From 0564cf4278d73c436bef3d52551986d6fbf5cefb Mon Sep 17 00:00:00 2001 From: csyufei <103623103+csyufei@users.noreply.github.com> Date: Sat, 11 Jan 2025 13:13:36 +0800 Subject: [PATCH] Update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 082f743..70caddb 100644 --- a/README.md +++ b/README.md @@ -195,11 +195,11 @@ CS231n (斯坦福计算机视觉课程): [website](https://cs231n.stanford.edu/s * ViT (第一个将Transformer用在视觉领域): [bilibili](https://www.bilibili.com/video/BV15P4y137jb/?spm_id_from=333.1387.collection.video_card.click&vd_source=930ef08bfb2ff0db87ec20bf72a99855) * Swin Transformer (披着Transformer皮的CNN): [bilibili](https://www.bilibili.com/video/BV13L4y1475U/?spm_id_from=333.1387.collection.video_card.click&vd_source=930ef08bfb2ff0db87ec20bf72a99855) * 对比学习论文综述: [bilibili](https://www.bilibili.com/video/BV19S4y1M7hm/?spm_id_from=333.1387.collection.video_card.click&vd_source=930ef08bfb2ff0db87ec20bf72a99855) -* 以判别式AI为主的感知任务，比如识别、分类、分割、检测等等，看看即可，现在继续刷点意义不大 -* 生成式AI +* 以判别式模型为主的感知任务，比如识别、分类、分割、检测等等，看看即可，现在继续刷点意义不大 +* 生成式模型 * 自回归综述: [PDF](https://arxiv.org/pdf/2411.05902) * 扩散模型综述: [PDF](https://arxiv.org/pdf/2209.00796) - * 如果对扩散模型的理论推导感兴趣，可以看苏剑林老师的博客 - 生成扩散模型漫谈: [link](https://kexue.fm/archives/9119) + * 如果对扩散模型的理论推导感兴趣，可以看苏剑林老师的博客 - 生成扩散模型漫谈(推导非常清楚): [link](https://kexue.fm/archives/9119)