Kinam Kim

M.S./PH.D Integrated Student

Artificial Intelligence, KAIST

Google Scholar | Github | CV

I'm a M.S./PH.D Integrated student at Kim Jaechul Graduate School of AI, KAIST, advised by professor Jaegul Choo.

I am deeply interested in AI research, particularly in Video Diffusion Models and Vision-Language-Action (VLA) models. With experience in Generative Video Models and Robotics, I aim to contribute to the advancement of real-world applicability through innovative AI technologies.

Contact

kinamplify [at] kaist.ac.kr

Education

M.S. Student/PH.D Integrated in Artificial Intelligence

Mar. 2025 - Present

Korea Advanced Institute of Science and Technology (KAIST)

Advisor: Prof. Jaegul Choo
B.S. in School of Computing

Mar. 2019 - 2024

Korea Advanced Institute of Science and Technology (KAIST)

News

[Sep. 2025] TIC-FT paper accepted to NeurIPS 2025.
[Mar. 2025] STG paper accepted to CVPR 2025.

Publications

EgoX: Egocentric Video Generation from a Single Exocentric Video

Taewoong Kang*, Kinam Kim*, Dohyeon Kim*, Jaegul Choo

under review

[ paper ] [ project page ]
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

[ paper ] [ project page ]
Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models

Kinam Kim*, Junha Hyung*, Jaegul Choo (* equal contribution)

The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

[ paper ] [ project page ]
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Junha Hyung*, Kinam Kim*, Susung Hong, Min-Jung Kim, Jaegul Choo (* equal contribution)

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[ paper ] [ project page ]
Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models

Sungwon Hwang*, Hyojin Jang*, Kinam Kim, Minho Park, Jaegul Choo (* equal contribution)

arXiv preprint, 2025

[ paper ] [ project page ]
Overcoming Camera-Facing Gaze Bias in EG3D Scene Generation

Kinam Kim, Juhyun Lee, Youngdo Lee

arXiv preprint, 2023

[ paper ] [ project page ]

Work Experience

KAIST DAVIAN Lab, Daejeon, South Korea
Undergraduate Research Intern (Aug. 2023 - Mar. 2025)
ThetaOne Korea, Seoul, South Korea
Natural Language Processing AI Developer (Jun. 2023 - Dec. 2023)
KAIST SiiT Lab, Daejeon, South Korea
Undergraduate Research Intern (Jun. 2020 - Dec. 2020)