Yo'Chameleon: Personalized Vision and Language Generation

Thao Nguyen; Krishna Kumar Singh; Jing Shi; Trung Bui; Yong Jae Lee; Yuheng Li

doi:10.1109/cvpr52734.2025.01346

CVPR2025顶会

Yo'Chameleon: Personalized Vision and Language Generation

Thao Nguyen, Krishna Kumar Singh, Jing Shi, Trung Bui, Yong Jae Lee, Yuheng Li

DOI 出版方

2025年份

7顶会引用

摘要

https://thaoshibe.github.io/YoChameleon Figure 1 . Using only 3-5 images of a novel concept/subject, we personalize Large Multimodal Models (e.g., Chameleon [1]) so that they retain their original capabilities while enabling tailored language and vision generation for the novel concept.