<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>featured | Chunzheng Zhu</title><link>https://zhcz328.github.io/tag/featured/</link><atom:link href="https://zhcz328.github.io/tag/featured/index.xml" rel="self" type="application/rss+xml"/><description>featured</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Mon, 13 Jul 2026 00:00:00 +0000</lastBuildDate><image><url>https://zhcz328.github.io/media/icon_huc9fe9d140a9bb016fbeeaa3ba1111928_724048_512x512_fill_lanczos_center_3.png</url><title>featured</title><link>https://zhcz328.github.io/tag/featured/</link></image><item><title>The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy</title><link>https://zhcz328.github.io/publication/self-evolving-clinical-systems/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/self-evolving-clinical-systems/</guid><description>&lt;p>This survey reframes medical agents from the perspective of clinical deployment. It introduces a three-level autonomy taxonomy, organizes the field around framework, capability, and environment scaling, and highlights clinical self-evolution as a key frontier for trustworthy medical AI systems in real-world clinical practice.&lt;/p></description></item><item><title>MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution</title><link>https://zhcz328.github.io/publication/medsynapse-v/</link><pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/medsynapse-v/</guid><description>&lt;p>MedSynapse-V bridges visual perception and clinical intuition via latent diagnostic memory evolution for medical vision-language models.&lt;/p></description></item><item><title>When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models</title><link>https://zhcz328.github.io/publication/medcausalx/</link><pubDate>Tue, 24 Mar 2026 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/medcausalx/</guid><description>&lt;p>MedCausalX explicitly models causal reasoning chains in medical VLMs to reduce spurious correlations and improve trustworthy diagnosis.&lt;/p></description></item><item><title>MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis</title><link>https://zhcz328.github.io/publication/medeyes/</link><pubDate>Sat, 14 Mar 2026 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/medeyes/</guid><description>&lt;p>MedEyes dynamically models clinician-style diagnostic reasoning by progressively attending to and interpreting relevant medical image regions.&lt;/p></description></item><item><title>fMRI2GES: Co-Speech Gesture Reconstruction From fMRI Signal With Dual Brain Decoding Alignment</title><link>https://zhcz328.github.io/publication/fmri2ges/</link><pubDate>Fri, 04 Apr 2025 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/fmri2ges/</guid><description>&lt;p>fMRI2GES reconstructs expressive co-speech gestures directly from fMRI recordings by aligning dual fMRI-to-gesture reconstruction patterns.&lt;/p></description></item><item><title>Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis</title><link>https://zhcz328.github.io/publication/pathology-aware-prototype-evolution/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://zhcz328.github.io/publication/pathology-aware-prototype-evolution/</guid><description>&lt;p>This work integrates fine-grained pathological descriptions with visual prototypes to resolve semantic ambiguity in multicenter diabetic retinopathy grading.&lt;/p></description></item></channel></rss>