Hyojin Jang
M.S./Ph.D Integrated Student at KAIST
Graduate School of Artificial Intelligence
wkdgywlsrud [AT] kaist.ac.kr
About
Hi! I am a M.S./Ph.D integrated student advised by Professor Jaegul Choo at KAIST Graduate School of AI.
My research focuses on generative models, with particular interests in Image/Video Generation and Vision-Language-Action (VLA) models.
On going Project
I am a researcher at Davian Robotics, working on Vision-Language-Action (VLA). My research interests include video object insertion (VOI), with an emphasis on lighting consistency and dynamic object behavior.
Publications
(*: Equal contribution, C: Conferences, A: ArXiv).
![[A3] InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion thumbnail](/assets/publications/2026_CVPR/VOI/teaser.png)
[A3] InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
Hoiyeong Jin*, Hyojin Jang*, Jeongho Kim*, Junha Hyung, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo
Under Review, 2025.
![[A2] ACG: Action Coherence Guidance for Flow-based VLA models thumbnail](/assets/publications/2026_ICRA/icra_2025_acg.png)
[A2] ACG: Action Coherence Guidance for Flow-based VLA models
Minho Park*, Kinam Kim*, Junha Hyung, Hyojin Jang, Hoiyeong Jin, Jooyeol Yun, Hojoon Lee, Jaegul Choo
Under Review, 2025.
![[A1] Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models thumbnail](/assets/publications/2025_Neurips/teaser.png)
[A1] Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
Under Review, 2025.
![[C2] Zero-Shot Head Swapping in Real-World Scenarios thumbnail](/assets/publications/2025_CVPR/teaser.png)
[C2] Zero-Shot Head Swapping in Real-World Scenarios
Taewoong Kang*, Sohyun Jeong*, Hyojin Jang*, Jaegul Choo
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Nashville TN, USA. (Acceptance Rate: 22.1%)
![[C1] SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars thumbnail](/assets/publications/2025_ICLR/teaser.png)
[C1] SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars
Jaeseong Lee*, Taewoong Kang*, Marcel C. Bühler, Min-Jung Kim, Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo
The International Conference on Learning Representations (ICLR), 2025, Singapore.
Education
Korea Advanced Institute of Science and Technology (KAIST) 2025 - Current
Integrated M.S/Ph.D Student in Graduate School of Artificial Intelligence
Korea Advanced Institute of Science and Technology (KAIST) 2019 - 2024
Computer Science
Experience
Undergraduate Researcher May. 2024 - Feb. 2025
Data and Visual Analytics Lab (DAVIAN Lab) (advised by Prof. Jaegul Choo)