😃 About me

I am currently working as a postdoctoral researcher at KAIST as part of South Korea’s alternative 1-year military service (March 2025 ~ Feb 2026). My expertise lies in Generative AI technologies (e.g., diffusion models) across multiple modalities, including images, videos, and natural language. I obtained Ph.D. (2025) and M.S. (2021) at KAIST, advised by Professor Chang D. Yoo.

I will be available to start work in March 2026.

I warmly welcome and appreciate any work opportunities given to me.

For more information, please refer to my CV.

📌 Research Interests

  • Computer Vision
  • Generative AI
  • Diffusion model
  • Multi-modal Reasoning
  • Causality and Debiasing
  • Natural Language Processing

🔥 News

  • 2025.06:  🎉 One paper accepted to ICCV 2025
  • 2025.05:  🎉 One paper accepted to ICML 2025 (Spotlight)
  • 2025.03:  🎉 Outstanding Ph.D. Dissertation Award, School of Electrical Engineering, KAIST, 2025
  • 2025.02:  🎉 One paper accepted to CVPR 2025

🏫 Education

  • Mar.2021 - Feb.2025: Ph.D. Electrical Engineering (KAIST)

   Thesis: “Diffusion-based Video Editing”

   Advisor: Prof. Chang D. Yoo

   Outstanding Ph.D. Dissertation Award, School of Electrical Engineering, KAIST, 2025

  • Sep.2019 - Feb.2021: M.S. Electrical Engineering (KAIST)

   Thesis: “Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval”

   Advisor: Prof. Chang D. Yoo

  • Mar.2015 - Feb.2019: B.S. Computer Science (DGIST)

   Advisor: Prof. Yongseob Lim

   Cum Laude

📎 Selected Publications

[10] Sunjae Yoon , Gwanhyeong Koo, Younghwan Lee, Ji Woo Hong and Chang D. Yoo, “Occlusion-robust Stylization for Drawing-based 3D Animation”, International Conference on Computer Vision (ICCV) 2025

[9] Sunjae Yoon , Gwanhyeong Koo, Younghwan Lee, and Chang D. Yoo, “TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation”, Neural Information Processing Systems (NeurIPS) 2024

[8] Sunjae Yoon , Gwanhyeong Koo, Ji Woo Hong, and Chang D. Yoo, “Dilutional Noise Initialization for Diffusion Video Editing”, European Conference on Computer Vision (ECCV) 2024

[7] Sunjae Yoon , Gwanhyeong Koo, Geonwoo Kim, and Chang D. Yoo, “FRAG: Frequency Adaptive Group for Diffusion Video Editing”, International Conference on Machine Learning (ICML) 2024

[6] Sunjae Yoon , Dahyun Kim, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, and Chang D. Yoo, “HEAR: Hearing Enhanced Audio Response for Viode-grounded Dialogue”, Findings of the Association for Computational Linguistics: EMNLP 2023 (long paper, findings)

[5] Sunjae Yoon , Gwanhyeong Koo, Dahyun Kim, and Chang D. Yoo “SCANet: Scene Complexity Aware Network for Weakly-supervised Video Moment Retrieval”, International Conference on Computer Vision (ICCV) 2023

[4] Sunjae Yoon , Ji Woo Hong, SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Daehyeok Kim, Junyeong Kim, Chanwoo Kim, and Chang D. Yoo, “Counterfactual Two-stage Debiasing Network for Video Corpus Moment Retrieval”, The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, Oral

[3] Sunjae Yoon , Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, and Chang D. Yoo “Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue”, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022. (long paper)

[2] Sunjae Yoon , Ji Woo Hong, Eunseop Yoon, Dahyun Kim , Junyeong Kim, Hee Suk Yoon, and Chang D. Yoo, “Selective Query-guided Debiasing for Video Corpus Moment Retrieval”, European Conference on Computer Vision (ECCV) 2022

[1] Minuk Ma *, Sunjae Yoon *, Junyeong Kim, Youngjuoon Lee, Sunghun Kang, and Chang D. Yoo, “VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval”, European Conference on Computer Vision (ECCV) 2020 (equal contribution)

📝 Publications (27 publications, 15 fisrt-author)

[*] equal contribution

2025

ICCV 2025
[C21] Occlusion-robust Stylization for Drawing-based 3D Animation
Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee, Ji Woo Hong, and Chang D. Yoo
International Conference on Computer Vision (ICCV) 2025 Review Score: 6,6,5 (avg. 5.67/6)
GitHub Repo Demo Page
ICML 2025
sym

[C20] FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields

Gwanhyeong Koo, Sunjae Yoon , Younghwan Lee, Ji Woo Hong, and Chang D. Yoo

International Conference on Machine Learning (ICML) 2025, Spotlight (<2.6%) GitHub Repo Demo Page

CVPR 2025
sym

[C19] ITA-MDT:Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On

Ji Woo Hong, Tri Ton, Trung X. Pham, Gwanhyeong Koo, Sunjae Yoon , Chang D. Yoo

Computer Vision and Pattern Recognition (CVPR) 2025

GitHub Repo Demo Page

2024

NeurIPS 2024
[C18] TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee, and Chang D. Yoo
Neural Information Processing Systems (NeurIPS) 2024
GitHub Repo Demo Page
ECCV 2024
[C17] Dilutional Noise Initialization for Dilution Video Editing
Sunjae Yoon, Gwanhyeong Koo, Ji Woo Hong, and Chang D. Yoo
European Conference on Computer Vision (ECCV) 2024
GitHub Repo (In process of U.S./J.P. patent registeration)
ECCV 2024
sym

[C16] FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

Gwanhyeong Koo, Sunjae Yoon , Ji Woo Hong, and Chang D. Yoo

European Conference on Computer Vision (ECCV) 2024

GitHub Repo Demo Page

ICML 2024
[C15] FRAG: Frequency Adapting Group for Diffusion Video Editing
Sunjae Yoon, Gwanhyeong Koo, Geonwoo Kim, and Chang D. Yoo
International Conference on Machine Learning (ICML) 2024
GitHub Repo Demo Page
ICPRAI 2024
sym

[C14] Character Identifying Video Language Alignment Network for Weakly-Supervised Video-Subtitle Moment Retrieval

Donghoon Lee ∗, Jun Yeop Shim ∗, Sunjae Yoon , and Chang D Yoo

International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI), 2024, Oral

Journal of the IEIE
sym

[J6] Spatial Adaptive Kernel Network for Enhanced Oriented Ship Detection in Synthetic Aperture Radar Imagery

Gwanhyeong Koo, Sunjae Yoon , Donghoon Lee, Soo Hwan Eom, JongSik Ahn, Tae-Young Lee, Chang D. Yoo.

Journal of The Institute of Electronics and Information Engineers, 2024

IEEE Access 2024
sym

[J5] Causal Localization Network for Radar Human Localization with micro-Doppler signature

Sunjae Yoon , Gwanhyeong Koo, Jun Yeop Shim, Soohwan Eom, Ji Woo Hong, Chang D. Yoo

IEEE Access, 2024

GitHub Repo

ICASSP 2024
sym

[C13] WAVELET-GUIDED ACCELERATION OF TEXT INVERSION IN DIFFUSION-BASED IMAGE EDITING

Gwanhyeong Koo, Sunjae Yoon , Chang D. Yoo

The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

(Related Patent: KR 10-2837290)

AAAI 2024
sym

[C12] SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation

Hyun Ryu, Sunjae Yoon , Hee Suk Yoon, Eunseop Yoon, and Chang D. Yoo

AAAI Association for the Advancement of Artificial Intelligence (AAAI) 2024

GitHub Repo

2023

EMNLP 2023
sym

[C11] HEAR: Hearing Enhanced Audio Response for Viode-grounded Dialogue

Sunjae Yoon , Dahyun Kim, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, and Chang D. Yoo

Empirical Methods in Natural Language Processing (EMNLP) 2023 (long paper, findings)

GitHub Repo 30th Samsung HumanTech Paper Award

ICCV 2023
sym

[C10] SCANet: Scene Complexity Aware Network for Weakly-supervised Video Moment Retrieval

Sunjae Yoon , Gwanhyeong Koo, Dahyun Kim, and Chang D. Yoo

International Conference on Computer Vision (ICCV) 2023

GitHub Repo

ICASSP 2023
sym

[C9] Counterfactual Two-stage Debiasing Network for Video Corpus Moment Retrieval

Sunjae Yoon , Ji Woo Hong, SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Daehyeok Kim, Junyeong Kim, Chanwoo Kim, and Chang D. Yoo

The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, Oral

Access 2023
sym

[J4] Joint Path Alignment Framework for 3D Human Pose and Shape Estimation from Video

Ji Woo Hong, Sunjae Yoon , Junyeong Kim, and Chang D. Yoo

IEEE Access, 2023

Sensors 2022
sym

[J3] CE-BART: Cause-and-Effect BART for Visual Comonsense Generation

Junyeong Kim, Ji Woo Hong, Sunjae Yoon , and Chang D. Yoo

MDPI Sensors, 2022

ICLR 2023
sym

[C8] ESD: EXPECTED SQUARED DIFFERENCE AS A TUNING-FREE TRAINABLE CALIBRATION MEASURE

Hee Suk Yoon, Joshua Tian Jin Tee , Eunseop Yoon, Sunjae Yoon , Gwangsu Kim, Yingzhen Li, and Chang D. Yoo

International Conference on Learning Representation (ICLR), 2023

GitHub Repo

2022

EMNLP 2022
sym

[C7] Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue

Sunjae Yoon , Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, and Chang D. Yoo

Empirical Methods in Natural Language Processing (EMNLP), 2022. (long paper)

GitHub Repo

EMNLP 2022
sym

[C6] SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation

Hee Suk Yoon , Eunseop Yoon , John Harvill, Sunjae Yoon , Mark Hasegawa-Johnson, and Chang D. Yoo

Empirical Methods in Natural Language Processing (EMNLP), 2022. (short paper, findings)

ECCV 2022
sym

[C5] Selective Query-guided Debiasing for Video Corpus Moment Retrieval

Sunjae Yoon , Ji Woo Hong, Eunseop Yoon, Dahyun Kim , Junyeong Kim, Hee Suk Yoon, and Chang D. Yoo

European Conference on Computer Vision (ECCV) 2022

GitHub Repo (Related Patent: U.S. 1,232,384)

Access 2022
sym

[J2] Cascaded MPN: Cascaded Moment Proposal Network for Video Corpus Moment Retrieval

Sunjae Yoon , Dahyun Kim, Junyeong Kim, and Chang D. Yoo

IEEE Access 2022

ICASSP 2022
sym

[C4] SEMANTIC ASSOCIATION NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL

Dahyun Kim *, Sunjae Yoon *, Ji Woo Hong, and Chang D. Yoo

The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. Oral

Sensors 2022
sym

[J1] Dual-Scale Doppler Attention for Human Identification

Sunjae Yoon , Dahyun Kim, Ji Woo Hong, and Chang D. Yoo

MDPI Sensors, 2022

GitHub Repo

2021

AAAI 2021
sym

[C3] Structured Co-reference Graph Attention for Video-grounded Dialogue

Junyeong Kim, Sunjae Yoon , Dahyun Kim, and Chang D. Yoo

AAAI Association for the Advancement of Artificial Intelligence (AAAI), 2021

ICIP 2021
sym

[C2] WEAKLY-SUPERVISED MOMENT RETRIEVAL NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL

Sunjae Yoon *, Dahyun Kim *, Ji Woo Hong, Junyeong Kim, Kookhoi Kim and Chang D. Yoo

International Conference on Image Processing (ICIP), 2021

GitHub Repo

2020

ECCV 2020
sym

[C1] VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval

Minuk Ma *, Sunjae Yoon *, Junyeong Kim, Youngjuoon Lee, Sunghun Kang, and Chang D. Yoo

European Conference on Computer Vision (ECCV) 2020

Academic Activities

💬 Invited Talks

  • 2023.05, CAU-AI Core Technology Seminar: Empirical Methods and Recent Topics for Video Moment Retrieval, (2023-05-19)

🏆 Awards

  • Outstanding Ph.D. Dissertation Award, School of Electrical Engineering, KAIST, (golden medal) (2025.03)

  • Winner of Datathon Award, 2nd Seoul National University Bundang Hospital (SNUBH) Datathon Award, 1st Prize ($2,000) (2024.10)

  • 30th Samsung HumanTech Paper Award, encouragement prize ($1,500) (2024.02)

  • Winner of Best Paper Award, Winter Conference of Korean Artificial Intelligence Association (KAIA), ($1,500), (2023.11)

  • Certificate of Commendation for Cum Laude Graduation, DGIST (2019.02)

  • Certificate of Commendation from Dalseong-gun Office, Daegu (2019.02)

  • Award Bronze Prize for International University Creative Car Competition (Autonomous driving) by Korea Transportation Safety Authority, (2018.05)

  • Award Excellence Prize in Autonomous Vehicle Creation Technology by Korea Auto Vehicle Safety Association, (2018.05)

📑 Reviewer

Confernce

  • Neural Information Processing Systems (Neurips): 2023 ~

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 2022 ~

  • European Conference on Computer Vision (ECCV): 2022 ~

  • IEEE International Conference on Computer Vision (ICCV) : 2023 ~

  • The Association for the Advancement of Artificial Intelligence (AAAI) : 2025 ~

  • Association for Computational Linguistics (ACL): 2023 ~

  • Empirical Methods on Natural Language Processing (EMNLP): 2022 ~

  • International Conference on Learning Representations (ICLR): 2024 ~

  • International Conference on Machine Learning (ICML): 2024 ~

  • International Conference on Acoustics, Speech, and Signal Processing (ICASSP): 2023 ~

  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): 2023 ~

  • International Conference on Artificial Intelligence and Statistics (AISTATS): 2025 ~

Journal

  • IEEE Transactions on Big Data

  • IEEE Transactions on Circuits and Systems for Video Technology

  • International Journal of Human-Computer Interaction

  • ACM Transactions on Multimedia, Computing, Communications, and Applications

  • Expert Systems With Applications

📏 Teaching Assistant

  • Seongnam-KAIST Next Generation ICT Research Center EE Co-op+ Joint Research Program, 2024 Fall

  • Digital Speech Processing, 2024 Fall

  • Signals and Systems, 2023 Spring, 2022 Fall, 2022 Spring, 2021 Spring

  • Statistical Learning Theory, 2021 Fall

🎏 Patent

  • METHOD AND DEVICE FOR WAVELET-GUIDED ACCELERATION OF TEXT INVERSION IN DIFFUSION-BASED IMAGE EDITING No. KR 10-2837290 (2025-07-17)

  • METHOD AND DEVICE FOR VIDEO MOMENT RETRIEVAL BASED ON SELECTIVE DEBIASING No. US 1,232,384 (2025-06-03)

  • METHOD AND DEVICE FOR VIDEO MOMENT RETRIEVAL BASED ON SELECTIVE DEBIASING No. KR 10-2022-0154621 (2022-11-17)

  • WEAKLY-SUPERVISED MOMENT RETRIEVAL NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL No. KR 10-2021-0172582 (2021-12-06)

  • Artificial Intelligence-based Radar Target Detection System No. KR 10-2557458 (2023-07-14)