I'm a magician ! [Jul. 2025]
I'm a magician ! [Jul. 2025]
Junsu Kim ( 김준수 )
Combined MS-PhD Student
==================================================
🔥E-MAIL: jjunsssk@unist.ac.kr (official), jjunsss0101@gmail.com (personal)
🔥Blog: BLOG LINK
🔥Linkedin: LinkedIN LINK
🔥CV Link : OVERLEAF LINK
==================================================
News.
📣NEW! Jul 2025 One paper accepted to BMVC (Co-first author).
📣NEW! Jul 2025 Two papers accepted to ICCVW (1st author).
📣NEW! Mar 2025 One paper released on arXiv (1st author).
📣NEW! Oct 2024 Research Intern, NAVER AI LAB, Backbone Research Team.
📣NEW! Sep 2024 Invited as the UNIST representative at the Digital Innovators Symposium.
📣NEW! CVPR 2024 First‑author paper selected as a Highlight Poster.
📣NEW! CVPRW 2024 First‑author paper accepted to the workshop track.
📣NEW! CVPR 2024 First‑author paper accepted to the main conference
==================================================
Bio.
My name is Junsu Kim. I am a Combined MS/Ph.D. student in the Artificial Intelligence Graduate School (AIGS) at UNIST, enrolled since March 2023. I hold a B.Sc. in Information and Communications Engineering from Pukyong National University (2022).
My research interests include computer vision, continual learning, open‑world object detection, vision‑language models, and efficient AI, with a particular focus on integrating these technologies into robotics and foundation models (e.g., diffusion models).
Outside academia, I completed an AI internship at NAVER AI Lab, served as an NVIDIA DLI Ambassador, and led the NVIDIA × MODULABS Foundation Models Lab. I aim to bridge cutting‑edge AI theory with real‑world applications to develop systems that make a positive impact.
Computer Vision and deep learning.
Continual learning, Open world object detection, Robotics, Foundations...
MS-Ph.D. in Artificial Intelligence | Mar. 2023 – Present
Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea
Advisor: Prof. Seungryul Baek
B.S. in Information and Communications Engineering | Mar. 2016 – Feb. 2022
Pukyong National University (PKNU), Busan, South Korea
Advisor: Prof. Hoon Lee (ACNL Lab)
AI research intern, NAVER AI Lab, Seoul, South Korea | Oct. 2024 ~ Apr. 2025
NAVER AI Lab (Backbone Research Team), Seoul, South Korea
Advisor : Dongyoon Han [LINK]
NVIDIA AI Ambassador | Feb. 2022 – Mar. 2025
Leader, NVIDIA × MODULABS Foundation Models Lab | Feb. 2024 – Present
AI research intern | Aug. 2022 – Feb. 2023
UVL Lab, Ulsan, South Korea
AI research intern | Apr. 2022 – Jul. 2022
Corp. KST, Busan, South Korea
J. Kim*, Y. Jang*, H. Kim, E. Lee, E. Kim, S. Baek, J. Yoo, "B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing," in Proc. of the British Machine Vision Conference (BMVC), Sheffield, UK, 2025 (to be presented). [PDF] (* indicates co-first authorship)
J. Kim, Y. Ku, S. Beak, "Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning", in Proc. of the IEEE/CVF International Conference on Computer Vision (ICCV) workshop, Honolulu, USA, 2025. [PDF]
J. Kim, Y. Ku, J. Kim, J. Cha, S. Beak, "VLM-PL: Advanced Pseudo Labeling approach Class Incremental Object Detection with Vision-Language Model," in Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) workshop, Seattle, WA, 2024. [PDF]
[HIGHLIGHT] J. Kim, H. Cho, J. Kim, Y. Tiruneh, S. Beak, "SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection," in Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 2024. [PDF] (Highlight, 324/11532≈2.8% ratio)
J. Kim, S. Hong, C. Kim, J. Kim, Y. Tiruneh, J. On, J. Song, S. Choi, and S. Baek, "Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy," accepted for publication in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, South Korea, 2024.[PDF]
J. Kim, S. Hong, J. Kim, J. On, C. Kim, Yihalem, J. Song, S. Choi and S. Baek "Reducing data imbalancing for Object Detection," in Proc. 2023 Summer Conference of Institute of Electronics and Information Engineers (IEIE), Jun. 2023.
H. Park, J. Kim, J. Kim and S. Baek, "Temporal MANO based Video Hand Pose and Shape Estimation," JKAIA, 2022.
[BEST PAPER AWARD] I. Lee, J. Kim, H. Lee, Y. Kim, D. Lee, H. Lee “Multi-Task Learning Approach to Autonomous Driving Techniques,” in Proc. 2021 Fall Conference of Institute of Electronics and Information Engineers (IEIE), Nov, 2021.
[BEST PAPER AWARD] H. Kim, J. Kim, I. Lee, and H. Lee ”Deep Learning-Based Self-Driving Systems for Swarm Vehicle,” in Proc. 2021 Summer Conference of Korea Information and Communications Society (KICS), Jun. 2021.
J. Kim, H. Kim, I. Lee, H. Lee “AI Edge Server Design for Swarm Vehicular Network,” in Proc. 2021 ICT College Paper Contest of Institute of Embedded Engineering of Korea (IEMEK), May. 2021.
H. Kim, J. Kim, I. Lee, and H. Lee “AI-Enabled Low-Complexity Autonomous Driving Using Tensor RT,” in Proc. 2021 Winter Conference of Korea Information and Communications Society (KICS), Feb. 2021.
J. Kim, N. Kim, J. Lee, I. Park, D. Han†, S. Baek†, “Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark,” ICCV Workshops (MMFM), Honolulu, USA, 2025. †corresponding authors. [non-arch.][arXiv] [code].
J. Kim, Y. Ku, D. Han†, S. Baek† "Diffusion Meets Few-shot Class Incremental Learning," In under review, †corresponding authors, ArXiv, Mar 2025 [paper]
J. Kim, S. Hong, C. Kim, H. Cho, Yihalem, J. Kim, E. Kim, J. Song, S. Choi, S. Baek "An Effective Buffer Training Strategy for Class-Incremental Object Detection", CVPR workshop (CLVision), Jun. 2023. [non-arch.] The improved version was accepted to ICASSP 2024.
Professional Service
Reviewer, British Machine Vision Conference (BMVC), 2025.
Reviewer, IEEE Transactions on Multimedia (TMM), 2024.
Reviewer, IEEE Transactions on Image Processing (TIP), 2024.
Presentations
Oral Presentation, UNIST Representative, Digital Innovators Symposiums, 2024.
Poster Presentation, Korean Conference on Computer Vision (KCCV), 2024.
Poster Presentation, "An Effective Buffer Training Strategy for Class-Incremental Object Detection," CVPR Workshop (CLVision), 2023.
"사람 중심 인공지능 핵심원천기술개발" (Human-centered AI Core Technology Development) | Sep. 2023 – Present
Funded by MIST (과기부) through IITP
"Development of Object Detection Models for Impurity Detection in Fish Cake Products" | Sep. 2023 – Present
Industry-University Cooperation with Samjin-food
"Expanding Data Coverage through Incremental Learning and Development of Integrated Domain Recognition Systems" | Aug. 2022 – Aug. 2023
Industry-University Cooperation with LG Electronics
Achievement: Led to the designation of our lab as a "Target Lab" by LG Electronics.
"Identification Systems of Dog Nose-Print Using Siamese Network" | Sep. 2021 – Dec. 2021
Co-work with Urobo AI (Startup)
"AI-Assisted Safety Systems Using Industrial Internet-of-Things (IIoT)" | Apr. 2021 – Dec. 2021
X-corps Festival Project
"Autonomous Driving Techniques for Industrial Safety" | Jun. 2021 – Sep. 2021
Pukyong National University Han Contest
"Deep Learning Approaches for Swarm Autonomous Vehicle Systems" | Jan. 2021 – Mar. 2021
Leaders in Industry-university Cooperation (LINC) Project
Excellence Award, Poster presentation, 37th Workshop on Image Processing and Image Understanding, 2025.
Excellence Award, PKNU Study Club Performance, 2022, (Host: Pukyong Nation Univ.)
Excellence Award, LINK+ Competitive Contest, 2021, (Host: Pukyong Nation Univ.)
Excellence Award, Han. Competitive Contest, 2021, (Host: Pukyong Nation Univ.)
Best Undergraduate Paper Award, 2021, (Host: IEMEK, The Institute of Embedded Engineering of Korea)
Best Undergraduate Paper Award, 2021, (Host: KICS, The Korea’s information and communications technology)
Best Undergraduate Paper Award, 2021, (Host: IEIE, The Institute of Electronics and Information Engineers)
Excellence Award, Presentation Engineering in literature, 2021, (Host: Pusan National Univ.)
1st Prize, PKNU Capstone Design, 2021, (Host: Pukyong Nation Univ)
2nd Prize (KIBO), Busan AI Idea Contest Exhibition, 2020, (Host: NILE, Busan)
Notion Ambassador | Jan. 2023 – Jan. 2025
Lecture Mentor (Language Model, RAG), 13th Samsung Software AI-academy For Youth (SSAFY), SAMSUNG, Busan, Jul. 2025
Workshop Lecturer, 6th AI Novatus Academia (Computer Vision), UNIST AI Innovation Park, Ulsan, Aug. 2023
Workshop Lecturer, 5th AI Novatus Academia (Computer Vision), UNIST AI Innovation Park, Masan, Apr. 2023.
Workshop Lecturer, NVIDIA Jetson AI Ambassador Workshop, Pukyong National University, May 2022.
Workshop Presentation, Corp. KST, May 2022.
Youtube videos
Anydoor / GLIGEN+BLIP / LayoutDM / Classifier-free guidance / I-blurry / PristmaticVLMs (2025)
혁신인재 심포지엄 2024
KCCV2024
CVPR2024
CVPR2024 workshop
ICASSP2024
CVPR2023 workshop
I'm flying ! [Oct. 2024]