Hello ๐ I am a Ph.D. student at Korea University, advised by Prof. Sangpil Kim. My research explores how embodied agents can reason, learn, and act in the physical world. In particular, I am interested in developing self-supervising and self-improving embodied agents through reasoning, with a focus on reasoning verification, latent reasoning, and continual learning and adaptation.
I'm always happy to chat about embodied AI, embodied reasoning, and related research. Feel free to reach out by email or schedule a coffee chat โ
Warning
Problem: The current name of your GitHub Pages repository ("") does not match the recommended repository name for your site ("").
Solution: Please consider renaming the repository to "
", so that your site can be accessed directly at "http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "",
which does not match the baseurl ("") configured in _config.yml.
Solution: Please set the
baseurl in _config.yml to "".
Education
-
Korea UniversityDeptartment of AI
Ph.D. StudentMar. 2022 - Feb. 2027 (Expected) -
Dongguk UniversityB.A. in Business ManagementMar. 2015 - Feb. 2019
Experience
-
University of Michigan, Ann ArborVisiting Researcher (Advisor - Prof. Honglak Lee)May. 2025 - May. 2026 -
Samsung Advanced Institute of Technology (SAIT)Visiting Researcher (Advisor - Prof. Sujin Jang)Mar. 2024 - Feb. 2025
News
Selected Publications (view all )

Path-level Hinsight Instructions for Semantic Exploration in Vision-Language Navigation
Sung June Kim, Sangpil Kim$^โ $, Honglak Lee$^โ $
European Conference on Computer Vision (ECCV) 2026
Path-level Hinsight Instructions for Semantic Exploration in Vision-Language Navigation
Sung June Kim, Sangpil Kim$^โ $, Honglak Lee$^โ $
European Conference on Computer Vision (ECCV) 2026

Test-time adaptation for Online Vision-Language Navigation with Feedback based Reinforcement Learning
Sung June Kim*, Gyeongrok Oh*, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung-Jun Lee, Sujin Jang, Sangpil Kim$^โ $ (* equal contribution)
International Conference on Machine Learning (ICML) 2025
Test-time adaptation for Online Vision-Language Navigation with Feedback based Reinforcement Learning
Sung June Kim*, Gyeongrok Oh*, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung-Jun Lee, Sujin Jang, Sangpil Kim$^โ $ (* equal contribution)
International Conference on Machine Learning (ICML) 2025

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
Gyeongrok Oh*, Sung June Kim*, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang$^โ $, Sangpil Kim$^โ $ (* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
Gyeongrok Oh*, Sung June Kim*, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang$^โ $, Sangpil Kim$^โ $ (* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

Higher-order Relational Reasoning for Pedestrian Trajectory Prediction
Sung June Kim, Hyung-gun Chi, Hyerin Lim, Karthik Ramani, Jinkyu Kim, Sangpil Kim$^โ $
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Higher-order Relational Reasoning for Pedestrian Trajectory Prediction
Sung June Kim, Hyung-gun Chi, Hyerin Lim, Karthik Ramani, Jinkyu Kim, Sangpil Kim$^โ $
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR) 2024
