The KNU Vision & Learning (KVL) Lab, part of the Department of Artificial Intelligence at Kyungpook National University (KNU), was established in September 2019. Our primary focus is solving image-based deep learning challenges, including object recognition and detection, generative adversarial networks, video recognition, and more. We also explore vision transformers (ViT), self-supervised learning, AutoML, domain adaptation, and lifelong learning. Additionally, we are interested in generative AI models such as large language models (LLMs), large multimodal models (LMMs), diffusion models, and GANs. However, our research topics are not limited to these areas—we continuously explore new and intriguing topics related to deep learning and computer vision.
이름에 Vision 이 들어가 있다고 우리랩은 컴퓨터 비전만 하지 않습니다. 최근에는 AI 신뢰성, 안전성, 딥페이크, 생성형 AI의 Hallucination 문제 해결, 메타인지 등 AI 관련하여 다양한 연구를 하고 있습니다. 또한, 이와 관련하여 NeurIPS, AAAI, EMNLP, EACL, ACCV 등 AI 우수 학회 성과들을 보유하고 있고, 2025년에는 AGI 개발을 위한 사업을 수주하여 5년간 KAIST, 연세대, 고려대 등과 함께 공동연구를 수행하고 있습니다. 졸업생 및 재학생들 일부는 현재 국립대 교수, 삼성전자, SK 실트론, 한국가스공사, DGIST, 스타트업 등에서 근무하고 있습니다. 본 연구실에서는 석박사통합과정 또는 박사과정을 모집중 (석사 only X) 이니 이메일 (heechul@knu.ac.kr) 로 연락 바랍니다. (참고로 교수님 성격도 괜찮습니다.)
We are currently recruiting students for the Integrated M.S./Ph.D. program and the Ph.D. program only.
We are not accepting M.S.-only applicants at this time.
Our lab conducts cutting-edge AI research with the goal of submitting papers to top-tier AI conferences, including CVPR, ICCV, AAAI, NeurIPS, and ICML. For more details, please refer to our Publications page.
Our Lab provides GPU machines to all the members in order to train deep learning models. We have a DGX A100 server (8 A100 GPUs), 12 Quadro 8000 GPUs, and 12 Quadro A6000 GPUs, 8 Titan RTX GPUs.
Deep Learning-based Autonomous Driving using Camera Sensors.
Autonomous Surgery in Medical Area.
Fashion Recognition and Classification.
Anything You Want.