心有所向，日复一日，必有精进

摘要： Pre title: SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis accepted: arXiv 2023 paper: https://arxiv.org/abs/2307.01952 co 阅读全文

摘要： prologue 今天看代码在想 torch.unbind + torch.cat 与 torch.reshape 的区别，直观上来看reshape似乎更便利。 chatgpt 问题 x is a tensor of three dimension, what is the difference b 阅读全文

摘要： ## Pre title: Handwriting Transformers accepted: ICCV 2021 paper: https://arxiv.org/abs/2104.03964 code: https://github.com/ankanbhunia/Handwriting-Tr 阅读全文

摘要： Pre title: Neural Transformation Fields for Arbitrary-Styled Font Generation accepted: CVPR 2023 paper: https://openaccess.thecvf.com/content/CVPR2023 阅读全文

摘要： Pre 之前618从pdd上买了配件，第一次尝试自己组装了电脑，本意是作为炼丹炉，不过毕竟是自己的电脑不像服务器可以一天到晚打黑工，还是用来开发就好，测测代码跑跑ai。 没显示器——远程连接（后来还是买了，而且今天才发现买的那款大降价，唉），没键鼠——远程连接，没网络——二手路由刷openwrt去中 阅读全文

摘要： 1. Pre title: CF-Font: Content Fusion for Few-shot Font Generation accepted: CVPR2023 paper: https://arxiv.org/abs/2303.14017 | https://openaccess.the 阅读全文

摘要： ## Pre title: A Closer Look at Self-supervised Lightweight Vision Transformers accepted: ICML 2023 paper: https://arxiv.org/abs/2205.14443 code: https 阅读全文

摘要： ## Pre title: Hard Patches Mining for Masked Image Modeling accepted: CVPR 2023 paper: https://arxiv.org/abs/2304.05919 code: https://github.com/Haoch 阅读全文

摘要： ## Pre title: DropKey accepted: CVPR 2023 paper: https://arxiv.org/abs/2208.02646 code: in paper 关键词： Transformer, dropout, 阅读理由： 方法简单通用，效果又好像很好，（组会） 阅读全文

摘要： ## Pre title: MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis accepted: CVPR2023 paper: https://arxiv.org/abs/221 阅读全文