Contact:
kiminlee at kaist dot ac dot kr
Kimin Lee
I am an assistant professor at the Graduate School of AI at KAIST. My current research goal is to develop safe and capable AI agents. Recently, I've focused on the following topics:
Reinforcement learning from human feedback
Decision-making agents
AI Alignment / Safety
World models
Before joining KAIST, I was a research scientist at Google Research. I completed my postdoctoral training at UC Berkeley (working with Pieter Abbeel) and PhD at KAIST (advised by Jinwoo Shin). During PhD, I also interned and collaborated closely with Honglak Lee at University of Michigan.
Publications (C: conference / J: journal / P: preprint / *: equal contribution / ^: equal advising)
2024
[C48] Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models [pdf][site][code]
Sangwon Jang*, Jaehyeong Jo*, Kimin Lee^, Sung Ju Hwang^
Conference on Neural Information Processing Systems (NeurIPS) 2024
[C47] By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting [pdf]
Hyungjun Yoon, Biniyam Aschalew Tolera, Taesik Gong, Kimin Lee, Sung-Ju Lee
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024 (main)
[C46] Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [pdf]
Kyuyoung Kim*, Ah Jeong Seo*, Hao Liu, Jinwoo Shin, Kimin Lee
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024 (findings)
[C45] Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation [pdf]
Katherine Collins, Najoung Kim, Yonatan Bitton, Verena Rieser, Shayegan Omidshafiei, Yushi Hu, Sherol Chen, Senjuti Dutta, Minsuk Chang, Kimin Lee, Youwei Liang, Georgie Evans, Sahil Singla, Gang Li, Adrian Weller, Junfeng He, Deepak Ramachandran, Krishnamurthy Dvijotham
[C44] Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences [pdf][site]
Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Aniruddha Kembhavi, Kiana Ehsani
Conference on Computer Vision and Pattern Recognition (CVPR) 2024
[C43] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models [pdf][code]
Kyuyoung Kim, Jongheon Jeong, Minyong An, Mohammad Ghavamzadeh, Krishnamurthy Dj Dvijotham, Jinwoo Shin, Kimin Lee
International Conference on Learning Representations (ICLR) 2024
[P16] Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models [pdf]
Yongjin Yang*, Sihyeon Kim*, Hojung Jung, Sangmin Bae, SangMook Kim, Se-Young Yun^, Kimin Lee^
Arxiv preprint 2024
[P15] MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control [pdf][code][site]
Juyong Lee*, Dongyoon Hahm*, June Suk Choi*, W. Bradley Knox, Kimin Lee
Arxiv preprint 2024
[P14] Latent Action Pretraining from Videos [pdf]
Seonghyeon Ye*, Joel Jang*, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee^, Jianfeng Gao^, Luke Zettlemoyer^, Dieter Fox^, Minjoon Seo^
Arxiv preprint 2024
[P13] When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs [pdf]
Hanna Kim, Minkyoo Song, Seung Ho Na, Seungwon Shin, Kimin Lee
Arxiv preprint 2024
[P12] Aligning Large Language Models with Self-generated Preference Data [pdf]
Dongyoung Kim, Kimin Lee, Jinwoo Shin, Jaehyung Kim
Arxiv preprint 2024
[P11] ADAPT^2: Adapting Pre-Trained Sensing Models to End-Users via Self-Supervision Replay [pdf]
Hyungjun Yoon, Jaehyun Kwak, Biniyam Aschalew Tolera, Gaole Dai, Mo Li, Taesik Gong, Kimin Lee, Sung-Ju Lee
Arxiv preprint 2024
[P10] DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing [pdf]
June Suk Choi, Kyungmin Lee, Jongheon Jeong, Saining Xie, Jinwoo Shin, Kimin Lee
ICML Workshop on the Next Generation of AI Safety 2024
[P9] Benchmarking Mobile Device Control Agents across Diverse Configurations [pdf][site][code]
Juyong Lee, Taywon Min, Minyong An, Changyeon Kim, Kimin Lee
ICLR Workshop on Generative Models for Decision Making 2024 as Spotlight presentation
[P8] InstructBooth: Instruction-following Personalized Text-to-Image Generation [pdf]
Daewon Chae, Nokyung Park, Jinkyu Kim, Kimin Lee
ICML Workshop on Foundation Models in the Wild 2024
2023
[C42] DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models [pdf][site][code]
Ying Fan*, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, Kimin Lee*
Conference on Neural Information Processing Systems (NeurIPS) 2023
[C41] Guide Your Agent with Adaptive Multimodal Rewards [pdf][site][code]
Changyeon Kim, Younggyo Seo, Hao Liu, Lisa Lee, Jinwoo Shin, Honglak Lee, Kimin Lee
Conference on Neural Information Processing Systems (NeurIPS) 2023
[C40] StyleDrop: Text-to-Image Generation in Any Style [pdf][site]
Kihyuk Sohn, Nataniel Ruiz, Kimin Lee, Daniel Castro Chin, Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, Yuan Hao, Irfan Essa, Michael Rubinstein, Dilip Krishnan
Conference on Neural Information Processing Systems (NeurIPS) 2023
[C39] Multi-View Masked World Models for Visual Robotic Manipulation [pdf][code]
Younggyo Seo*, Junsu Kim*, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel
[C38] Controllability-Aware Unsupervised Skill Discovery [pdf][code]
Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel
[C37] Preference Transformer: Modeling Human Preferences using Transformers for RL [pdf][code]
Changyeon Kim, Jongjin Park, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee
[P7] Algorithms for Optimal Adaptation of Diffusion Models to Reward Functions [pdf]
Krishnamurthy Dj Dvijotham, Shayegan Omidshafiei, Katherine M. Collins, Deepak Ramachandran, Kimin Lee, Ying Fan, Jeremiah Zhe Liu, Milad Nasr, Mohammad Ghavamzadeh
ICML workshop on New Frontiers in Learning, Control, and Dynamical Systems 2023
[P6] Aligning Text-to-Image Models using Human Feedback [pdf]
Kimin Lee, Hao Liu, Moonkyung Ryu, Olivia Watkins, Yuqing Du, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Shixiang Shane Gu
Arxiv preprint 2023
2022
[C36] Masked World Models for Visual Control [pdf][code]
Younggyo Seo, Danijar Hafner, Hao Liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel
[C35] Reinforcement Learning with Action-Free Pre-Training from Videos [pdf][code]
Younggyo Seo, Kimin Lee, Stephen James, Pieter Abbeel
[C34] SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning [pdf]
Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee
International Conference on Learning Representations (ICLR) 2022
NeurIPS Workshop on Deep RL 2021
[C33] Reward Uncertainty for Exploration in Preference-based Reinforcement Learning [pdf]
Xinran Liang, Katherine Shu, Kimin Lee^, Pieter Abbeel^
International Conference on Learning Representations (ICLR) 2022
NeurIPS Workshop on Deep RL 2021
[C32] Towards More Generalizable One-shot Visual Imitation Learning [pdf][code]
Zhao Mandi*, Fangchen Liu*, Kimin Lee, Pieter Abbeel
International Conference on Robotics and Automation (ICRA) 2022
[C31] Programmatic Modeling and Generation of Real-time Strategic Soccer Environments for Reinforcement Learning [pdf]
Abdus Salam Azad*, Edward Kim*, Qiancheng Wu, Kimin Lee, Ion Stoica, Pieter Abbeel, Sanjit A. Seshia
[C30] HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator [pdf]
Younggyo Seo, Kimin Lee, Fangchen Liu, Stephen James, Pieter Abbeel
[P5] Instruction-Following Agents with Jointly Pre-Trained Vision-Language Models [pdf][code]
Hao Liu, Lisa Lee, Kimin Lee, Pieter Abbeel
Arxiv preprint 2022
[P4] Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization [pdf]
Changyeon Kim, Junsu Kim, Younggyo Seo, Kimin Lee, Honglak Lee, Jinwoo Shin
NeurIPS Workshop on Offline RL 2022
2021
[C29] B-Pref: Benchmarking Preference-Based Reinforcement Learning [pdf][code]
Kimin Lee, Laura Smith, Anca Dragan, Pieter Abbeel
Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track 2021 (round 1)
[C28] URLB: Unsupervised Reinforcement Learning Benchmark [pdf][code]
Michael Laskin*, Denis Yarats*, Hao Liu, Kimin Lee, Albert Zhan, Kevin Lu, Catherine Cang, Lerrel Pinto, Pieter Abbeel
Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track 2021 (round 2)
NeurIPS Workshop on Deep RL 2021
[C27] Decision Transformer: Reinforcement Learning via Sequence Modeling [pdf][code]
Lili Chen*, Kevin Lu*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas^, Igor Mordatch^
Conference on Neural Information Processing Systems (NeurIPS) 2021
ICML workshop on URL and RL4RL 2021
[C26] Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [pdf][code]
Lili Chen, Kimin Lee, Aravind Srinivas, Pieter Abbeel
Conference on Neural Information Processing Systems (NeurIPS) 2021
Previous version [pdf] [video] in NeurIPS Workshop on Deep RL 2020
[C25] Improving Transferability of Representations via Augmentation-Aware Self-Supervision [pdf][code]
Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS) 2021
ICML Workshop on Self-Supervised Learning for Reasoning and Perception 2021
[C24] Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback [pdf][code]
Xiaofei Wang, Kimin Lee, Kourosh Hakhamaneshi, Pieter Abbeel, Michael Laskin
NeurIPS Workshop on Deep RL 2021
[C23] Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble [pdf][code]
Seunghyun Lee*, Younggyo Seo*, Kimin Lee, Pieter Abbeel, Jinwoo Shin
Previous version [pdf] in NeurIPS Workshop on Offline RL 2020 as Oral presentation & NeurIPS Workshop on Deep RL 2020
[C22] PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training [pdf][code][site]
Kimin Lee*, Laura Smith*, Pieter Abbeel
International Conference on Machine Learning (ICML) 2021 as Long oral presentation (166/5513=3.0%)
[C21] State Entropy Maximization with Random Encoders for Efficient Exploration [pdf][code][site]
Younggyo Seo*, Lili Chen*, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee
ICLR Workshop on Self-Supervision for RL 2021
[C20] SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning [pdf][code]
Kimin Lee, Michael Laskin, Aravind Srinivas, Pieter Abbeel
Previous version [pdf] in NeurIPS Workshop on Deep RL 2020
[C19] Decoupling Representation Learning from Reinforcement Learning [pdf][code]
Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin
NeurIPS Workshop on Deep RL 2020
[C18] Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environments [pdf][podcast]
Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L Lewis, Satinder Singh
International Joint Conference on Artificial Intelligence (IJCAI) 2021
Previous version 1 [pdf] in NeurIPS Workshop on Deep RL 2020
Previous version 2 [pdf] in ICML Workshop on OOL 2020
[C17] Learning to Sample with Local and Global Contexts in Experience Replay Buffer [pdf][code]
Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
International Conference on Learning Representations (ICLR) 2021
NeurIPS Workshop on Deep RL 2020
[C16] MASKER: Masked Keyword Regularization for Reliable Text Classification [pdf][code]
Seung Jun Moon*, Sangwoo Mo*, Kimin Lee, Jaeho Lee, Jinwoo Shin
2020
[C15] Reinforcement Learning with Augmented Data [pdf][code][blog] [media]
Michael Laskin*, Kimin Lee*, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas
Conference on Neural Information Processing Systems (NeurIPS) 2020 as Spotlight presentation (280/9454=2.9%)
[C14] Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [pdf][code][site]
Younggyo Seo*, Kimin Lee*, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel
Conference on Neural Information Processing Systems (NeurIPS) 2020
[C13] Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning [pdf][code][site]
Kimin Lee*, Younggyo Seo*, Seunghyun Lee, Honglak Lee, Jinwoo Shin
[C12] Regularizing Class-wise Predictions via Self-knowledge Distillation [pdf] [code]
Sukmin Yun*, Jongjin Park*, Kimin Lee, Jinwoo Shin
Conference on Computer Vision and Pattern Recognition (CVPR) 2020
[C11] Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning [pdf] [code]
Kimin Lee*, Kibok Lee*, Jinwoo Shin, Honglak Lee
International Conference on Learning Representations (ICLR) 2020
Previous version [pdf] in NeurIPS Workshop on Deep RL 2019 as Oral presentation
[P3] R-LAtte: Visual Control via Deep Reinforcement Learning with Attention Network [pdf]
Mandi Zhao, Qiyang Li, Aravind Srinivas, Ignasi Clavera, Kimin Lee, Pieter Abbeel
NeurIPS Workshop on Deep RL 2020
[P2] Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning [pdf]
Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin
Arxiv preprint 2020
2019
[C10] Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild [pdf][code]
Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee
CVPR Workshop on Uncertainty and Robustness in Deep Visual Learning 2019
[C9] Robust Inference via Generative Classifiers for Handling Noisy Labels [pdf][code]
Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin
International Conference on Machine Learning (ICML) 2019 as Long oral presentation (159/3424=4.64%)
Previous version [pdf] in NeurIPS Workshop on Bayesian Deep Learning 2018
[C8] Using Pre-Training Can Improve Model Robustness and Uncertainty [pdf] [code]
Dan Hendrycks, Kimin Lee, Mantas Mazeika
ICLR Workshop on Safe Machine Learning 2019
[J1] Dynamic Control for On-demand Interference-managed WLAN Infrastructures [pdf]
Seokhyun Kim, Kimin Lee, Yeonkeun Kim, Jinwoo Shin, Seungwon Shin, Song Chong
IEEE/ACM Transactions on Networking (TON) 2019
2018
[C7] A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks [pdf] [code]
Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS) 2018 as Spotlight presentation (168/4856=3.5%)
ICML Workshop on TADGM 2018
[C6] Learning to Specialize with Knowledge Distillation for Visual Question Answering [pdf] [code]
Jonghwan Mun, Kimin Lee, Jinwoo Shin, Bohyung Han
Conference on Neural Information Processing Systems (NeurIPS) 2018
[C5] Hierarchical Novelty Detection for Visual Object Recognition [pdf] [code]
Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee
Conference on Computer Vision and Pattern Recognition (CVPR) 2018
[C4] Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples [pdf] [code]
Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin
International Conference on Learning Representations (ICLR) 2018
NeurIPS Workshop on Bayesian Deep Learning 2017
2017
[C3] Confident Multiple Choice Learning [pdf] [code]
Kimin Lee, Changho Hwang, Kyoungsoo Park, Jinwoo Shin
[P1] Simplified Stochastic Feedforward Neural Networks [pdf]
Kimin Lee, Jaehyung Kim, Song Chong, Jinwoo Shin
Arxiv preprint 2017
2016
[C2] TravelMiner: On the Benefit of Path-based Mobility Prediction
Jaeseong Jeong, Kyunghan Lee, Beknazar Adbikamaov, Kimin Lee, Song Chong
International Conference on Sensing, Communication and Networking (SECON) 2016
[C1] Just-in-time WLANs: On-demand Interference-managed WLAN Infrastructures [pdf] [slides]
Kimin Lee, Yeonkeun Kim, Seokhyun Kim, Jinwoo Shin, Seungwon Shin, Song Chong
International Conference on Computer Communications (INFOCOM) 2016
Education
2015.02-2020.02: Doctor of Philosophy (Ph.D.), School of Electrical Engineering (Machine/deep learning), KAIST (adviser: Jinwoo Shin)
2013.02-2015.02: Master of Science (MS), School of Electrical Engineering (Wireless communication networks), KAIST (adviser: Song Chong and Jinwoo Shin)
2009.02-2013.02: Bachelor of Engineering (BS), School of Electrical Engineering, KAIST
Academic Activities
Area chair
NeurIPS, NeurIPS Datasets and Benchmarks, ICLR
Conference reviewer
NeurIPS, ICML, ICLR, AAAI, ICRA, RSS, CoRL, UAI, IJCAI, CoLLAs, ACML
Journal reviewer
Journal of Machine Learning Research, IEEE Transactions on Pattern Analysis and Machine Intelligence, Transactions on Machine Learning Research, IEEE Robotics and Automation Letters, IEEE/ACM Transactions on Networking
Workshop organizer
Towards Safe & Trustworthy Agents Workshop, NeurIPS 2024
Deep Reinforcement Learning Workshop, NeurIPS 2020
Admissions Committee
UC Berkeley EECS, 2020
Tutorial organizer
SCENIC: An Open-Source Probabilistic Programming System for Data Generation and Safety in AI-Based Autonomy, CVPR 2024
Work Experience
2023.08 - present: Assistant professor at KAIST
2022.02 - 2023.07: Research scientist at Google Research
2020.02 - 2022.01: Postdoctoral fellow at UC Berkeley (working with Pieter Abbeel)
2019.04 - 2019.09: Visiting student at University of Michigan (working with Honglak Lee)
2018.06 - 2018.10: Visiting student at UC Berkeley (working with Dawn Song and Bo Li)