<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Representation Learning | Feiying Chen</title><link>https://cfy2yue.github.io/tags/representation-learning/</link><atom:link href="https://cfy2yue.github.io/tags/representation-learning/index.xml" rel="self" type="application/rss+xml"/><description>Representation Learning</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 01 Jan 2026 00:00:00 +0000</lastBuildDate><image><url>https://cfy2yue.github.io/media/icon_hu_1c0e9cb08cfb822a.png</url><title>Representation Learning</title><link>https://cfy2yue.github.io/tags/representation-learning/</link></image><item><title>BiEvo: From autoregression to bidirectional genomic representations with MNTP and architectural symmetrization</title><link>https://cfy2yue.github.io/publications/bievo/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://cfy2yue.github.io/publications/bievo/</guid><description>&lt;p&gt;&lt;strong&gt;Citation.&lt;/strong&gt; &lt;strong&gt;Feiying Chen&lt;/strong&gt; et al. BiEvo: From autoregression to bidirectional genomic representations with MNTP and architectural symmetrization. Ongoing manuscript.&lt;/p&gt;
&lt;p&gt;This project studies bidirectional genomic representation learning, using objective and architecture changes to improve how sequence models encode biological context. It is listed as ongoing rather than under review.&lt;/p&gt;</description></item></channel></rss>