CV
Education
- Ph.D. in Artificial Intelligence, Sep. 2021 – present
Korea Advanced Institute of Science and Technology (KAIST)- Advisor: Prof. Jaegul Choo
- B.S. in School of Computing, Electrical Engineering (Double Major), Mar. 2016 – Aug. 2021
Korea Advanced Institute of Science and Technology (KAIST)- GPA: 3.93 / 4.3
Professional Experience
- Microsoft Research — AI Research Intern, Jun. 2025 – Sep. 2025
- NVIDIA — AI Research Intern, Jun. 2024 – Dec. 2024
- Naver — AI Research Intern, Feb. 2024 – Jun. 2024
- Kakao Enterprise — AI Research Intern, Jul. 2022 – Dec. 2022
- Mindslab — AI Research Intern, Mar. 2021 – Aug. 2021
- SKT — AI Fellowship, Jun. 2019 – Jun. 2020
- Kakao — AI Research Intern, Sep. 2018 – Feb. 2019
Publications
Geometry-Aware Mid-Training for World-Action Models
Junha Hyung*, Hyojin Jang*, Jaegul Choo (* equal contribution)
Under Review
Generative Failure-to-Success Bridging for Robot Learning
Junha Hyung*, Hyojin Jang*, Jaegul Choo (* equal contribution)
Under Review
Towards Data-Efficient and Real-Time World Models
Raluca Stevenson, David Bignell, Jennifer C. White, Tabish Rashid, Emanuele Aiello, Mariya Hendriksen, Junha Hyung, Sadegh Aliakbarian, Abdelhak Lemkhenter, Marko Tot, Katja Hofmann, Sarah Parisot
Under Review
EgoX: Egocentric Video Generation from a Single Exocentric Video
Taewoong Kang*, Kinam Kim*, Dohyeon Kim*, Minho Park, Junha Hyung, Jaegul Choo (* equal contribution)
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
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 (* equal contribution)
IEEE International Conference on Robotics & Automation (ICRA), 2026
Probability-Conserving Flow Guidance
Parsa Esmati*, Junha Hyung*, Amirhossein Dadashzadeh, Jaegul Choo, Majid Mirmehdi (* equal contribution)
Under Review (arXiv:2605.20079)
InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion
Hoiyeong Jin*, Hyojin Jang*, Junha Hyung*, Jeongho Kim, Kinam Kim, Dongjin Kim, Huijin Choi, Hyunji Kim, Jaegul Choo (* equal contribution)
The 19th European Conference on Computer Vision (ECCV), 2026
Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models
Kinam Kim*, Junha Hyung*, Jaegul Choo (* equal contribution)
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
Daehoon Gwak*, Minseo Jung*, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, Jaegul Choo
The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
Junha Hyung*, Kinam Kim*, Susung Hong, Min-Jung Kim, Jaegul Choo (* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel-based Head Avatars
Jaeseong Lee*, Taewoong Kang*, Marcel Buehler, Min-Jung Kim, Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo
The Thirteenth International Conference on Learning Representations (ICLR), 2025
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, Jin-Hwa Kim
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
Jaeseong Lee*, Junha Hyung*, Sohyun Jeong, Jaegul Choo (* equal contribution)
The 18th European Conference on Computer Vision (ECCV), 2024
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Junha Hyung*, Jaeyo Shin*, Jaegul Choo (* equal contribution)
The Association for the Advancement of Artificial Intelligence (AAAI), 2024
Local 3D Editing via 3D Distillation of CLIP Knowledge
Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee, Jaegul Choo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields
Sungwon Hwang, Junha Hyung, Daejin Kim, Min-Jung Kim, Jaegul Choo
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Injecting Inductive Bias to 3D Gaussian Splatting for Geometrically Accurate Radiance Fields
Sungwon Hwang, Soohyun Ryu, Jaeseong Yun, Jaeseong Lee, Junha Hyung, Min-Jung Kim, Taewoong Kang, Joohyun Park, Jaegul Choo, Suyong Yeon
Under Review
Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model
Sungwon Hwang, Junha Hyung, Jaegul Choo
arXiv preprint (arXiv:2309.03550)
PixelHuman: Animatable Neural Radiance Fields from Few Images
Gyumin Shim, Jaeseong Lee, Junha Hyung, Jaegul Choo
arXiv preprint (arXiv:2307.09070)
Awards, Fellowships, & Grants
- Google Cloud Award, Google, 2023
- Kakao Research Grant, Kakao, 2023
- Qualcomm-KAIST Kaggle 1st Prize, Qualcomm, 2020
- KAIST Dean’s List, KAIST, 2019
Teaching Experience
- KAIST, Generative Models — Teaching Assistant, Fall 2023
- SK, Deep Learning — Instructor, Spring 2023
- SK, CVPR review — Instructor, Spring 2023
- MNC, Deep Learning — Instructor, Fall 2023
- FastCampus, 3D Deep Learning — Instructor, Fall 2022
Contact
sharpeeee [at] kaist.ac.kr