Innocore 2026 Postdoctoral Recruitment

Submisison deadline : ~April 21st (or until the position is filled)

We are looking for postdoctoral researchers to join the KAIST Computer Vision and Learning Lab (KCVL), led by Prof. Tae-Kyun (T-K) Kim, starting around May 2026, through the InnoCORE Fellowship Program 2026.

Our group works at the intersection of Physical AI, Generative AI, and World Models, building video and 3D generative systems that understand and simulate the physical world.

🔬 Research Scope

Candidates with independent research directions aligned with the lab's vision are also welcome.


🎯 Who we are looking for

💻 Compute

💰 What we offer

📩 Send your CV and Google Scholar link to: kimtaekyun@kaist.ac.kr Lab: https://sites.google.com/view/tkkim/home




Open positions: PhD students and Postdocs in Computer Vision and Machine Learning

We are always looking for strong candidates for PhD and postdoc positions. Topics include (not limited to) 6D object/hand pose estimation, 3D object detection and tracking, GANs, data augmentation, 2D/3D face, deep reinforcement learning, robotics. Applicants should have a first-class degree and a strong track record in CVPR/ICCV/ECCV, NIPS/ICML/ICLR, or PAMI/IJCV/TIP. Candidates who are able to carry highest quality research independently are pursued. If you are interested, please send me an email at kimtaekyun@kaist.ac.kr titled ‘phd/postdoc application’, where you include your CV and indicate the earliest starting date.


call for internships

Application deadline: 30 July 2024

Internship period: summer only, summer/fall, fall/winter, winter only 2024


The computer vision and learning lab at KAIST (SoC) is recruiting multiple student interns on broad topics of computer vision and deep learning. 

The successful candidates will work with other lab members on projects of pose estimation, motion tracking, object detection/segmentation, Gaussian splatting, motion generation, reinforcement learning, agent learning. 

The projects will exploit a given set of training and testing data, and focus on evaluating SOTAs and novel ideas to improve their performances. 


Please send me an email at kimtaekyun@kaist.ac.kr if you are interested, and feel free to forward this to anyone who might be interested.