I am a Ph.D. candidate in Scalable Graphics, Vision, and Robotics (SGVR) Lab at KAIST advised by Prof. Sung-Eui Yoon. My research focuses on generative AI for Physical AI, particularly in 3D scene understanding and action planning under incomplete real-world observations. I am broadly interested in developing models for autonomous driving and robotics that can understand and reconstruct dynamic 3D environments, enabling more reliable reasoning and interaction in the physical world.

Contact

  • jmlee [at] kaist.ac.kr

  • 291 Daehak-ro, Yuseong-gu, Daejeon, Korea

Internship Experience

  • Research Intern, Robot Vision & Learning Team, NAVER Labs

    Nov. 2024 – May. 2025

Education

  • Ph.D in Computer Science, KAIST

    - Advisor: Sung-Eui Yoon

    Mar. 2024 - Current

  • M.S. in Artificial Intelligence, KAIST

    - Advisor: Sung-Eui Yoon

    Mar. 2022 - Feb. 2024

  • B.S. in Artificial Intelligence and Mechanical Engineering, SungKyunKwan University

    Sep. 2017 - Feb. 2022

News

  • [Jun 2026] Two papers are accepted to ECCV 2026.
  • [Mar 2026] One paper is accepted to CVPR 2026 as a highlight paper.
  • [May 2025] One paper is accepted to ICIP 2025 as a best student paper.
  • [Jun 2024] One paper is accepted to ECCV 2024.
  • [Jun 2024] I received a Ph.D fellowship from NRF(National Research Foundation) of Korea.
  • [Jun 2024] One paper is accepted to ICIP 2024.
  • [Mar 2024] One paper is accepted to CVPR 2024.
  • [Jun 2023] One paper is accepted to IPIU 2023 as an oral paper.

Publications

  • What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA

    Jinhwan Seo, Kyu Beom Han, Jumin Lee, Junhyug Noh and Sung-eui Yoon

    European Conference on Computer Vision (ECCV) 2026

  • MorphGS: Morphable Gaussian Splatting for 3D Scene Representation

    Taeyeon Kim*, Youngju Na*, Jumin Lee, Sebin Lee, Minhyuk Sung and Sung-Eui Yoon

    European Conference on Computer Vision (ECCV) 2026

  • VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection

    Jumin Lee, Siyeong Lee, Namil Kim and Sung-Eui Yoon

    [Paper] [Project]

  • Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering

    Sebin Lee*, Jumin Lee*, Taeyeon Kim, Woobin Im, Youngju Na and Sung-Eui Yoon

    Computer Vision and Pattern Recognition (CVPR) 2026

    Highlight paper

    [Paper] [Project]

  • Pose-free 3D Gaussian splatting via shape-ray estimation

    Youngju Na*, Taeyeon Kim*, Jumin Lee, Kyu Beom Han, Woo Jae Kim, and Sung-eui Yoon

    International Conference in Image Processing (ICIP) 2025

    Best Student Paper Award

    [Paper] [Code]

  • Regularizing Dynamic Radiance Fields with Kinematic Fields

    Woobin Im, Geonho Cha, Sebin Lee, Jumin Lee, Juhyeong Seon, Dongyoon Wee, and Sung-Eui Yoon

    European Conference on Computer Vision (ECCV) 2024

    [Paper] [Code]

  • Extending SAM into Auditory and Temporal Dimensions for Audio-Visual Segmentation

    Juhyeong Seon, Woobin Im, Sebin Lee, Jumin Lee, and Sung-Eui Yoon

    International Conference in Image Processing (ICIP) 2024

    [Paper] [Code]

  • SemCity: Semantic Scene Generation with Triplane Diffusion

    Jumin Lee*, Sebin Lee*, Changho Jo, Woobin Im, Juhyeong Seon, and Sung-Eui Yoon

    Computer Vision and Pattern Recognition (CVPR) 2024

    [Paper] [Code] [Project]

  • Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data

    Jumin Lee, Woobin Im, Sebin Lee, and Sung-Eui Yoon

    Image Processing and Image Understanding (IPIU) 2023

    Oral paper

    [Paper] [Code]

Awards & Honors

  • Winner, NRF Ph.D. Fellowship, National Research Foundation of Korea, 2024
  • Grand Prize Award, 35th Workshop on Image Processing and Image Understanding (IPIU), 2023