<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>News &amp; Research Notes | Wenrui Fan</title><link>https://wenruifan.github.io/blog/</link><atom:link href="https://wenruifan.github.io/blog/index.xml" rel="self" type="application/rss+xml"/><description>News &amp; Research Notes</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 05 Aug 2026 12:00:00 +0100</lastBuildDate><image><url>https://wenruifan.github.io/media/icon_hu_75a089107c6a8eba.png</url><title>News &amp; Research Notes</title><link>https://wenruifan.github.io/blog/</link></image><item><title>Welcome to my research notes</title><link>https://wenruifan.github.io/blog/welcome-research-notes/</link><pubDate>Wed, 05 Aug 2026 12:00:00 +0100</pubDate><guid>https://wenruifan.github.io/blog/welcome-research-notes/</guid><description>&lt;p&gt;Welcome to my research notes. I will use this space to share project updates, practical lessons from building multimodal machine-learning systems, and reflections on reproducible AI research.&lt;/p&gt;
&lt;p&gt;My current interests include medical AI, multimodal representation learning, computer vision, foundation models, and AI for scientific discovery. Publications and longer-term work are collected on the
and
pages.&lt;/p&gt;</description></item><item><title>Foundation models for data-scarce neuropathic pain research</title><link>https://wenruifan.github.io/blog/foundation-models-neuropathic-pain/</link><pubDate>Mon, 03 Mar 2025 12:00:00 +0000</pubDate><guid>https://wenruifan.github.io/blog/foundation-models-neuropathic-pain/</guid><description>&lt;p&gt;Neuropathic pain is difficult to treat, and data scarcity makes it challenging to train high-capacity models for drug-response prediction. Our work studies how foundation models can transfer knowledge from larger, pain-agnostic datasets into small, pain-specific neuroimaging cohorts.&lt;/p&gt;
&lt;p&gt;The resulting framework combines multimodal information within the target cohort with representations learned from external fMRI data. The paper is available on
.&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>CardioVAE released</title><link>https://wenruifan.github.io/blog/2024-cardiovae/</link><pubDate>Wed, 20 Mar 2024 12:00:00 +0000</pubDate><guid>https://wenruifan.github.io/blog/2024-cardiovae/</guid><description>&lt;p&gt;
, our multimodal approach to low-cost cardiac hemodynamics assessment, is available on arXiv.&lt;/p&gt;</description></item><item><title>MeDSLIP released</title><link>https://wenruifan.github.io/blog/2024-medslip/</link><pubDate>Fri, 15 Mar 2024 12:00:00 +0000</pubDate><guid>https://wenruifan.github.io/blog/2024-medslip/</guid><description>&lt;p&gt;We released
, a dual-stream vision-language pre-training framework for fine-grained medical image-text alignment.&lt;/p&gt;</description></item><item><title>Joined Sheffield AIRE</title><link>https://wenruifan.github.io/blog/2023-joined-aire/</link><pubDate>Mon, 04 Sep 2023 12:00:00 +0100</pubDate><guid>https://wenruifan.github.io/blog/2023-joined-aire/</guid><description>&lt;p&gt;I joined the University of Sheffield&amp;rsquo;s
as an AI Research Engineer.&lt;/p&gt;</description></item></channel></rss>