<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>NLP | Ken Research Group</title><link>https://mospsyde-ntu.github.io/tags/nlp/</link><atom:link href="https://mospsyde-ntu.github.io/tags/nlp/index.xml" rel="self" type="application/rss+xml"/><description>NLP</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 11 Jan 2024 00:00:00 +0000</lastBuildDate><image><url>https://mospsyde-ntu.github.io/media/icon_hu_982c5d63a71b2961.png</url><title>NLP</title><link>https://mospsyde-ntu.github.io/tags/nlp/</link></image><item><title>Machine Learning</title><link>https://mospsyde-ntu.github.io/research/machine-learning/</link><pubDate>Thu, 11 Jan 2024 00:00:00 +0000</pubDate><guid>https://mospsyde-ntu.github.io/research/machine-learning/</guid><description>&lt;h2 id="overview"&gt;Overview&lt;/h2&gt;
&lt;p&gt;We build robust and interpretable ML models to accelerate scientific discovery across domains, with emphasis on generalization, uncertainty, and physical constraints.&lt;/p&gt;
&lt;h2 id="focus-areas"&gt;Focus Areas&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;Physics-informed neural networks (PINNs)&lt;/li&gt;
&lt;li&gt;Graph neural networks for structured scientific data&lt;/li&gt;
&lt;li&gt;Interpretable models and reliability assessment&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id="selected-publications"&gt;Selected Publications&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;See our recent work in Nature Machine Intelligence and NeurIPS.&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>