Publications
2026
-
Efficient Post-Training for Robot Foundation Models in Real-World Deployment
Ph.D. Dissertation
-
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
CoRL 2026 Continually Self-Improving Robots Workshop
CoRL 2026 Roadmap to Sample-Efficient Real-World Reinforcement Learning Workshop
Best Paper Award Oral Presentation
-
RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection
NeurIPS 2026 Robot Learning Workshop
CoRL 2026 Robot Learning at Deployment Workshop
-
Q-Learning with Scalar Adjoint Matching
ArXiv preprint, 2026
-
Trust Region Q Adjoint Matching
Conference on Neural Information Processing Systems (NeurIPS), 2026
-
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
International Conference on Machine Learning (ICML), 2026
Oral Presentation (168 / 23918 = 0.7%)
-
Contrastive Representation Regularization for Vision-Language-Action Models
International Conference on Machine Learning (ICML), 2026
-
Learning Multi-View Spatial Reasoning from Cross-View Relations
Conference on Computer Vision and Pattern Recognition (CVPR), 2026
(*: equal contribution)
-
DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
International Conference on Learning Representations (ICLR), 2026
(^: equal advising)
-
Verifier-free Test-Time Sampling for Vision Language Action Models
International Conference on Learning Representations (ICLR), 2026
-
HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy
International Conference on Learning Representations (ICLR), 2026
2025
-
B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations
Conference on Lifelong Learning Agents (CoLLAs), 2025
ICLR 2024 Generative Models for Decision Making Workshop
Spotlight Presentation
-
Subtask-Aware Visual Reward Learning from Segmented Demonstrations
International Conference on Learning Representations (ICLR), 2025
(^: equal advising)
2023
-
Guide Your Agent with Adaptive Multimodal Rewards
Conference on Neural Information Processing Systems (NeurIPS), 2023
Finalist of Qualcomm Innovation Fellowship 2024 Korea
ICML 2023 New Frontiers in Learning, Control, and Dynamical Systems Workshop
-
Preference Transformer: Modeling Human Preferences using Transformers for RL
International Conference on Learning Representations (ICLR), 2023
(*: equal contribution)
2022
-
Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization
NeurIPS 2022 Offline Reinforcement Learning Workshop
(*: equal contribution)
Other publications
-
Moi-mixer: Improving mlp-mixer with multi order interactions in sequential recommendation
ArXiv preprint, 2021
-
Collecting the public perception of AI and robot rights
Proceedings of the ACM on Human-Computer Interaction, 4(CSCW2), pp. 1โ24, 2020
BibTeX: Publications ยท Other publications