Hello! I am

Kim Dongjin

I'm a

About

About Me

I am an integrated M.S.–Ph.D. student in the DAVIAN Lab at KAIST AI, advised by Professor Jaegul Choo. My research interests include Vision-Language-Action (VLA), LLM Safety, and various multi-modal learning tasks.

  • Name: Kim Dongjin
  • Address: Seoul, South Korea
  • Email: dj_kim@kaist.ac.kr
  • LinkedIn: Click here
0 Published Papers
0 Total Research Hours
0 Sleepless Nights

Education

2025-Present

Integrated M.S.–Ph.D. in AI

KAIST, DAVIAN Lab
  • Advisor: Prof. Jaegul Choo
  • Research focus: VLA, LLM Safety, multi-modal learning
2019-2025

B.S. in Computer Science & Engineering

Kyung Hee University
  • Undergraduate researcher at Visual AI Lab
  • Advisor: Prof. Jung Uk Kim
  • Research focus: Multi-modal learning, Video Understanding, Sound Source Localization

Publications

2025

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

CVPR 2025

Sung Jin Um*, Dongjin Kim*, Sangmin Lee, Jung Uk Kim (*Equal contribution)

#Multi-modal #Video Understanding #Sound Source Localization

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

AAAI 2025

Sung Jin Um, Dongjin Kim, Sangmin Lee, Jung Uk Kim

#Multi-modal #Video Understanding #Moment Retrieval #Highlight Detection

2024

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

CVPR 2024

Dongjin Kim*, Sung Jin Um*, Sangmin Lee, Jung Uk Kim (*Equal contribution)

#Multi-modal #Video Understanding #Sound Source Localization

2023

Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization

ACM MM 2023

Sung Jin Um*, Dongjin Kim*, Jung Uk Kim (*Equal contribution)

#Multi-modal #Video Understanding #Sound Source Localization

Work & Lab Experiences

2025.03-Present

Integrated M.S.–Ph.D. Student

DAVIAN Lab, KAIST AI
  • Research on VLA, LLM Safety, and multi-modal learning.
2024.03-2024.08

AI Engineer

LETSUR, AI Startup
  • Development of AI-based services utilizing LLMs and RAG
2024.01-2024.02

AI Research Intern

ETRI, Electronics and Telecommunications Research Institute
  • Research on Video Moment Retrieval and Highlight Detection
2022.11-2025.02

Undergraduate Researcher

Visaul AI Lab, Kyung Hee University
Supervisor

Jung Uk Kim

Publications
  • [CVPR 2025] Object-aware Sound Source Localization via Audio-Visual Scene Understanding
  • [AAAI 2025] Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
  • [CVPR 2024] Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge
  • [ACM MM 2023] Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization

Talks & Presentations

Conference Presentations

2025

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

CVPR 2025, Nashville, Tennessee

Poster presentation at the Conference on Computer Vision and Pattern Recognition (CVPR) 2025.

Poster

2024

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

CVPR 2024, Seattle, WA

Poster presentation at the Conference on Computer Vision and Pattern Recognition (CVPR) 2024.

Poster

2023

Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization

ACM MM 2023, Ottawa, Canada

Poster presentation at the ACM International Conference on Multimedia (ACM MM) 2023.

Poster

Invited Talks

2025

My Experience of CVPR Acceptance as an Undergraduate and Advice for Graduate School

NexusAI Cohort 2 Final Seminar, Seoul, South Korea

Invited talk on my experience of submitting CVPR 2025 and my advice for pursuing a PhD.

Slides

Contact

Contact Me

If you have questions about my research
or would like to discuss a potential collaboration,
please feel free to reach out at any time.

Address

Seoul, South Korea

Contact Number

+ 82 10 2128 0852

Email Address

dj_kim@kaist.ac.kr

LinkedIn

LinkedIn Profile