<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Xiaohui Xie - Professor of Computer Science on Xiaohui Xie's Site</title><link>https://xhx.github.io/</link><description>Recent content in Xiaohui Xie - Professor of Computer Science on Xiaohui Xie's Site</description><generator>Hugo -- 0.149.0</generator><language>en-us</language><lastBuildDate>Thu, 19 Dec 2024 00:00:00 +0000</lastBuildDate><atom:link href="https://xhx.github.io/index.xml" rel="self" type="application/rss+xml"/><item><title>Gauss-Newton Optimization</title><link>https://xhx.github.io/notes/ai/ml/gauss-newton/</link><pubDate>Thu, 19 Dec 2024 00:00:00 +0000</pubDate><guid>https://xhx.github.io/notes/ai/ml/gauss-newton/</guid><description>Gauss-Newton and second-order methods for deep learning</description></item><item><title>Hello World</title><link>https://xhx.github.io/posts/hello-world/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://xhx.github.io/posts/hello-world/</guid><description>Welcome to my new Hugo site with PaperMod theme</description></item><item><title>LSH Attention: Multiple Hyperplanes and Bucketing</title><link>https://xhx.github.io/notes/ai/ml/lsh-attention/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://xhx.github.io/notes/ai/ml/lsh-attention/</guid><description>Understanding how multiple random hyperplanes create better locality-sensitive hashing for attention mechanisms</description></item><item><title>My Post</title><link>https://xhx.github.io/posts/my-post/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://xhx.github.io/posts/my-post/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;Start your post here&amp;hellip;&lt;/p&gt;
&lt;h2 id="main-content"&gt;Main Content&lt;/h2&gt;
&lt;p&gt;Add your main content here&amp;hellip;&lt;/p&gt;
&lt;h2 id="conclusion"&gt;Conclusion&lt;/h2&gt;
&lt;p&gt;Wrap up your thoughts here&amp;hellip;&lt;/p&gt;</description></item><item><title>Self-Attention Approximation Methods</title><link>https://xhx.github.io/notes/ai/ml/self-attention-approx/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://xhx.github.io/notes/ai/ml/self-attention-approx/</guid><description>Efficient attention mechanisms including kernelization, low-rank approximations, and structured sparsity</description></item></channel></rss>