<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Contrastive Learning | A Quest After Perspectives</title><link>https://iphysresearch.github.io/blog/tag/contrastive-learning/</link><atom:link href="https://iphysresearch.github.io/blog/tag/contrastive-learning/index.xml" rel="self" type="application/rss+xml"/><description>Contrastive Learning</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 15 Apr 2026 00:00:00 +0000</lastBuildDate><image><url>https://iphysresearch.github.io/blog/media/sharing.png</url><title>Contrastive Learning</title><link>https://iphysresearch.github.io/blog/tag/contrastive-learning/</link></image><item><title>Robust parameter inference for Taiji via time-frequency contrastive learning and normalizing flows</title><link>https://iphysresearch.github.io/blog/mypublication/2026_taiji_robust_inference/</link><pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate><guid>https://iphysresearch.github.io/blog/mypublication/2026_taiji_robust_inference/</guid><description>&lt;p>The framework studies inference under transient contamination and compares alternative encoders and training objectives. Its evaluation supplements coverage checks with a distributional scoring rule.&lt;/p>
&lt;h2 id="sources">Sources&lt;/h2>
&lt;ul>
&lt;li>&lt;a href="https://arxiv.org/abs/2604.13867" target="_blank" rel="noopener">arXiv abstract and submission history&lt;/a>&lt;/li>
&lt;/ul></description></item></channel></rss>