优化GFlowNets以实现文本到图像的扩散对齐
原文英文，约200词，阅读约需1分钟。发表于：。This paper was accepted at the Foundation Models in the Wild workshop at ICML 2024. Diffusion models have become the de-facto approach for generating visual data, which are trained to match the...
介绍了Diffusion Alignment with GFlowNet (DAG)算法，用于训练生成式流网络模型。该算法通过黑盒属性函数对扩散模型进行后训练，生成高奖励图像。实验证明，该方法能有效将文本到图像扩散模型与奖励信息对齐。
