一篇题为《FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders》的论文已在 Hugging Face 论文页面发布。
论文标题指出,正则化层融合可以缓解表征自编码器中的重建-生成差距。
![]()
该论文发布在 Hugging Face 的论文页面上,页面显示有 1,966 次浏览。
特别声明:以上内容(如有图片或视频亦包括在内)为自媒体平台“网易号”用户上传并发布,本平台仅提供信息存储服务。
Notice: The content above (including the pictures and videos if any) is uploaded and posted by a user of NetEase Hao, which is a social media platform and only provides information storage services.