Machine Learning & Vision Lab

Machine Learning & Vision Lab

Machine Learning and Vision Lab (MLV) led by Hyunwoo J. Kim at Korea Advanced Institute of Science & Technology (KAIST) started in February 2025. Prior to the position, he led his lab at Korea University. Earlier in his career, he worked at Amazon Lab126 in Sunnyvale California. In 2017, he earned the Ph.D. in the Department of Computer Sciences at the University of Wisconsin-Madison (Ph.D. minor: statistics) under the supervision of Dr. Vikas Singh. In 2013, he completed his internship in the Machine Learning Analytics Team at Amazon in Seattle Washington. 

The Machine Learning and Vision Lab (MLV) tackles fundamental open problems in machine learning and computer vision to advance toward artificial general intelligence (AGI) capable of handling any complex tasks. One key focus is advancing high-level visual perception, including  video foundation models, video question answering, and video-language models. Another focus is accelerating scientific discovery by understanding and generating multimodal scientific data (e.g., molecules, weather patterns), leading to generalization of models on non-Euclidean spaces, such as manifolds and graphs. We develop efficient and scalable solutions to process real-world visual data at scale, as well as in resource-limited environments. 

Our lab actively publishes at leading AI venues, including CVPR, ICCV, ECCV, NeurIPS, and ICML.

We have openings for postdoctoral researcher (박사후 연구원), graduate students (대학원 지원), and undergraduate interns (학부인턴). If interested, email us.


News

Supports & Collaborators