Daneul Kim

I'm a first year Ph.D student in the Department of Computer Science and Engineering at Seoul National University, advised by Jaesik Park. I'll also be joining SONY Research as a research scientist intern at the SONY AI Lab from this Fall. My research interests lie at the intersection of computer vision and machine learning, with a focus on generative models and multimodal understanding.

I received my M.S. degree from Seoul National University, advised by Jaesik Park, and was honored with the Best Thesis Award. During my master’s, I worked as a research scientist intern at Microsoft Research Asia with Chong Luo and Qi Dai.

I earned my B.S. in Electrical Engineering and Computer Science from Gwangju Institute of Science and Technology (GIST). During my bachelor's, I was fortunate to be advised by Jonghyun Choi at Yonsei University and Jeany Son at GIST. I was also a recipient of the Presidential Science Scholarship.

CV  /  LinkedIn  /  Mail

profile photo

    News

       2025.08    NEW! I graduated Seoul National University with M.S. degree, honored with Best Thesis Award!

       2025.07    NEW! I will be joining SONY Research as a research scientist intern in Fall 2025, in the SONY AI Lab at Tokyo!

       2025.06     Two papers about video understanding and image editing has been accepted to ICCV 2025, Hawaii!

       2025.04     A preprint about video customization has been released on ArXiv!


    Research Experience

SONY Research
Research Scientist Intern at SONY AI Lab (Sep. 2025 ~ Mar. 2026 - (Planned))
Microsoft Research Asia
Research Scientist Intern at Visual Computing Group (Sep. 2024 ~ Mar. 2025)
Advisor: Chong Luo and Qi Dai
Seoul National University logo Seoul National University
Ph.D. student at SNU (starting Sep. 2025) – Present
Advisor: Prof. Jaesik Park
----
M.S. at SNU with Jaesik Park (Sep. 2023 – Aug. 2025)
Graduated M.S. with Best Thesis Award.
    Publications
Online Generic Event Boundary Detection
Hyung Rok Jung* , Daneul Kim* , Seunggyun Lim , Jeany Son‡ , Jonghyun Choi‡
(* equal contribution, ‡ corresponding authors)
NEW! ICCV 2025
[paper - to be released]
Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
Joonghyuk Shin , Alchan Hwang , Yujin Kim , Daneul Kim , Jaesik Park
NEW! ICCV 2025
[paper] [bibtex] [code] [project]
Subject-driven Video Generation via Disentangled Identity and Motion
Daneul Kim , Jingxu Zhang , Wonjoon Jin , Sunghyun Cho , Qi Dai , Jaesik Park , Chong Luo
NEW! 2504.17816 (arXiv preprint)
[paper] [bibtex] [code] [project]
Improving Editability in Image Generation with Layer-wise Memory
Daneul Kim , Jaeah Lee , Jaesik Park
CVPR 2025
[paper] [bibtex] [code] [project]
Pick-or-Mix: Dynamic Channel Sampling for ConvNets
Ashish Kumar , Daneul Kim, Jaesik Park , Laxmidhar Behera
CVPR 2024
[paper] [bibtex] [code]
Story Visualization by Online Text Augmentation with Context Memory
Daechul Ahn , Daneul Kim , Gwangmo Song , Seung Hwan Kim , Honglak Lee , Dongyeop Kang , Jonghyun Choi
ICCV 2023
[paper] [bibtex] [code] [project]
    Honors and Awards
  • Best Master's Thesis
    1. (Aug. 2025) Graduated with Best Master's Thesis Award
      Thesis: ``Advancing Image Editing through Layer Memory in Diffusion''
  • Award for Outstanding Poster Presentation
    1. (Feb. 2025) "층위별 메모리를 활용한 이미지 편집 개선 기법" at IPIU 2025
  • Magna Cum Laude
    1. (Aug. 2023) Graduation with honors of Magna Cum Laude at GIST.
  • Presidential Science Scholarship
    1. (Mar. 2021 - Aug. 2023) Full tuition and stipend of $5,000 per year. ~150 students are selected nationally.
  • Scholarship for Study Abroad Program
    1. (Jun. 2021 - Dec. 2021) Full support of expenses + $24,000 stipend for UC Berkeley Exchange Program.

    Academic Services
  • Teaching Assistant
    1. (Summer 2025) Creating Images Using Generative AI, @ Samsung Data Scientist Academy, Samsung Electronics
      (Summer 2025) Generative AI Capstone Project @ HD Hyundai
      (Fall 2023) Generative Artificial Intelligence, @ SNU
      (Spring 2021) Object Oriented Programming, @ GIST
  • Invited Talk
    1. (Aug. 2025) Recent Trends on Visual Generation: From Basics to Application, @ SNUH, SNU Medical Vision Lab.
      (Apr. 2025) Improving Editability in Image Generation with Layer-wise Memory, @ SNU AI Institute Brown Bag Seminar

This template is from Jon Barron.