug. 2025

M.S. in Artificial Intelligence (advisor: Minjoon Seo)

Korea UniversityMar. 2020 - Feb. 2024

B.S. in Computer Science

Publications

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

Seongyun Lee, Seungone Kim, Minju Seo, Yongrae Jo, Dongyoung Go, Hyeonbin Hwang, Jinho Park, Xiang Yue, Sean Welleck, Graham Neubig, Moontae Lee, Minjoon Seo

Preprint

Paper Code

Paper2code: Automating code generation from scientific papers in machine learning

Minju Seo, Jinheon Baek, Seongyun Lee, Sung Ju Hwang

Preprint

Paper Code

Scaling evaluation-time compute with reasoning models as process evaluators

Seungone Kim, Ian Wu, Jinu Lee, Xiang Yue, Seongyun Lee, Mingyeong Moon, Kiril Gashteovski, Carolin Lawrence, Julia Hockenmaier, Graham Neubig, Sean Welleck

Preprint

Paper

Efficient Long Context Language Model Retrieval with Compression

Minju Seo, Jinheon Baek, Seongyun Lee, Sung Ju Hwang

EMNLP 2025

Paper Code

Aligning to thousands of preferences via system message generalization

Seongyun Lee, Sue Hyun Park, Seungone Kim, Minjoon Seo

NeurIPS 2024

Paper Code

Evaluating language models as synthetic data generators

Seungone Kim, Juyoung Suk, Xiang Yue, Vijay Viswanathan, Seongyun Lee, Yizhong Wang, Kiril Gashteovski, Carolin Lawrence, Sean Welleck, Graham Neubig

ACL 2025

Paper Code

How does vision-language adaptation impact the safety of vision language models?

Seongyun Lee, Geewook Kim, Jiyeon Kim, Hyunji Lee, Hoyeon Chang, Sue Hyun Park, Minjoon Seo

ICLR 2025

Paper

Prometheus-vision: Vision-language model as a judge for fine-grained evaluation

Seongyun Lee, Seungone Kim, Sue Park, Geewook Kim, Minjoon Seo

Findings of ACL 2024

Paper Code

The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models

Seungone Kim, Juyoung Suk, Ji Yong Cho, Shayne Longpre, Chaeeun Kim, Dongkeun Yoon, Guijin Son, Yejin Cho, Sheikh Shafayat, Jinheon Baek, Sue Hyun Park, Hyeonbin Hwang, Jinkyung Jo, Hyowon Cho, Haebin Shin, Seongyun Lee, Hanseok Oh, Noah Lee, Namgyu Ho, Se June Joo, Miyoung Ko, Yoonjoo Lee, Hyungjoo Chae, Jamin Shin, Joel Jang, Seonghyeon Ye, Bill Yuchen Lin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo

NAACL 2025 (Best Paper Award)

Paper Code

Lg ai research & kaist at ehrsql 2024: Self-training large language models with pseudo-labeled unanswerable questions for a reliable text-to-sql system on ehrs

Yongrae Jo, Seongyun Lee, Minju Seo, Sung Ju Hwang, Moontae Lee

NAACL 2024 Clinical NLP Workshop (Oral)

Paper

Volcano: mitigating multimodal hallucination through self-feedback guided revision

Seongyun Lee, Sue Hyun Park, Yongrae Jo, Minjoon Seo

NAACL 2024 Main

Paper Code

Zero-shot dense video captioning by jointly optimizing text and moment

Yongrae Jo, Seongyun Lee, Aiden SJ Lee, Hyunji Lee, Hanseok Oh, Minjoon Seo

Preprint

Paper

LIQUID: A framework for list question answering dataset generation

Seongyun Lee, Hyunjae Kim, Jaewoo Kang

AAAI 2023

Paper Code
( * indicates equal contribution )

Vitæ

Full CV in PDF.

  • KAIST COCO Lab & LK Lab Sep. 2025 - Present
    Ph.D. Student (Advisor: Hyunwoo Kim and Minjoon Seo)
    Mitigating and Evaluating the Agentic Misalignment & Scheming for Trustworthy AGI
  • LG AI Research Apr 2025 - Dec 2025
    Research Intern (Mentors: Moontae Lee, Yongrae Jo)
    Monitoring and Enhancing the Robustness of the Chain-of-Thought for Large Reasoning Model
  • KAIST LK Lab Mar. 2024 - Aug. 2025
    M.S. Student (Advisor: Minjoon Seo)
    From Pre-trained Language Model To Trustworthy Multimodal Model
  • Twelve Labs June 2023 - Sep 2023
    Research Intern (Mentors: Raehyuk Jung, Minjoon Seo)
    Working on developing Video-Language Foundation Model, Pegasus-1
  • Korea University Mar. 2020 - Feb. 2024
    B.S. in Computer Science
Seongyun Lee
Last updated on April 23, 2022