👩‍💻 MVL Lab 

In Machine learning, Vision & Language lab, we are interested in Machine Learning and applications to Computer Vision and Language Processing. Specifically, we work on Deep Learning, Multimodal Learning, and Generative Models and our research topics include (but not limited to) text-to-image/video generation, multi-modal conversational models, embodied AI, and video understanding and question answering.

🔥 Announcements

We are looking for self-motivated and curiosity-driven graduate students and undergraduate interns to join our group. If you are interested, please send an email to Prof. Taehwan Kim (✉ taehwankim@unist.ac.kr) with your CV and transcript. We also strongly encourage you to apply for an internship before applying for graduate school to make sure we are a good fit to each other. 

📰 Recent News

• [2024.07] One paper is accepted in ECCV 2024 [New]

• [2024.06] One paper is accepted in CVPR 2024 Workshop (Embodied AI) [New]

• [2024.03] Yongsik Jo has been selected for the CMU AI Intensive Program, supported by Carnegie Mellon University and the IITP! [New]

• [2024.02] One paper is accepted in CVPR 2024 [New]

• [2023.10] One paper is accepted in Findings of EMNLP 2023

• [2023.08] One paper is accepted in CIKM 2023 (short paper)

• [2023.07] One paper is accepted in ICCV 2023

• [2023.03] Wonjin Yang has been selected for the CMU AI Intensive Program, supported by Carnegie Mellon University and the IITP! 

• [2022.10] One paper is accepted in NeurIPS 2022 Workshop (MLPS)

• [2022.06] We won the 2nd place in LOVEU challenge held in CVPR 2022