about

img

  Greetings! I am June, a Ph.D. student under the supervision of Prof. Jaegul Choo at KAIST, where I also received my M.S. degree advised by Prof. In So Kweon. I was a visiting scholar at CMU in 2024, a research intern at NAVER in 2025 ,Lunit AI in 2023 and Qualcomm AI Research in 2022, and a research engineer at Hyundai Mobis in 2021-2022. I invite you to explore my blog, where you'll find that I am a highly self-motivated researcher. My ultimate goal is to develop AI that benefits all individuals, regardless of their socioeconomic status.



Research Experiences



Publications

  • nbf-rld Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data.
    Junha Song, Tae Soo Kim, Gunhee Nam, Junha Kim, Thijs Kooi, and Jaegul Choo
    In the European Conference on Computer Vision (ECCV), 2024
    [pdf], [project page], [code]
  • ecotta Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management.
    Junha Song, Kwanyong Park, Inkyu Shin, Sanghyun Woo, Chaoning Zhang, and In So Kweon
    In IEEE Robotics and Automation Letters (RA-L, ICRA Oral), 2024
    [pdf], [article], [presentation]
  • ecotta A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond.
    Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi, and In So Kweon
    In International Joint Conference on Artificial Intelligence (IJCAI), 2023.
    [pdf], [slide]
  • ecotta EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization.
    Junha Song, Jungsoo Lee, In So Kweon, and Sungha Choi
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
    [pdf], [project page]


Patents



Research Interests

  • Efficient captioning and video understanding
    • A crucial next step in AI's evolution is enabling systems to visually sense, understand, and anticipate their environment. Recent works in video understanding achieve this by combining LLMs' broad knowledge with frame-by-frame video captioning. I am particularly interested in developing such models for practical applications, as this technology could help visually impaired individuals better perceive and interact with their surroundings through text descriptions.
    • On this topic, I collaborated with Yonatan Bisk and  Tiffany Min.
    • Recommended reading - my top pick from related research: Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
  • On-device adaptation frameworks
    • Despite advances in deep learning, the AI model often struggles with performance degradation due to environmental changes. For example, the cognitive ability of self-driving cars can change depending on time, weather, and city-state. To address this, I am fascinated with adaptation techniques, such as adaptation with user-provided feedback (ECCV'24) and test-time adaptation (CVPR'23). I believe this technique would be key to ensuring robust performance of the model and ultimately building reliable AI applications.
  • Adaptation with foundation models
    • Powerful foundation models, such as CLIP, SAM, and Stable Diffusion, are trained on mountains of data and thus possess a remarkable capacity for understanding a wide range of images. I am captivated by their potential and eager to leverage them so as to develop and adapt ML models for real-world products. This endeavor holds immense promise in mitigating the out-of-distribution generalization problem, ensuring that AI systems can reliably perform across diverse scenarios.
    • Exploring the opportunities of foundation models (paper from CRFM at the Standord).
    but also open to other challenging fields. My ultimate goal is to develop AI for everyone by applying the above technologies to real applications.



Education

  • Korea Advanced Institute of Science and Technology (KAIST) Aug 2023 - Present
    Ph.D student
    in Graduate School of AI
    Advisor: Prof. Jaegul Choo
  • Korea Advanced Institute of Science and Technology (KAIST) Feb 2021 - Feb 2023
    M.S. degree
    in the Division of Future Vehicle
    Advisor: Prof. In So Kweon
    Grade: 3.9 / 4.3 (Percent: 95.56/100)
  • Kookmin University (Seoul, South Korea) Feb 2015 - Feb 2021
    B.S. degree
    in IT and Automobile Engineering
    Grade: 4.39 / 4.5 (Rank: 1/121 | Percent: 98.7/100 | Major: 4.43)
    National Science and Engineering Scholarship (Full tuition) from Korea Student Aid Foundation
    Mandatory Military Service for 21 Months


Awards and Honors



Projects

  • Development of real-time masking/unmasking system for personal video information for public services such as CCTV (article), Korea Ministry of Science and ICT (2021 - 2023)
  • Development of segmentation networks robust to environment variance, Hyundai Mobis (2021)
  • Satellite image precision object detection, Korea Agency for Defense Development (ADD) (2020)
  • Detection of Surrounding Vehicles using Deep Neural Network and Fusion of Panoramic Camera and Lidar Sensor, Korea Foundation for the Advancement of Science and Creativity (KORAC), Korea (2019)


B.S. Research Experiences

  • "Style Transfer Maps from Satellite Images by using Generative Model", Korean Institute of Communications and Information Science (KICS) (2020)
  • "Improvement of LiDAR and IMU-based autonomous driving performance in right-angle corner situations", Korean Sociey of Automotive Engineers (2019)
  • Research Intern at Machine Intelligence Lab, Kookmin University (Dec 2019 - Oct 2020)
  • Research Intern at Intelligence and Interaction Lab, Kookmin University (Feb 2019 - Nov 2019)


Skills

  • Programming language: Python, C++
  • Machine Learning Librarie: Pytorch, Tensorflow
  • Application development: Robot Operating System (ROS)
  • Sensor utilization: Camera, RGB-D Camera, LiDAR, GPS/IMU