Welcome to Vision & AI Lab @ Korea University!

The Vision & AI (VAI) Lab at Korea University is dedicated to advancing next-generation AI technologies that integrate visual and linguistic understanding. Our research centers on computer vision and natural language processing, with a strong emphasis on multimodal learning and foundation models. We study the design and training of large-scale models, including large language models (LLMs) and vision-language models (VLMs), and develop intelligent systems that address challenging real-world problems. Our research is further expanding into autonomous driving, Vision-Language-Action (VLA), and robotics, with the ultimate goal of building embodied AI systems that can actively perceive, understand, and interact with the real world. In collaboration with leading universities, research institutes, and industry partners in Korea and worldwide, we strive to achieve impactful research outcomes through joint projects and academia-industry partnerships.

We are currently looking for undergraduate interns, master’s, and Ph.D. students. We welcome self-motivated students who enjoy identifying and solving problems independently. If you are interested, please contact Jungbeom (jbeomlee@korea.ac.kr) with your CV and transcript. We look forward to collaborating with you in our research journey!

Latest News

  • Our lab was awarded a grant through the Excellent Young Researcher Program, Type B (우수신진연구 유형 B)
  • Two papers were accepted at CVPR 2026, and one paper was accepted at CVPR 2026 Findings
  • Jungbeom gave an invited talk at Samsung Advanced Institute of Technology (SAIT, 삼성종합과학기술원)
  • A paper on fine-tuning text-to-image generative model was accepted at WACV 2026
  • A paper on vision-language model was accepted at ICCV 2025