About Me
I am a Ph.D. student at KAIST, Kim Jaechul Graduate School of AI, and a member of the CVML Lab. My research interests are Generative Modeling and Vision-Language Action Models / World Action Models.
I am driven by a desire to leverage artificial intelligence to solve complex real-world challenges and push the boundaries of multimodal understanding. I believe in developing robust, scalable AI systems that seamlessly connect perception with action.
Beyond academics, I enjoy playing the piano.
Research Interest
- Generative Modeling
- Vision-Language Action Models / World Action Models
Education
Ph.D. in Artificial Intelligence
KAIST, Kim Jaechul Graduate School of AI
September 2026 – Present
M.S. in Artificial Intelligence
KAIST, Kim Jaechul Graduate School of AI
September 2024 – August 2026
B.S. in Mathematics and Computer Science
Sogang University
March 2018 – August 2022
Experience
KAIRI Intern
KAIST, Kim Jaechul Graduate School of AI
June 2023 – August 2023
- Advisor : Jongchul Ye
KAIRI Intern
KAIST, Kim Jaechul Graduate School of AI
December 2022 – February 2023
- Advisor : Jaegul Choo
Recent Publications
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
Hojun Choi, Jaeyo Shin, Suin Lee, Hyunjung Shim.
arXiv preprint, 2026.
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Seojeong Park*, Jiho Choi*, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim.
International Conference on Machine Learning (ICML), 2026.
Representation Alignment for Just Image Transformers is not Easier than You Think
Jaeyo Shin*, Jiwook Kim*, Hyunjung Shim.
European Conference on Computer Vision (ECCV), 2026.
Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
Inha Kang, Eunki Kim, Wonjeong Ryu, Jaeyo Shin, Seungjun Yu, Yoon-Hee Kang, Seongeun Jeong, Eunhye Kim, Soontae Kim, Hyunjung Shim.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving
Seungjun Yu, Seonho Lee, Namho Kim, Jaeyo Shin, Junsung Park, Wonjeong Ryu, Raehyuk Jung, Hyunjung Shim.
Findings of the Association for Computational Linguistics (EMNLP), 2026.
MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
Hojun Choi, Youngsun Lim, Jaeyo Shin, Hyunjung Shim.
European Conference on Computer Vision (ECCV), 2026.
DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation
Jiwook Kim*, Seonho Lee*, Jaeyo Shin, Jiho Choi, Hyunjung Shim.
International Conference on Learning Representations (ICLR), 2025.
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Junha Hyung*, Jaeyo Shin*, Jaegul Choo.
AAAI Conference on Artificial Intelligence (AAAI), 2024.