タグ #Vision-Language Model に関するスライド

slide-thumbnail

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
user-img Deep Learning JP 3.8K
slide-thumbnail

論文紹介：Iterated Learning Improves Compositionality in Large Vision-Language Models (CVPR2024)
user-img 品川政太朗 21.4K
slide-thumbnail

【DL輪読会】MoAI: Mixture ofAll Intelligence for Large Language andVision Models
user-img Deep Learning JP 4.1K
#Vision-Language Model
#CVPR2024
#Compositionality
#Iterated Learning
#CLIP