👨👩👧👦
Members
Current Members
Alumni
About me
I am an Associate Professor at the School of Computing, KAIST, Daejeon, Korea since 2025. Prior to KAIST, I joined Dept. of Elec. Eng. (adjunct with Grad. school of AI and Dept. of Creative IT Eng.), POSTECH, Korea as an Assistant Professor in 2020 and was appointed as an Associate Professor since 2023. I was also jointly affiliated with OpenLab, POSCO-RIST, Pohang, Korea from 2021 to 2023 as Research Director.
I received the B.E. degree (Valedictorian of the class) in Computer Engineering from Kwang-Woon University, South Korea in '10, and the M.S. and Ph.D. degrees in Electrical Engineering from KAIST, South Korea in '12 and '17, respectively.
Tae-Hyun Oh, Ph.D.
Professor
Youngmi Jin
Research Professor
Jungjoon Park
Postdoc Fellow
Compositionality in ML
Self-supervised Learning
3D/4D Human understanding
Embodied AI
Chengxin Liu
Postdoc Fellow
Visual Perception
Data-efficient Learning
Multi-modal Learning
Junuk Cha
Postdoc Fellow
3D Human & Scene Interaction
3D Human Reconstruction
3D Human Motion
Nam Hyeon-Woo
Ph.D. Student
Machine Learning
XAI
Automatic Evaluation
Moon Ye-Bin
Ph.D. Student
Multi-modal Learning
Agent System
Kwon Byung-Ki
Ph.D. Student
Synthetic Data Generation
Meta Learning
Motion Understanding
LiDAR
Kim Youwang
Kim Youwang
Joint M.S. & Ph.D.
Digital Twins
World Models
Generative Models
Kim Sung-Bin
Ph.D. Student
Multi-modal Learning
Generative Models
I'm currently a joint MS & PhD Student at AMI Lab @ EE, POSTECH. My reseatch lies in 3D machine perception including, 3D Reconstruction, Neural rendering, and Computational Photography, but not limited to.
Kim Jun-Seong
Joint M.S. & Ph.D.
3D Reconstruction
Kim Ji-Yeon
Joint M.S. & Ph.D.
3D Mesh Reconstruction
3D Human & Scene Interaction
Hyunwoo Ha
Ph.D. Student
Embodied AI
Kim Yu-Ji
Joint M.S. & Ph.D.
3D Scene Understanding
3D Reconstruction
Oh Hyun-Bin
Joint M.S. & Ph.D.
Multi-modal Learning
Audio-visual
Video Understanding
Motion Understanding
Wonjun Jo
Joint M.S. & Ph.D.
Self-supervised Learning
Multi-modal Learning
World Models
Embodied AI
I'm currently a Ph.D student at AMI Lab, KAIST. Please visit my personal page for more information.
GeonU Kim
Joint M.S. & Ph.D.
3D Reconstruction
Generative Models
Wonseok Choi
Joint M.S. & Ph.D.
Synthetic Data Generation
Data-efficient Learning
Meta Learning
Multi-modal Learning
Generative Models
Kyeongseon Ella Kim (Lab representative)
Ph.D. Student
Multi-modal Learning
Data Issues in Deep Learning
Hi! I am currently 1st-year Ph.D student at AMI Lab. I’m currently working on multimodal LLM, and data & model interpretation, but not limited to.
Visit My website!: https://mok0102.github.io/
Lee Jung-Mok
Ph.D. Student
Multi-modal Learning
Agent System
XAI
Hi, I am currently M.S. student in AMI Lab (KAIST). I’m currently working on multimodal LLM, and bayesian optimization using LLM, but not limited to.
Visit My website!: https://baekseongeun.github.io/
Baek Seong-Eun
Master Student
Video Understanding
Embodied AI
Multi-modal Learning
Kim Ohn
Master Student
3D Scene Understanding
Embodied AI
Joohyun Chang
Master Student
Multi-modal Learning
Video Understanding
Audio-visual
Jin-Woo Kong
Master Student
3D Reconstruction
3D Scene Understanding
Neural Rendering
Minsung Kim
Master Student
Multi-modal Learning
Synthetic Data Generation
Visual Perception
Kim Hyung-Min
Master Student
3D Human & Scene Interaction
3D Human Motion
Embodied AI
Hyeyeon Kim
Master Student
Multi-modal Learning
Audio-visual
3D Mesh Generation
3D Human & Scene Interaction
I am an M.S. student at KAIST's Advanced Machine Intelligence (AMI) Lab advised by Prof. Tae-Hyun Oh. I work on computer vision and multimodal learning with a focus on embodied AI. My interests span the perception-to-action stack, emphasizing 3D scene understanding and scene/task representations that support reliable long-horizon planning and execution.
Looking ahead, I aim to build human-like embodied systems that can generate high-level plans from instructions and perception, acquire new atomic skills, refine them at the action level from both observation and interaction using multimodal perceptual signals, and hierarchically compose these skills to execute the plans.
For more information:
Yohan Park
Master Student
3D Scene Understanding
Vision-Language Planning
Policy Learning
Agent System
Jiyeon Son
Master Student
Multi-modal Learning
Generative Models
Audio-visual
Agent System
Yejin Yeo
Master Student
Multi-modal Learning
Agent System
Song Seung-Ah
Staff Assistant
Seongok Lee
Staff Assistant