Seokin Seo

Publications

International

📑 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:  Reinforcement learning    NLP 

📑 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:  Imitation learning    Robust learning 

📑 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:  Reinforcement learning    NLP 

📑 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:  Imitation learning    Causal learning 

📑 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) 

• Keywords:  Reinforcement learning    Multi-view learning 

📑 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:  Imitation learning 

📑 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:  Reinforcement learning    NLP 

📑 A Bayesian Approach to Generative Adversarial Imitation Learning

• Wonseok Jeon, Seokin Seo, Kee-Eung Kim

• Neural Information Processing Systems (NeurIPS) 2018 (Spotlight)

• Keywords:  Imitation learning 

Domestic

📑 특징조합 교란자 균형을 통한 인과정규화된 로지스틱 회귀 개선
          (Improving Causally-Regularized Logistic Regression via Confounder Balancing with Feature Combinations)

• • 서석인, 황형주, 양홍석, 김기응

  • 한국소프트웨어종합학술대회 (KSC) 2022 (우수발표논문상 수상)

  • Keywords:  Causal learning 

📑 관계적 메모리 코어 구조를 적용한 변분적 순환신경망
        (Variational Recurrent Neural Networks with Relational Memory Core Architectures)

• • 김건형, 서석인, 김신형, 김기응

  • 한국정보과학회 (KCC) 학술발표논문지 2019

  • Keywords:  Variational Inference 

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)