Multimodal AI Lab

Multimodal AI Lab @ EWHA focuses on developing robust and generalizable AI models that understand and generate information across multiple modalities—vision, language, and audio. Our research spans multimodal generation, large audiovisual/vision-language models, video understanding, 3D perception, and cross-modal grounding. We build multimodal systems that learn with minimal supervision and perform reliably in diverse, real-world settings. We aim to push the boundaries of multimodal learning and create AGI that is creative, effective, and efficient.

Recruiting Undergraduate Interns/ Graduate Students: We are looking for undergraduate interns, and graduate students to research with! If you are interested in doing cool multimodal learning research, please send your CV and GPA to .

 

News