I am a PhD candidate at KAIST, co-advised by Kee-Eung Kim and Hongseok Yang.
Research Interest: Imitation learning, Reinforcement learning, Causal inference and Robust learning
E-mail: siseo [at] ai.kaist.ac.kr
CV: link
Education
2017. 09 - 2019. 08 : MS, School of Computing, KAIST, Korea (Advisor: Kee-Eung Kim)
Thesis: A study on generating explanations for reinforcement learning policies in control tasks
2011. 02 - 2017. 08 : BS, Computer Science and Mathematics, Sogang University, Korea
Publications
International
๐ Goal-Conditioned DPO: Prioritizing Safety in Misaligned Instructions
Joo Bon Maeng*, Seongmin Lee*, Seokin Seo, Kee-Eung Kim
Annual Conference of the Nations of Americas Chapter of the Association for Computational Linguistics (NAACL) 2025
Keywords: ย Reinforcement learning ย ย ย NLPย
๐ Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
Seokin Seo, Byung-Jun Lee, Jongmin Lee, HyeongJoo Hwang, Hongseok Yang, Kee-Eung Kim
Neural Information Processing Systems (NeurIPS) 2024
Keywords: ย Imitation learning ย ย ย Robust learningย
๐ Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models
Seongmin Lee*, Jaewook Shin*, Youngjin Ahn, Seokin Seo, Ohjoon Kwon, Kee-Eung Kim
arxiv 2409.19382 (https://arxiv.org/abs/2409.19382)
Keywords: ย Reinforcement learning ย ย ย NLPย
๐ Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
Seokin Seo, HyeongJoo Hwang, Hongseok Yang, Kee-Eung Kim
Neural Information Processing Systems (NeurIPS) 2023 (Spotlight)
Keywords: ย Imitation learning ย ย ย Causal learningย
๐ Information-Theoretic State Space Model for Multi-View Reinforcement Learning
HyeongJoo Hwang, Seokin Seo, Youngsoo Jang, Sungyoon Kim, Geon-Hyeong Kim, Seunghoon Hong, Kee-Eung Kim
International Conference of Machine Learning (ICML) 2023 (Oral presentation)ย
Keywords: ย Reinforcement learning ย ย ย Multi-view learningย
๐ DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations
Geon-Hyeong Kim, Seokin Seo, Jongmin Lee, Wonseok Jeon, HyeongJoo Hwang, Hongseok Yang, Kee-Eung Kim
International Conference on Learning Representations (ICLR) 2022
Keywords: ย Imitation learningย
๐ Monte-Carlo Planning and Learning with Language Action Value Estimates
Youngsoo Jang, Seokin Seo, Jongmin Lee, Kee-Eung Kim
International Conference on Learning Representations (ICLR) 2021
Keywords: ย Reinforcement learning ย ย ย NLPย
๐ A Bayesian Approach to Generative Adversarial Imitation Learning
Wonseok Jeon, Seokin Seo, Kee-Eung Kim
Neural Information Processing Systems (NeurIPS) 2018 (Spotlight)
Keywords: ย Imitation learningย
Domestic
๐ ํน์ง์กฐํฉ ๊ต๋์ ๊ท ํ์ ํตํ ์ธ๊ณผ์ ๊ทํ๋ ๋ก์ง์คํฑ ํ๊ท ๊ฐ์
ย ย ย ย ย (Improving Causally-Regularized Logistic Regression via Confounder Balancing with Feature Combinations)
์์์ธ, ํฉํ์ฃผ, ์ํ์, ๊น๊ธฐ์
ํ๊ตญ์ํํธ์จ์ด์ข ํฉํ์ ๋ํ (KSC) 2022 (์ฐ์๋ฐํ๋ ผ๋ฌธ์ ์์)
Keywords: ย Causal learningย
๐ ๊ด๊ณ์ ๋ฉ๋ชจ๋ฆฌ ์ฝ์ด ๊ตฌ์กฐ๋ฅผ ์ ์ฉํ ๋ณ๋ถ์ ์ํ์ ๊ฒฝ๋ง
ย ย ย ย (Variational Recurrent Neural Networks with Relational Memory Core Architectures)
๊น๊ฑดํ, ์์์ธ, ๊น์ ํ, ๊น๊ธฐ์
ํ๊ตญ์ ๋ณด๊ณผํํ (KCC) ํ์ ๋ฐํ๋ ผ๋ฌธ์ง 2019
Keywords: ย Variational Inferenceย
Academic Experiences
Reviewer
NeurIPS (2021, 2024), ICLR (2025), ICML (2025)
Teaching Assistance
KAIST Machine Learning Engineer Bootcamp: Introduction to Reinforcement Learning (2022)
KAIST-Samsung DS AI Expert Program : Dialogue System (2020)
Mathematics for AI (AI503) @KAIST (2021 Fall)
Machine Learning (CS376) @KAIST (2019 Fall)
Data Structure (CS206) @KAIST (2018 Spring, 2018 Fall)