MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens.

Kaizhi Zheng Xuehai He Xin Eric Wang

Published in: CoRR (2023)

Keyphrases

language generation
computer vision
vision system
generative model
real time
unsupervised learning
information systems
computational vision
data sets
discriminative learning
visual perception
data driven
image processing
text classification
high level
machine learning
visually guided