SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs. (arXiv:2306.17842v2 [cs.CV] UPDATED) Show more
http://arxiv.org/abs/2306.17842 #arXiv #NLProc
CleverLibre Social is an inclusive social instance for open discussion, learning, and community. All cultures welcome. Hate speech and harassment strictly forbidden.