MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models
Paper
•
2410.09733
•
Published
•
8
Yunlong Tang
yunlong10
·
AI & ML interests
Multimodal Learning, Video Understanding & Generation
Recent Activity
authored
a paper
about 1 month ago
Caption Anything: Interactive Image Description with Diverse Multimodal
Controls
authored
a paper
about 1 month ago
Video Understanding with Large Language Models: A Survey
authored
a paper
about 1 month ago
Emo-Avatar: Efficient Monocular Video Style Avatar through Texture
Rendering
Organizations
None yet