
Jongha Kim
M.S & Ph.D Integrated Student in MLV Lab, advised by Prof. Hyunwoo J. Kim.
Department of Computer Science and Engineering at Korea University, Seoul, Republic of Korea.
My goal is to develop personalized and reliable multimodal AI agents. My research focuses on personalizing Multimodal Large Language Models, exploring post-training methods (e.g., DPO), systems (e.g., RAG), and ways to leverage structured representations to complement these models to achieve the goal. For more information, please see my CV.
If you are interested in collaboration or have opportunities that align with my expertise, please feel free to reach out to me via contact email.
selected publications [full list]
(*) denotes equal contribution- MICCAI WorkshopConcept Bottleneck with Visual Concept Filtering for Explainable Medical Image ClassificationIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2023 Workshop)
- ECCV WorkshopObject Detection in Aerial Images with Uncertainty-Aware Graph NetworkIn European Conference on Computer Vision (ECCV 2022 Workshop)
- Under ReviewRelevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question AnsweringIn Under Review