<?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>Transformers on Thomas van Dongen</title><link>https://thomasvandongen.dev/tags/transformers/</link><description>Recent content in Transformers on Thomas van Dongen</description><image><title>Thomas van Dongen</title><url>https://thomasvandongen.dev/avatar.png</url><link>https://thomasvandongen.dev/avatar.png</link></image><generator>Hugo -- 0.154.5</generator><language>en-us</language><lastBuildDate>Mon, 07 Nov 2022 00:00:00 +0000</lastBuildDate><atom:link href="https://thomasvandongen.dev/tags/transformers/index.xml" rel="self" type="application/rss+xml"/><item><title>Demystifying Efficient Self-Attention</title><link>https://thomasvandongen.dev/blog/efficient-self-attention/</link><pubDate>Mon, 07 Nov 2022 00:00:00 +0000</pubDate><guid>https://thomasvandongen.dev/blog/efficient-self-attention/</guid><description>A practical overview of efficient attention mechanisms that tackle the quadratic scaling problem.</description></item><item><title>Overcoming Input Length Constraints of Transformers</title><link>https://thomasvandongen.dev/blog/overcoming-input-length-constraints/</link><pubDate>Tue, 14 Dec 2021 00:00:00 +0000</pubDate><guid>https://thomasvandongen.dev/blog/overcoming-input-length-constraints/</guid><description>Using extractive summarization to train Transformers on long documents efficiently.</description></item></channel></rss>