タグ #Vision-Language Model に関するスライド

slide-thumbnail

【DL輪読会】VisionZip: Longer is Better but Not Necessary in Vision Language Models [S. Yang+CVPR'25]
user-img Deep Learning JP 1.6K
slide-thumbnail

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
user-img Deep Learning JP 4.3K
slide-thumbnail

論文紹介：Iterated Learning Improves Compositionality in Large Vision-Language Models (CVPR2024)
user-img 品川政太朗 22.9K
slide-thumbnail

【DL輪読会】MoAI: Mixture ofAll Intelligence for Large Language andVision Models
user-img Deep Learning JP 4.3K
#Vision-Language Model