https://zhonglifr.github.io//publications/

1<!doctype html><html lang="en" class="no-js"><head><meta charset="utf-8"> <!-- begin SEO --><title>Publications - Zhong Li / Homepage</title><meta property="og:locale" content="en-US"><meta property="og:site_name" content="Zhong Li / Homepage"><meta property="og:title" content="Publications"><link rel="canonical" href="https://zhonglifr.github.io//publications/"><meta property="og:url" content="https://zhonglifr.github.io//publications/"> 

1<script type="application/ld+json"> { "@context" : "http://schema.org", "@type" : "Person", "name" : "Your Name", "url" : "https://zhonglifr.github.io/", "sameAs" : null } </script>

1 <!-- end SEO --><link href="https://zhonglifr.github.io//feed.xml" type="application/atom+xml" rel="alternate" title="Zhong Li / Homepage Feed"> <!-- http://t.co/dKP3o1e --><meta name="HandheldFriendly" content="True"><meta name="MobileOptimized" content="320"><meta name="viewport" content="width=device-width, initial-scale=1.0"> 

1<script> document.documentElement.className = document.documentElement.className.replace(/\bno-js\b/g, '') + ' js '; </script>

1 <!-- For all browsers --><link rel="stylesheet" href="https://zhonglifr.github.io//assets/css/main.css"><meta http-equiv="cleartype" content="on"> <!-- start custom head snippets --><link rel="apple-touch-icon" sizes="57x57" href="https://zhonglifr.github.io//images/apple-touch-icon-57x57.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="60x60" href="https://zhonglifr.github.io//images/apple-touch-icon-60x60.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="72x72" href="https://zhonglifr.github.io//images/apple-touch-icon-72x72.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="76x76" href="https://zhonglifr.github.io//images/apple-touch-icon-76x76.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="114x114" href="https://zhonglifr.github.io//images/apple-touch-icon-114x114.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="120x120" href="https://zhonglifr.github.io//images/apple-touch-icon-120x120.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="144x144" href="https://zhonglifr.github.io//images/apple-touch-icon-144x144.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="152x152" href="https://zhonglifr.github.io//images/apple-touch-icon-152x152.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="180x180" href="https://zhonglifr.github.io//images/apple-touch-icon-180x180.png?v=M44lzPylqQ"><link rel="icon" type="image/png" href="https://zhonglifr.github.io//images/favicon-32x32.png?v=M44lzPylqQ" sizes="32x32"><link rel="icon" type="image/png" href="https://zhonglifr.github.io//images/android-chrome-192x192.png?v=M44lzPylqQ" sizes="192x192"><link rel="icon" type="image/png" href="https://zhonglifr.github.io//images/favicon-96x96.png?v=M44lzPylqQ" sizes="96x96"><link rel="icon" type="image/png" href="https://zhonglifr.github.io//images/favicon-16x16.png?v=M44lzPylqQ" sizes="16x16"><link rel="manifest" href="https://zhonglifr.github.io//images/manifest.json?v=M44lzPylqQ"><link rel="mask-icon" href="https://zhonglifr.github.io//images/safari-pinned-tab.svg?v=M44lzPylqQ" color="#000000"><link rel="shortcut icon" href="/images/favicon.ico?v=M44lzPylqQ"><meta name="msapplication-TileColor" content="#000000"><meta name="msapplication-TileImage" content="https://zhonglifr.github.io//images/mstile-144x144.png?v=M44lzPylqQ"><meta name="msapplication-config" content="https://zhonglifr.github.io//images/browserconfig.xml?v=M44lzPylqQ"><meta name="theme-color" content="#ffffff"><link rel="stylesheet" href="https://zhonglifr.github.io//assets/css/academicons.css"/> 

1<script type="text/x-mathjax-config"> MathJax.Hub.Config({ TeX: { equationNumbers: { autoNumber: "all" } } }); </script>

1 

1<script type="text/x-mathjax-config"> MathJax.Hub.Config({ tex2jax: { inlineMath: [ ['$','$'], ["\\(","\\)"] ], processEscapes: true } }); </script>

1 

1<script src='https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/latest.js?config=TeX-MML-AM_CHTML' async></script>

1 <!-- end custom head snippets --></head><body> <!--[if lt IE 9]><div class="notice--danger align-center" style="margin: 0;">You are using an <strong>outdated</strong> browser. Please <a href="http://browsehappy.com/">upgrade your browser</a> to improve your experience.</div><![endif]--><div class="masthead"><div class="masthead__inner-wrap"><div class="masthead__menu"><nav id="site-nav" class="greedy-nav"> <button><div class="navicon"></div></button><ul class="visible-links"><li class="masthead__menu-item masthead__menu-item--lg"><a href="https://zhonglifr.github.io//">Zhong Li / Homepage</a></li><li class="masthead__menu-item"><a href="https://zhonglifr.github.io//publications/">Publications</a></li><li class="masthead__menu-item"><a href="https://zhonglifr.github.io//cv/">CV</a></li><li class="masthead__menu-item"><a href="https://zhonglifr.github.io//teaching/">Teaching</a></li></ul><ul class="hidden-links hidden"></ul></nav></div></div></div><div id="main" role="main"><div class="sidebar sticky"><div itemscope itemtype="http://schema.org/Person"><div class="author__avatar"> <img src="https://zhonglifr.github.io//images/profile2019.png" class="author__avatar" alt="Zhong Li"></div><div class="author__content"><h3 class="author__name">Zhong Li</h3><p class="author__bio">Postdoc in AI for Math</p></div><div class="author__urls-wrapper"> <button class="btn btn--inverse">Follow</button><ul class="author__urls social-icons"><li><i class="fa fa-fw fa-map-marker" aria-hidden="true"></i> Leiden, the Netherlands</li><li><a href="mailto:[email protected]"><i class="fas fa-fw fa-envelope" aria-hidden="true"></i> Email</a></li><li><a href="https://www.researchgate.net/profile/Zhong-Li-44"><i class="fab fa-fw fa-researchgate" aria-hidden="true"></i> ResearchGate</a></li><li><a href="https://www.linkedin.com/in/https://www.linkedin.com/in/data-science-zhong-li/"><i class="fab fa-fw fa-linkedin" aria-hidden="true"></i> LinkedIn</a></li><li><a href="https://github.com/ZhongLIFR"><i class="fab fa-fw fa-github" aria-hidden="true"></i> Github</a></li><li><a href="https://scholar.google.com/citations?user=m5u8VlIAAAAJ&hl=en&oi=ao"><i class="fas fa-fw fa-graduation-cap"></i> Google Scholar</a></li><li><a href="https://orcid.org/0000-0003-1124-5778"><i class="ai ai-orcid-square ai-fw"></i> ORCID</a></li></ul></div></div></div><div class="archive"><h1 class="page__title">Publications</h1><p>You can also find my articles on my <u><a href="https://scholar.google.com/citations?user=m5u8VlIAAAAJ&amp;hl=en&amp;oi=ao">Google Scholar</a>.</u> My research can be summarised by the following keywords:</p><ul><li>Methodologies-Oriented: <em>Generative Models; Flow Matching; Diffusion Models; Unsupervised Machine Learning; Anomaly Detection; Transfer Learning; XAI; Graph Neural Networks</em></li><li>Applications-Oriented: <em>Log Analysis; Predictive Maintenance; Digital Twin; AI for Manufacturing</em></li></ul><h2 id="2026">2026</h2><ul><li><strong>MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling.</strong><ul><li><strong>Zhong Li</strong>, Qi Huang, Yuxuan Zhu, Mohammad Mohammadi Amiri, Niki van Stein, Thomas Bäck, Matthijs van Leeuwen, Zaiwen Wen, Lincen Yang. Under Review for an AI conference. “#” means equal contribution</li></ul></li><li><strong>OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling.</strong><ul><li><strong>Zhong Li</strong>, Zihan Guo, Xiaohan Lu, Juntao Wang, Jie Song, Chao Shen, Jiageng Wu, Mingyang Sun. Under Review for an AI conference. “#” means equal contribution</li></ul></li><li><strong>Latent Space Analaysis for Unsupervised Hyperparameter Optimisation.</strong><ul><li>Yuhang Wang #, <strong>Zhong Li #</strong>, Shujian Yu, Matthijs van Leeuwen. Under Review for an AI conference. “#” means equal contribution</li></ul></li><li><strong>Diffusion and Flow Matching Models for Tabular Data: A Survey.</strong><ul><li><strong>Zhong Li</strong>, Qi Huang, Lincen Yang*, Jiayang Shi, Zhao Yang, Niki van Stein, Thomas Bäck, Matthijs van Leeuwen. Under Review for TKDE. “*” means corresponding author</li><li><a href="https://arxiv.org/abs/2502.17119">[paper]</a>, <a href="https://github.com/Diffusion-Model-Leiden/awesome-diffusion-models-for-tabular-data">[code]</a></li></ul></li><li><strong>Explainable Graph Neural Networks under Fire.</strong><ul><li><strong>Zhong Li</strong>, Simon Geisler, Yuhang Wang, Stephan Günnemann, Matthijs van Leeuwen. Under Review for an AI conference.</li><li><a href="https://arxiv.org/abs/2406.06417">[paper]</a>, <a href="https://github.com/ZhongLIFR/GXAttack">[code]</a></li></ul></li><li><strong>Constructing Industrial-Scale Optimization Modeling Benchmark.</strong><ul><li><strong>Zhong Li</strong>, Hongliang Lu, Tao Wei, Yuxuan Chen, Wenyu Liu, Yuan Lan, Fan Zhang, Zaiwen Wen. ICML 2026.</li><li><a href="https://arxiv.org/abs/2602.10450">[paper]</a>, <a href="https://github.com/optsuite/MIPLIB-NL">[code]</a></li></ul></li></ul><h2 id="2025">2025</h2><ul><li><strong>Learning Subgroups with Maximum Treatment Effects without Causal Heuristics.</strong><ul><li>Lincen Yang, <strong>Zhong Li*</strong>, Matthijs van Leeuwen, Saber Salehkaleybar. AAAI 2026 Oral. “*” means corresponding author.</li><li><a href="https://arxiv.org/abs/2511.20189">[paper]</a>, <a href="https://github.com/ylincen/causal-subgroup">[code]</a></li></ul></li><li><strong>Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching.</strong><ul><li><strong>Zhong Li</strong>, Qi Huang, Yuxuan Zhu, Lincen Yang*, Mohammad Mohammadi Amiri, Niki van Stein, Matthijs van Leeuwen. NeurIPS 2025. “*” means corresponding author.</li><li><a href="https://arxiv.org/abs/2510.18328">[paper]</a>, <a href="https://github.com/ZhongLIFR/TCCM-NIPS">[code]</a></li></ul></li><li><strong>Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection.</strong><ul><li><strong>Zhong Li</strong>, Yuhang Wang, Matthijs van Leeuwen. Data Mining and Knowledge Discovery (DAMI). 39

1(44): 1-43. (AAAI 2026 Journal Track)</li><li><a href="https://link.springer.com/article/10.1007/s10618-025-01115-5">[paper]</a>, <a href="https://github.com/ZhongLIFR/AutoGAD2024">[code]</a></li></ul></li></ul><h2 id="2024">2024</h2><ul><li><strong>Graph Neural Networks based Log Anomaly Detection and Explanation.</strong><ul><li><strong>Zhong Li</strong>, Jiayang Shi, Matthijs van Leeuwen. ICSE’24 poster track.</li><li><a href="https://arxiv.org/abs/2307.00527">[paper]</a>, <a href="https://github.com/ZhongLIFR/Logs2Graph">[code]</a> (ArXiv full version)</li><li><a href="https://dl.acm.org/doi/pdf/10.1145/3639478.3643084">[paper]</a> (ICSE short version)</li></ul></li><li><strong>Cross-Domain Graph Level Anomaly Detection.</strong><ul><li><strong>Zhong Li</strong>, Sheng Liang, Jiayang Shi, Matthijs van Leeuwen. IEEE Transactions on Knowledge and Data Engineering (TKDE). 36(12):7839-7850</li><li><a href="https://ieeexplore.ieee.org/document/10684507/keywords#keywords">[paper]</a>, <a href="https://github.com/ZhongLIFR/ARMET/">[code]</a></li></ul></li></ul><h2 id="2023">2023</h2><ul><li><strong>A Survey on Explainable Anomaly Detection.</strong><ul><li><strong>Zhong Li</strong>, Yuxuan Zhu, Matthijs van Leeuwen. ACM Transactions on Knowledge Discovery from Data (TKDD). 23: 1–54.</li><li><a href="https://dl.acm.org/doi/10.1145/3609333">[paper]</a></li></ul></li><li><strong>Explainable Contextual Anomaly Detection using Quantile Regression Forests.</strong><ul><li><strong>Zhong Li</strong>, Matthijs van Leeuwen. Data Mining and Knowledge Discovery (DAMI). 37: 2517–2563.</li><li><a href="https://link.springer.com/article/10.1007/s10618-023-00967-z">[paper]</a>, <a href="https://github.com/ZhongLIFR/QCAD">[code]</a></li></ul></li></ul><h2 id="2022">2022</h2><ul><li><strong>Feature Selection for Fault Detection and Prediction based on Log Analysis.</strong><ul><li><strong>Zhong Li</strong>, Matthijs van Leeuwen. SIGKDD Explorations Newsletter. 24(2): 96–104.</li><li><a href="https://dl.acm.org/doi/10.1145/3575637.3575652">[paper]</a></li></ul></li><li><strong>Choosing and changing the analysis scale in non-inferiority trials with a binary outcome.</strong><ul><li><strong>Zhong Li</strong>, Matteo Quartagno, Stefan Böhringer, and Nan van Geloven. Clinical Trials. 19(1): 14-21.</li><li><a href="https://journals.sagepub.com/doi/full/10.1177/17407745211053790">[paper]</a></li></ul></li></ul><!--<div class="list__item"><article class="archive__item" itemscope itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://zhonglifr.github.io//publication/2015-10-01-paper-title-number-3" rel="permalink">Paper Title Number 3 </a></h2><p>Published in <i>Journal 1</i>, 2015</p><p class="archive__item-excerpt" itemprop="description"><p>This paper is about the number 3. The number 4 is left for future work.</p></p><p>Recommended citation: Your Name, You. (2015). &quot;Paper Title Number 3.&quot; <i>Journal 1</i>. 1(3). <a href="http://academicpages.github.io/files/paper3.pdf"><u>http://academicpages.github.io/files/paper3.pdf</u></a></p></article></div><div class="list__item"><article class="archive__item" itemscope itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://zhonglifr.github.io//publication/2010-10-01-paper-title-number-2" rel="permalink">Paper Title Number 2 </a></h2><p>Published in <i>Journal 1</i>, 2010</p><p class="archive__item-excerpt" itemprop="description"><p>This paper is about the number 2. The number 3 is left for future work.</p></p><p>Recommended citation: Your Name, You. (2010). &quot;Paper Title Number 2.&quot; <i>Journal 1</i>. 1(2). <a href="http://academicpages.github.io/files/paper2.pdf"><u>http://academicpages.github.io/files/paper2.pdf</u></a></p></article></div><div class="list__item"><article class="archive__item" itemscope itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://zhonglifr.github.io//publication/2009-10-01-paper-title-number-1" rel="permalink">Paper Title Number 1 </a></h2><p>Published in <i>Journal 1</i>, 2009</p><p class="archive__item-excerpt" itemprop="description"><p>This paper is about the number 1. The number 2 is left for future work.</p></p><p>Recommended citation: Your Name, You. (2009). &quot;Paper Title Number 1.&quot; <i>Journal 1</i>. 1(1). <a href="http://academicpages.github.io/files/paper1.pdf"><u>http://academicpages.github.io/files/paper1.pdf</u></a></p></article></div>--></div></div><div class="page__footer"><footer> <!-- start custom footer snippets --> <a href="/sitemap/">Sitemap</a> <!-- end custom footer snippets --><div class="page__footer-follow"><ul class="social-icons"><li><strong>Follow:</strong></li><li><a href="http://github.com/ZhongLIFR"><i class="fab fa-github" aria-hidden="true"></i> GitHub</a></li><li><a href="https://zhonglifr.github.io//feed.xml"><i class="fa fa-fw fa-rss-square" aria-hidden="true"></i> Feed</a></li></ul></div><div class="page__footer-copyright">&copy; 2026 Your Name. Powered by <a href="http://jekyllrb.com" rel="nofollow">Jekyll</a> &amp; <a href="https://github.com/academicpages/academicpages.github.io">AcademicPages</a>

1, a fork of <a href="https://mademistakes.com/work/minimal-mistakes-jekyll-theme/" rel="nofollow">Minimal Mistakes</a>.</div></footer></div>

1<script src="https://zhonglifr.github.io//assets/js/main.min.js"></script>

1 

1<script> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', '', 'auto'); ga('send', 'pageview'); </script>

1</body></html>