Multimodal Models
Focus on joint understanding and generation of images, text, audio, and more. From vision-language models to video understanding, we document cutting-edge attempts at cross-modal alignment.
아직 공개된 연구 노트가 없습니다.
Focus on joint understanding and generation of images, text, audio, and more. From vision-language models to video understanding, we document cutting-edge attempts at cross-modal alignment.
아직 공개된 연구 노트가 없습니다.