Suchae Jeong
I am a Master’s student at KAIST, advised by Kimin Lee, and a Member of Technical Staff at Config Intelligence.
My research centers on building robot foundation models that generalize across embodiments, environments, and tasks at scale. I am particularly interested in:
Scalable learning paradigms for robotics
Action representation for behavior cloning
Bridging control theory and Vision-Language-Action models
Alongside research, I work on practical system development for real-world deployment, including:
Control systems across diverse robot platforms (e.g., FR3, Vega Pro, RBY1)
Efficient inference pipelines for Vision-Language-Action models
My long-term goal is to advance robot foundation models toward robust, scalable, and physically grounded intelligence.
Publications
(C: conference / J: journal / D: domestic / P: preprint / *: equal contribution / ^: equal advising)
2026
[C3] Learning Multi-View Spatial Reasoning from Cross-View Relations [pdf]
Suchae Jeong*, Jaehwi Song*, Haeone Lee, Hanna Kim, Jian Kim, Dongjun Lee, Dong Kyu Shin, Changyeon Kim, Dongyoon Hahm, Woogyeol Jin, Juheon Choi, Kimin Lee
Conference on Computer Vision and Pattern Recognition (CVPR). 2026
2025
[C2] Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement [pdf]
Suchae Jeong*, Inseong Choi*, Youngsik Yun, Jihie Kim
Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL). 2025
2024
[D1] Easy-Read Conversion using LLM: Investigating Sentence Transformation Ability in Terms of Readability and Semantic Similarity [pdf]
Suchae Jeong, Jaehyeong Hwang, Hyesu Kim, Minji Lee, Yeji Lee, Jaehun Lee
Annual Conference of Korea Information Processing Society (ACK). 2024
[C1] Improving LLM Classification of Logical Errors by Integrating Error Relationship into Prompts [pdf]
Yanggyu Lee, Suchae Jeong, Jihie Kim
International Conference on Intelligent Tutoring Systems (ITS). 2024 as Best Paper Award
Experience
RISE Lab at KAIST [May. 2025 ~ Present]
Master’s Student (Former Research Intern)
Research Focus
Robot intelligence and embodied foundation models
Multi-view spatial reasoning [C3]
Human–robot collaboration
Advisor: Kimin Lee
Config Intelligence [Feb. 2025 ~ Present]
Member of Technical Staff (Former Data Intern)
Research & Engineering Contributions
Redesigned teleoperation control loops to improve cross-platform stability
Led action chunking and asynchronous inference experiments for real-world VLA deployment
Defined IK/ID evaluation metrics to diagnose control instability and latency
Built and deployed inference scheduling and model-serving systems across multiple robots
Supervisor: Sungdong Kim
Collaborators: Kimin Lee, Minjoon Seo, and Hyungmok Son
Machine Learning Lab at DGU [Aug. 2023 ~ May. 2025]
Student Researcher
Research Area:
Fairness in AI
Cultural Alignment of Generative Models [C2]
Large Language Model Application [C1] [D1]
Advisor: Jihie Kim
Education
M.S. [Mar. 2026 ~ Present]
Graduate School of AI, Korea Advanced Institute of Science and Technology, Seoul, South Korea
GPA: -
Advisor: Kimin Lee
B.S. [Mar. 2020 ~ Feb. 2026]
Department of Computer Science and Engineering, Dongguk University, Seoul, South Korea
GPA: 4.38/4.5 (2nd place out of 41)
Advisor: Kangwoo Lee