<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Reward Modeling | Sohyun An</title><link>https://cownowan.github.io/tag/reward-modeling/</link><atom:link href="https://cownowan.github.io/tag/reward-modeling/index.xml" rel="self" type="application/rss+xml"/><description>Reward Modeling</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 30 Jun 2026 00:00:00 +0000</lastBuildDate><image><url>https://cownowan.github.io/media/icon_hu21a84279b79fe6bccfeffab7e390148e_110081_512x512_fill_lanczos_center_3.png</url><title>Reward Modeling</title><link>https://cownowan.github.io/tag/reward-modeling/</link></image><item><title>Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist</title><link>https://cownowan.github.io/publication/ban2026arenat2ihardbenchmarkingimproving/</link><pubDate>Tue, 30 Jun 2026 00:00:00 +0000</pubDate><guid>https://cownowan.github.io/publication/ban2026arenat2ihardbenchmarkingimproving/</guid><description/></item></channel></rss>