😃 About me

I’m a Ph.D. student at Artificial Intelligence & Machine Learning (U-AIM) Lab. in KAIST, under the supervision of Prof. Chang D. Yoo. My primary research interests focus on the application of generative models in the field of computer vision. Starting from image/video generation and editing, I have recently been focusing on 3D/4D generation and reconstruction. My long-term goal is to integrate these directions toward building generative world models that can perceive, reconstruct, and simulate the 3D world.

My research interest includes:

  • 3D/4D Reconstruction, Generation
  • World Models and Simulation

🔥 News

  • 2026.06:  🎉 Two papers accepted to ECCV 2026
  • 2026.05:  🎉 One paper accepted to ICML 2026
  • 2026.03:  🏆 Received the Outstanding Research Achievement Award from KAIST Electrical Engineering.

📝 Conference Publications

2026

ECCV 2026
sym

[C14] InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image

Gwanhyeong Koo, Hyunsu Kim, Youngji Kim, Taejae Lee, Siwoo Lim, Sunjae Yoon, Suyong Yeon, Chang D. Yoo

ECCV 2026

Project Page

*Work done during the internship at NAVER LABS

ECCV 2026
sym

[C13] TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization

Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo, Hyeonseo Yun, Chang D. Yoo

ECCV 2026

Project Page

ICML 2026
sym

[C12] GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting

Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo, Chang D. Yoo

ICML 2026

Paper

CVPR 2026
sym

[C11] PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning

Hee Suk Yoon, Eunseop Yoon, Ji Woo Hong, SooHwan Eom, Gwanhyeong Koo, Mark A. Hasegawa-Johnson, Qi Dai, Chong Luo, Chang D. Yoo

CVPR 2026

Paper

2025

ICCV 2025
sym

[C10] Occlusion-robust Stylization for Drawing-based 3D Animation

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

ICCV 2025, Review Score: 6,6,5 (avg. 5.67/6)

Paper Code Project Page

ICML 2025
sym

[C9] FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields

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

ICML 2025, Spotlight (313/12107=2.6%)

Paper Code Project Page Poster

CVPR 2025
sym

[C8] 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

CVPR 2025

Paper Code Project Page

2024

NeurIPS 2024
sym

[C7] TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation

Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee, Chang D. Yoo

NeurIPS 2024

Paper Code

EMNLP 2024
sym

[C6] Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM

SooHwan Eom, Jay Shim, Gwanhyeong Koo, Haebin Na, Mark A. Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo

EMNLP 2024 (Findings)

Paper

ECCV 2024
sym

[C5] FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

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

ECCV 2024

Paper Code Project Page Poster

ECCV 2024
sym

[C4] Dilutional Noise Initialization for Dilution Video Editing

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

ECCV 2024

Paper Code

ICML 2024
sym

[C3] FRAG: Frequency Adapting Group for Diffusion Video Editing

Sunjae Yoon, Gwanhyeong Koo, Geonwoo Kim, Chang D. Yoo

ICML 2024

Paper Code Project Page

ICASSP 2024
sym

[C2] Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing

Gwanhyeong Koo, Sunjae Yoon, Chang D. Yoo

ICASSP 2024

Paper

2023

ICCV 2023
sym

[C1] SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval

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

ICCV 2023

Paper Code

💼 Work Experience

NAVER LABS

Research Intern @ NAVER LABS — Spatial AI Team

2025.09 - 2026.03 · Seongnam-si, South Korea

Mentor: Suyong Yeon

🎖 Honors and Awards

  • 2026.03 Received the Outstanding Research Achievement Award from KAIST Electrical Engineering.
  • 2025.06 CVPR Outstanding Reviewer (2025), Recognized as one of the top 5.64% among 12,582 reviewers for CVPR 2025
  • 2024.10 1st Prize 2nd Seoul National University Bundang Hospital (SNUBH) Datathon Award
  • 2023.11 Best Paper Award, Winter Conference, Korean Artificial Intelligence Association (JKAIA), 2023
  • 2022.09 TensorFlow Developer Certificate
  • 2019.10 Bronze Award in 2019 International University Student Creative Car Competition, in Autonomous Driving

📖 Educations

  • 2024.09 - Present, Ph.D. in Electrical Engineering. (KAIST)
  • 2023.03 - 2024.08, M.S. in Electrical Engineering (Devision of Future Vehicle). (KAIST)
  • 2017.03 - 2023.02, B.S. in Electric Engineering. (DGIST)

🎯 Projects

  • 2023 - 2025, Oriented Object Detection in Optical Remote Sensing Image, Hanwha Systems

🎨 Academic Services

  • Conference Reviewer: ECCV’24, ICASSP’25, CVPR’25, ICML’25, SIGGRAPH’25, ACM MM’25, NeurIPS’25, WACV’26, AAAI’26, ICLR’26, ICASSP’26, CVPR’26, ECCV’26, SIGGRAPH Asia’26, NeurIPS’26
  • Journal Reviewer:
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    • Pattern Recognition
    • Transactions on Machine Learning Research (TMLR)
    • Expert Systems With Applications

✏️ Teaching Assistant

  • [EE531] Statistical Learning Theory: 2025 Spring, 2026 Spring
  • [EE331] Introduction to Machine Learning: 2024 Fall