<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Foundation Models | Wenrui Fan</title><link>https://wenruifan.github.io/tags/foundation-models/</link><atom:link href="https://wenruifan.github.io/tags/foundation-models/index.xml" rel="self" type="application/rss+xml"/><description>Foundation Models</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 01 Sep 2025 00:00:00 +0000</lastBuildDate><image><url>https://wenruifan.github.io/media/icon_hu_75a089107c6a8eba.png</url><title>Foundation Models</title><link>https://wenruifan.github.io/tags/foundation-models/</link></image><item><title>Foundation-model-boosted multimodal learning for fMRI-based neuropathic pain drug response prediction</title><link>https://wenruifan.github.io/publications/foundation-model-neuropathic-pain/</link><pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate><guid>https://wenruifan.github.io/publications/foundation-model-neuropathic-pain/</guid><description>&lt;p&gt;We study how foundation models can transfer knowledge from larger, pain-agnostic datasets into small, pain-specific neuroimaging cohorts for drug-response prediction.&lt;/p&gt;</description></item><item><title>Foundation-model multimodal learning paper available</title><link>https://wenruifan.github.io/blog/2025-foundation-model-paper/</link><pubDate>Mon, 03 Mar 2025 12:00:00 +0000</pubDate><guid>https://wenruifan.github.io/blog/2025-foundation-model-paper/</guid><description>&lt;p&gt;Our work on
is available on arXiv.&lt;/p&gt;</description></item><item><title>Foundation Models for Neuropathic Pain</title><link>https://wenruifan.github.io/projects/neuropathic-pain/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://wenruifan.github.io/projects/neuropathic-pain/</guid><description>&lt;p&gt;Neuropathic pain is difficult to treat, while therapeutic response varies substantially across patients. This project combines foundation models and multimodal representation learning to make better use of small neuroimaging cohorts and predict response to treatment.&lt;/p&gt;</description></item></channel></rss>