<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Yu Zhu</title><link>https://zeheru.github.io/yuzhu-academic-cv/</link><atom:link href="https://zeheru.github.io/yuzhu-academic-cv/index.xml" rel="self" type="application/rss+xml"/><description>Yu Zhu</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 04 Apr 2026 00:00:00 +0000</lastBuildDate><image><url>https://zeheru.github.io/yuzhu-academic-cv/media/icon_hu_1c0e9cb08cfb822a.png</url><title>Yu Zhu</title><link>https://zeheru.github.io/yuzhu-academic-cv/</link></image><item><title>KappaFormer: Physics-aware Transformer for Lattice Thermal Conductivity via Cross-domain Transfer Learning</title><link>https://zeheru.github.io/yuzhu-academic-cv/publications/kappaformer/</link><pubDate>Sat, 04 Apr 2026 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/publications/kappaformer/</guid><description>&lt;p&gt;KappaFormer embeds a harmonic-anharmonic decomposition into its architecture
and transfers knowledge from large-scale elastic-property data to smaller
thermal-conductivity datasets.&lt;/p&gt;</description></item><item><title>MPBR: Multimodal Progressive Bidirectional Reasoning for Open-Set Fine-Grained Recognition</title><link>https://zeheru.github.io/yuzhu-academic-cv/publications/mpbr/</link><pubDate>Wed, 01 Oct 2025 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/publications/mpbr/</guid><description>&lt;p&gt;MPBR combines forward visual-feature refinement with backward multimodal
consistency constraints to improve recognition when unknown fine-grained
categories appear at inference time.&lt;/p&gt;</description></item><item><title>Reconstructing Pristine Molecular Orbitals from Scanning Tunneling Microscope Images via Artificial Intelligence Approaches</title><link>https://zeheru.github.io/yuzhu-academic-cv/publications/reconstructing-pristine-molecular-orbitals/</link><pubDate>Mon, 16 Jun 2025 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/publications/reconstructing-pristine-molecular-orbitals/</guid><description>&lt;p&gt;This work connects STM simulation, Tersoff-Hamann theory, Chen&amp;rsquo;s derivative
rule, and physics-driven image restoration. STM-Net separates molecular-orbital
signals from contributions introduced by CO-functionalized tips.&lt;/p&gt;</description></item><item><title>Probing the Limit of Heat Transfer in Inorganic Crystals with Deep Learning</title><link>https://zeheru.github.io/yuzhu-academic-cv/publications/probing-limit-heat-transfer/</link><pubDate>Fri, 14 Mar 2025 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/publications/probing-limit-heat-transfer/</guid><description>&lt;p&gt;The study combines deep learning, high-throughput structure exploration, and
density-functional-theory validation to map the thermal-conductivity landscape
of inorganic crystals.&lt;/p&gt;</description></item><item><title>MPBR for Open-Set Fine-Grained Recognition</title><link>https://zeheru.github.io/yuzhu-academic-cv/projects/mpbr/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/projects/mpbr/</guid><description>&lt;p&gt;MPBR explores recognition in open-world settings where unknown fine-grained
categories appear at inference time. The method combines forward refinement of
visual features with backward multimodal consistency constraints.&lt;/p&gt;
&lt;p&gt;My work included developing benchmark pipelines and evaluating leading
open-set-recognition models on iNat2021-OSR. Analysis used t-SNE, Grad-CAM,
Swin Transformer backbones, and HAN-OSFGR.&lt;/p&gt;</description></item><item><title>MatterSim: Materials Modeling Workflows</title><link>https://zeheru.github.io/yuzhu-academic-cv/projects/mattersim/</link><pubDate>Mon, 01 Jul 2024 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/projects/mattersim/</guid><description>&lt;p&gt;During an AI for Science internship at Microsoft Research, I contributed
benchmarks and computational workflows supporting materials-model development,
training-data generation, and property-prediction studies.&lt;/p&gt;
&lt;p&gt;The work involved high-throughput materials datasets, inference on models up to
1B parameters, and Azure pipelines supporting up to 10K concurrent tasks.
Tools included VASP, atomate2, joblib, phonopy, phono3py, ESEN, MACE, and ORB.&lt;/p&gt;</description></item><item><title>STM-Net: Reconstructing Molecular Orbitals from STM Images</title><link>https://zeheru.github.io/yuzhu-academic-cv/projects/stm-net/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/projects/stm-net/</guid><description>&lt;p&gt;In a nutshell: &lt;strong&gt;Are orbitals observable?&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;This project reconstructs pristine molecular-orbital information from
high-resolution scanning tunneling microscopy images. STM images are simulated
at the density-functional-theory level using Bardeen&amp;rsquo;s approximation, and
STM-Net separates s-wave molecular-orbital signals from p-wave contributions
introduced by CO-functionalized tips.&lt;/p&gt;
&lt;p&gt;The approach connects Tersoff-Hamann theory and Chen&amp;rsquo;s derivative rule with
physics-informed image restoration. Experiments included DAE, U-Net, and
Mask2Former-based models.&lt;/p&gt;</description></item><item><title>SERS Imaging for Fingerprint Identification</title><link>https://zeheru.github.io/yuzhu-academic-cv/projects/sers-fingerprint-imaging/</link><pubDate>Thu, 01 Apr 2021 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/projects/sers-fingerprint-imaging/</guid><description>&lt;p&gt;This project developed a surface-enhanced Raman scattering imaging approach for
fingerprint recognition and chemical mapping under varied surface and
environmental conditions.&lt;/p&gt;
&lt;p&gt;The work involved collecting fingerprint samples, performing SERS imaging, and
analyzing chemical maps for non-invasive identification of residues such as
drugs or nicotine.&lt;/p&gt;</description></item><item><title>Curriculum Vitae</title><link>https://zeheru.github.io/yuzhu-academic-cv/cv/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/cv/</guid><description>&lt;p&gt;The web version of my curriculum vitae is organized across the
,
, and
pages.&lt;/p&gt;
&lt;p&gt;
&lt;/p&gt;
&lt;p&gt;Academic profiles:
,
,
, and
.&lt;/p&gt;
&lt;p&gt;Other writing:
.&lt;/p&gt;</description></item><item><title>Experience</title><link>https://zeheru.github.io/yuzhu-academic-cv/experience/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://zeheru.github.io/yuzhu-academic-cv/experience/</guid><description/></item></channel></rss>