Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Menon, Nandakishore S"'
Our work aims to build a model that performs dual tasks of image captioning and image generation while being trained on only one task. The central idea is to train an invertible model that learns a one-to-one mapping between the image and text embedd
Externí odkaz:
http://arxiv.org/abs/2410.20171