Linear Spaces of Meanings: Compositional Structures in Vision-Language Models
Author:
Trager Matthew1,
Perera Pramuditha1,
Zancato Luca1,
Achille Alessandro1,
Bhatia Parminder1,
Soatto Stefano1
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. TIAM - A Metric for Evaluating Alignment in Text-to-Image Generation;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03