BriefGPT.xyz
Aug, 2022
LogicRank: 逻辑诱导的生成式文本到图像系统重排序
LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems
HTML
PDF
Björn Deiseroth, Patrick Schramowski, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting
TL;DR
本研究介绍了当前文本生成图像模型的问题并提出了使用神经符号推理框架LogicRank，以更精确的方式对当前存在的一些问题进行重新排序以便在理性化情境中的使用。
Abstract
text-to-image models
have recently achieved remarkable success with seemingly accurate samples in photo-realistic quality. However as state-of-the-art
language models
still struggle evaluating precise statements
→