Byoungjip Kim, PhD (김병집)
Byoungjip Kim, PhD (김병집)
Embedded Files
AI Researcher
Post-Training and Reinforcement Learning for LLM Agents
byoungjip.kim at gmail.com
"Try not to become a man of success, but rather try to become a man of value." -- Albert Einstein
Recent Research Areas
Large Language Models (LLMs)
LLM Agents
LLM Post-Training
Agentic Reinforcement Learning
Vision Language Models (VLMs)
Education
2004.03 ~ 2013.02: Ph.D. in Computer Science at KAIST (Advisor: Prof. Junehwa Song)
2002.03 ~ 2004.02: M.S. in Electrical and Electronic Engineering at KAIST (Advisor: Prof. Daeyeon Park)
1998.03 ~ 2002.02: B.S. in Electrical and Electronic Engineering at KAIST (Korea Advanced Institute of Science and Technology)
1996.03 ~ 1998.02: Hansung Science High School
Experiences
2026.01 ~ Present: Researcher and Professor in LG Graduate School of AI at LG AI Research
2025.01 ~ 2025.12: VP and Head of Financial AI Center at KB Kookmin Bank
2021.08 ~ 2024.12: Research Scientist (& Code LLM Squad Leader) in Advanced ML Lab at LG AI Research
2018.12 ~ 2021.07: Principal Engineer in AI Research Center at Samsung SDS
2018.05 ~ 2018.11: Chief AI Officer at Speclipse Inc.
2017.03 ~ 2018.05: Research Scientist in T-Brain at SK Telecom
2015.09 ~ 2017.02: Assistant Professor in Department of Information and Communication Engineering at Sangmyung University
2013.05 ~ 2015.08: Senior Software Engineer in Health Service Lab at Samsung Electronics
2005.06 ~ 2006.06: Research Intern at IBM T.J. Watson Research Center
Recent Publications
2026
⭐⭐⭐ [LLM/RL] SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety [pdf]
Geon-Hyeong Kim, Yu Jin Kim, Byoungjip Kim, Honglak Lee, Kyunghoon Bae, Youngsoo Jang, Moontae Lee
ICLR 2026 (Oral) 🎉
2025
[LLM/Code] Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code [pdf]
Geonmo Gu, Jaeho Kwak, Haksoo Moon, Hyun Seung Shim, Yu Jin Kim, Byoungjip Kim, Moontae Lee, Hyejeong Jeon
ACL 2025 (Industry Track)
2024
⭐⭐⭐ [LLM/Agent] Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking [pdf] [blog (en)] [blog (kr)]
Byoungjip Kim, Youngsoo Jang, Lajanugen Logeswaran, Geon-Hyeong Kim, Yu Jin Kim, Honglak Lee, Moontae Lee
EMNLP 2024 Findings
[LLM] ChatEXAONE: Enterprise AI Agent [pdf][blog (en)]
participated as a core contributor
LG AI Research
⭐⭐⭐ [LLM/Multimodal] Show, Think, and Tell: Thought-Augmented Fine-Tuning of Large Language Models for Video Captioning [pdf]
Byoungjip Kim, Dasol Hwang, Sungjun Cho, Youngsoo Jang, Honglak Lee, Moontae Lee
CVPR 2024 Workshop Multi-Modal Foundation Models (MMFM)
⭐⭐⭐ [LLM/RL] Degeneration-free Policy Optimization: RL Fine-Tuning of Language Models without Degeneration [pdf]
Youngsoo Jang, Geon-Hyeong Kim, Byoungjip Kim, Yu Jin Kim, Honglak Lee, Moontae Lee
ICML 2024
2023
[LLM/Code] On Sample-Efficient Code Generation [pdf]
Hojae Han, Yu Jin Kim, Byoungjip Kim, Youngwon Lee, Kyungjae Lee, Kyungmin Lee, Moontae Lee, Kyunghoon Bae, Seung-won Hwang
EMNLP 2023 (Industry Track)
[RL] SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations [pdf] [video]
Youngsoo Jang, Geon-Hyeong Kim, Jongmin Lee, Sungryull Sohn, Byoungjip Kim, Honglak Lee, Moontae Lee
NeurIPS 2023
2022
⭐⭐⭐ [LLM/Multimodal] BeamCLIP: Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching [pdf] [video] [blog (en)] [blog (kr)]
Byoungjip Kim, Sungik Choi, Dasol Hwang, Moontae Lee, Honglak Lee
NeurIPS 2022
[CV] ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision [pdf]
Seongho Joe, Byoungjip Kim, Hoyoung Kang, Kyoungwon Park, Bogun Kim, Jaeseon Park, Joonseok Lee, Youngjune Gwon
IEEE ICPR 2022
2021
[CV] VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning [pdf]
Jongwon Choi, Kwang Moo Yi, Jihoon Kim, Jincho Choo, Byoungjip Kim, Jin-Yeop Chang, Youngjune Gwon, Hyung Jin Chang
CVPR 2021
2020
⭐⭐⭐ [CV] SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning [pdf]
Byoungjip Kim, Jinho Choo, Yeong-Dae Kwon, Seongho Joe, Seungjai Min, Youngjune Gwon
NeurIPS 2020 Workshop Self-Supervised Learning
⭐⭐⭐ [RL] POMO: Policy Optimization with Multiple Optima for Reinforcement Learning [pdf] [code]
Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Seungjai Min, Youngjune Gwon
NeurIPS 2020
⭐⭐⭐ [GAN] DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets [pdf] [code]
Yonghyun Jeong, Hyunjin Choi, Byoungjip Kim, Youngjune Gwon
AAAI 2020 (Oral) 🏆
[GAN] Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks [pdf]
Taeksoo Kim, Byoungjip Kim, Moonsu Cha, Jiwon Kim
arXiv 1707.09798
Other Publications
Awards
2023 LG AI Research Best Challenge Award
Research and Development of EXACODE, an EXAONE-based Code LLM
2020 Samsung Best Paper Award Bronze
DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
Yonghyun Jeong, Hyunjin Choi, Byoungjip Kim, Youngjune Gwon
AAAI 2020 (Oral)
IEEE MDM 2006 Best Paper Award
BMQ-Index: Shared and Incremental Processing of Border Monitoring Queries over Data Streams
Jinwon Lee, Youngki Lee, Seungwoo Kang, SangJeong Lee, Hyunju Jin, Byoungjip Kim, Junehwa Song
Acedemic Services
Machine Learning / Artificial Intelligence
NeurIPS Area Chair
ICLR Reviewer
ICML Reviewer
AAAI Reviewer
AISTATS Reviewer
Natural Language Processing
ACL Reviewer
EMNLP Reviewer
Computer Vision
CVPR Reviewer
ECCV Reviewer
WACV Reviewer
Page updated
Google Sites
Report abuse