Hi, I’m Miso Lee, a Ph.D. student in Visual Computing Lab and a research intern at NAVER Cloud. My research interests span computer vision and deep learning, with a primary focus on camera pose estimation, 3D vision, and geometric deep learning.

👤 83653, Sungkyunkwan University, Republic of Korea

✉️ [email protected]

🌐 [Google Scholar] [LinkedIn]

🎓 EDUCATION

Sungkyunkwan University

Ph.D. of Artificial Intelligence**,** 2023.03-present (Advisor: Jae-Pil Heo)

B.S. of Computer Science and Engineering, 2020.03-2023.02

B.S. of Mechanical Engineering, 2019.03-2023.02

Sangsan High School

36th graduate, 2016.03-2019.02

📚 PUBLICATIONS

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Yerim Jeon, Miso Lee, WonJun Moon, and Jae-Pil Heo

IEEE/CVF Conference Computer Vision and Pattern Recognition (CVPR), 2026

[Arxiv] [Code]

• Keywords: Multimodal LLM, 3D Scene-Language Understanding

Temporally Consistent Long-Term Memory for 3D Single Object Tracking

Jaejoon Yoo, SuBeen Lee, Yerim Jeon, Miso Lee, and Jae-Pil Heo

IEEE/CVF Conference Computer Vision and Pattern Recognition (CVPR) Findings, 2026