PageSourceSearch

https://psui3905.github.io/

html psui3905.github.io collected 2026-10-03 09:47:31 UTC 30,195 bytes, 416 lines download raw bytes

1<!DOCTYPE html>
2<html lang="en" style="scroll-behavior:smooth">
3<head>
4    <meta charset="UTF-8">
5    <meta name="viewport" content="width=device-width, initial-scale=1.0">
6    <title>Pengwei Sui - Harvard Medical School</title>
7    <!-- Favicon for different browsers and devices - Horizontal Optimized -->
8    <link rel="icon" type="image/png" sizes="32x16" href="img/hms-logo.png">
9    <link rel="icon" type="image/png" sizes="24x16" href="img/hms-logo.png">
10    <link rel="icon" type="image/png" sizes="16x16" href="img/hms-logo.png">
11    <link rel="shortcut icon" href="img/favicon.png">
12    <link rel="apple-touch-icon" sizes="180x180" href="img/hms-logo.png">
13    <meta name="msapplication-TileImage" content="img/hms-logo.png">
14    <meta name="msapplication-TileColor" content="#FDFCFA">
15    <meta name="theme-color" content="#FDFCFA">
16    <link rel="preconnect" href="https://fonts.googleapis.com">
17    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
18    <link href="https://fonts.googleapis.com/css2?family=Source+Serif+4:ital,opsz,wght@0,8..60,400;0,8..60,500;0,8..60,600;0,8..60,700;1,8..60,400&display=swap" rel="stylesheet">
19    <link rel="stylesheet" href="style.css">
20    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
21    <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
22</head>
23<body>
24    <div class="container">
25        <!-- Left Profile Section -->
26        <aside class="profile-section">
27            <div class="profile-card">
28                <div class="profile-image">
29                    <img src="img/Avatar.png" alt="Profile Photo">
30                </div>
31                
32                <div class="profile-text">
33                    <h1 class="name">Pengwei Sui</h1>
34                    <p class="title">Research Associate @ HMS</p>
35                </div>
36                
37                <div class="contact-info">
38                    <div class="contact-item">
39                        <i class="fas fa-map-marker-alt"></i>
40                        <span>Countway, 10 Shattuck St</span>
41                    </div>
42                    <!-- <div class="contact-item">
43                        <i class="fas fa-link"></i>
44                        <a href="https://dbmi.hms.harvard.edu/people/pengwei-sui">dbmi.hms.harvard.edu/~pengwei</a>
45                    </div> -->
46                    <div class="contact-item">
47                        <i class="fas fa-envelope"></i>
48                        <a href="mailto:[email protected]">[email protected]</a>
49                    </div>
50                    <div class="contact-item">
51                        <i class="fab fa-twitter"></i>
52                        <a href="https://x.com/sui67713">Twitter</a>
53                    </div>
54                    <div class="contact-item">
55                        <i class="fab fa-linkedin"></i>
56                        <a href="https://www.linkedin.com/in/pengweisui/">LinkedIn</a>
57                    </div>
58                    <div class="contact-item">
59                        <i class="fab fa-github"></i>
60                        <a href="https://github.com/psui3905">GitHub</a>
61                    </div>
62                    <div class="contact-item">
63                        <i class="fas fa-graduation-cap"></i>
64                        <a href="https://scholar.google.com/citations?user=9PF9rfcAAAAJ&hl=en&authuser=2">Google Scholar</a>
65                    </div>
66                </div>
67
68                <div class="mobile-links">
69                    <a href="mailto:[email protected]" title="Email"><i class="fas fa-envelope"></i></a>
70                    <a href="https://scholar.google.com/citations?user=9PF9rfcAAAAJ&hl=en&authuser=2" title="Google Scholar"><i class="fas fa-graduation-cap"></i></a>
71                    <a href="https://github.com/psui3905" title="GitHub"><i class="fab fa-github"></i></a>
72                    <a href="https://www.linkedin.com/in/pengweisui/" title="LinkedIn"><i class="fab fa-linkedin"></i></a>
73                    <a href="https://x.com/sui67713" title="Twitter"><i class="fab fa-twitter"></i></a>
74                </div>
75            </div>
76        </aside>
77
78        <!-- Main Content Section -->
79        <main class="main-content">
80            <!-- About Section -->
81            <section id="about" class="content-section">
82                <h2>About</h2>
83                <div class="about-content">
84                    <p>I'm a research associate at Harvard Medical School, working in the <a href="https://zitniklab.hms.harvard.edu/research/">Zitnik Lab</a> with <a href="https://zitniklab.hms.harvard.edu/bio/">Prof.&nbsp;Marinka Zitnik</a> in the <a href="https://dbmi.hms.harvard.edu/">Department of Biomedical Informatics</a>. I also collaborate closely with <a href="https://hidivelab.org/team/members/nils-gehlenborg/">Prof.&nbsp;Nils Gehlenborg</a> and colleagues in the <a href="https://hidivelab.org/">HIDIVE Lab</a>. Previously, I completed my M.S. in Computer Science at Columbia University as part of the <a href="https://www.cs.columbia.edu/nlp/index.cgi">Columbia NLP Group</a>, and my B.S. (Honours) at The University of Sydney with <a href="https://scholar.google.com/citations?user=Sqou_P0AAAAJ&hl=en">Prof.&nbsp;Zhiyong Wang</a>.</p>
85
86                    <p>My research interest focuses on how AI can move from producing plausible biomedical knowledge to making claims that survive biological scrutiny. I enjoy developing methods that integrate perturbations, omics, and literature evidence to reason about cellular state and disease mechanisms in immunology, pharmacology, and cell biology.</p>
87
88                    <p>I am particularly interested in the backside of AI-assisted discovery: grounding predictions in mechanism, tracking conflicting evidence, estimating when a model should abstain, and prioritizing experiments that can change what we believe.</p>
89
90                    <p class="reach-out">If anything sparks your interest, I would love to hear from you. Please don’t he
90sitate to reach out!</p>
91                    
92                </div>
93            </section>
94
95            <!-- News Section -->
96            <section id="news" class="content-section">
97                <h2>News</h2>
98                <div class="news-container">
99                    <div class="news-year-group">
100                        <div class="news-year">2026</div>
101                        <div class="news-year-items">
102                            <article class="news-item">
103                                <time class="news-month" datetime="2026-07">Jul</time>
104                                <div class="news-content">
105                                    <div class="news-headline"><a href="https://arxiv.org/abs/2603.23522">Qworld</a> accepted to <strong>COLM 2026</strong>.</div>
106                                    <div class="news-detail"><strong>89%</strong> expert-criteria coverage and <strong>79%</strong> novel criteria validated by human experts.</div>
107                                </div>
108                            </article>
109                            <article class="news-item">
110                                <time class="news-month" datetime="2026-07">Jul</time>
111                                <div class="news-content">
112                                    <div class="news-headline"><a href="https://aiscientist.tools">ToolUniverse</a> now integrates natively with <a href="https://www.anthropic.com/news/claude-science-ai-workbench" target="_blank" rel="noopener noreferrer">Claude Science</a>.</div>
113                                    <div class="news-detail">One prompt installs <strong>2,500+</strong> scientific tools and bundled research workflows directly inside the workbench, with no MCP server or plugin required.</div>
114                                </div>
115                            </article>
116                            <article class="news-item">
117                                <time class="news-month" datetime="2026-05">May</time>
118                                <div class="news-content">
119                                    <div class="news-headline"><a href="https://medea.openscientist.ai/">Medea</a> featured in <a href="https://www.nature.com/articles/s41592-026-03088-9" target="_blank" rel="noopener noreferrer">Nature Methods</a>.</div>
120                                    <div class="news-detail">With the <a href="https://idekerlab.ucsd.edu/" target="_blank" rel="noopener noreferrer">Ideker Lab</a>, we validated Medea on a previously unpublished <strong>5,806 × 41</strong> yeast E-MAP (<strong>238,046 gene pairs</strong>), recovering experimentally measured synthetic lethal interactions under two DNA-damaging conditions.</div>
121                                </div>
122                            </article>
123                        </div>
124                    </div>
125
126                    <div class="news-year-group">
127                        <div class="news-year">2025</div>
128                        <div class="news-year-items">
129                            <article class="news-item">
130                                <time class="news-month" datetime="2025-12">Dec</time>
131                                <div class="news-content">
132                                    Our <a href="https://curebench.ai/">CURE-Bench</a> workshop at NeurIPS received submissions from <strong>320+ teams</strong> working on precision therapeutics.
133                                </div>
134                            </article>
135                            <article class="news-item">
136                                <time class="news-month" datetime="2025-10">Oct</time>
137                                <div class="news-content">
138                                    <a href="https://aiscientist.tools">ToolUniverse</a> appeared in <a href="https://www.science.org/content/article/can-ai-capture-mind-boggling-complexity-human-cell" target="_blank" rel="noopener noreferrer">Science</a> and <a href="https://www.nature.com/articles/d41586-025-03246-7" target="_blank" rel="noopener noreferrer">Nature News</a> coverage.
139                                </div>
140                            </article>
141                            <article class="news-item">
142                                <time class="news-month" datetime="2025-09">Sep</time>
143                                <div class="news-content">
144                                    <a href="https://www.researchgate.net/publication/392189958_DQVis_Dataset_Natural_Language_to_Biomedical_Visualization">DQVis Dataset</a> accepted to <a href="https://neurips.cc/Conferences/2025">NeurIPS 2025</a>.
145                                </div>
146                            </article>
147                        </div>
148                    </div>
149                </div>
150            </section>
151
152            <!-- Research Section -->
153            <section id="research" class="content-section">
154                <h2>Research</h2>
155                <div class="publications-list">
156
157                        <div class="publication">
158                            <div class="pub-figure">
159                                <img src="img/qworld-thumb.svg" alt="Qworld evaluation criteria animation">
160                            </div>
161                            <div class="pub-content">
162                            <div class="pub-title">
163                                <a href="https://arxiv.org/abs/2603.23522">Qworld: Question-Specific Evaluation Criteria for LLMs</a>
164                            </div>
165                            <div class="pub-authors">
166                                Shanghua Gao*, Yuchang Su*, <strong><u>Pengwei Sui</u></strong>, Curtis Ginder, Marinka Zitnik
167                            </div>
168                            <div class="pub-venue-name">
169                                <strong>COLM 2026</strong> (Conference on Language Modeling)
170                            </div>
171                            <div class="pub-venue">
172                                <a href="https://arxiv.org/abs/2603.23522"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/mims-harvard/Qworld"><i class="fab fa-github"></i>Github</a> / <a href="https://qworld.openscientist.ai/#try-it"><i class="fas fa-globe"></i>Website</a> / <a href="https://huggingface.co/datasets/suyc21/qworld">🤗 Hugging Face</a> / <a href="#" onclick="showBibtex('qworld'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
173                            </div>
174                            </div>
175                        </div>
176
177                        <div class="publication">
178                            <div class="pub-figure">
179                                <img src="img/medea.png" alt="Medea paper Figure">
180                            </div>
181                            <div class="pub-content">
182                            <div class="pub-title">
183                                <a href="https://www.biorxiv.org/content/10.64898/2026.01.16.696667v1">Medea: An omics AI agent for therapeutic discovery</a>
184                            </div>
185                            <div class="pub-authors">
186                                <strong><u>Pengwei Sui</u></strong>*, Michelle Li*, Shanghua Gao, Wanxiang Shen, Valentina Giunchiglia, Andrew Shen, Yepeng Huang, Zhenglun Kong, Marinka Zitnik
187                            </div>
188                            <div class="pub-venue-name">
189                                <strong>bioRxiv preprint</strong> | <span class="github-stars-widget" data-repo="mims-harvard/MEDEA"><i class="fab fa-github"></i> <span class="star-count loading">...</span> ⭐</span>
190                            </div>
191                            <div class="pub-media-coverage">
192                                <a href="https://www.nature.com/articles/s41592-026-03088-9" class="nature-link"><img src="img/nature-icon.png" alt="Nature" class="nature-icon"><strong>Nature Methods Feature</strong></a>
193                            </div>
194                            <div class="pub-venue">
195                                <a href="https://www.biorxiv.org/content/10.64898/2026.01.16.696667v1.full.pdf"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/mims-harvard/MEDEA"><i class="fab fa-github"></i>Github</a> / <a href="https://medea.openscientist.ai/"><i class="fas fa-globe"></i>Website</a> / <a href="#" onclick="showBibtex('medea'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
196                            </div>
197                            </div>
198                        </div>
199
200                        <div class="publication">
201                            <div class="pub-figure-live live-tooluniverse">
202                                <iframe src="https://aiscientist.tools/" title="ToolUniverse" loading="lazy" sandbox="allow-scripts allow-same-origin" tabindex="-1" aria-hidden="true"></iframe>
203                            </div>
204                            <div class="pub-content">
205                            <div class="pub-title">
206                                <a href="https://arxiv.org/pdf/2509.23426">Democratizing AI scientists using ToolUniverse</a>
207                            </div>
208                            <div class="pub-authors">
209                                Shanghua Gao, Richard Zhu*, <strong><u>Pengwei Sui</u></strong>*, Zhenglun Kong*, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik
210                            </div>
211                            <div class="pub-venue-name">
212                                <strong>arXiv preprint</strong> | <span class="github-stars-widget" data-repo="mims-harvard/ToolUniverse"><i class="fab fa-github"></i> <span class="star-count loading">...</span> ⭐</span>
213                            </div>
214                            <div class="pub-media-coverage">
215                                <a href="https://www.anthropic.com/news/healthcare-life-sciences" class="anthropic-link"><img src="img/claude.png" alt="Anthropic" class="anthropic-icon"><strong>Anthropic Announcements</strong></a> | <a href="https://www.nature.com/articles/d41586-025-03246-7" class="nature-link"><img src="img/nature-icon.png" alt="Nature" class="nature-icon"><strong>Nature News</strong></a> | <a href="https://www.science.org/content/article/can-ai-capture-mind-boggling-complexity-human-cell" class="science-blog-link"><img src="img/science-icon.png" alt="Science" class="science-blog-icon"><strong>Science Blog</strong></a>
216                            </div>
217                            <div class="pub-venue">
218                                <a href="https://arxiv.org/pdf/2509.23426"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/mims-harvard/ToolUniverse"><i class="fab fa-github"></i>Github</a> / <a href="https://aiscientist.tools/"><i class="fas fa-globe"></i>Website</a> / <a href="#" onclick="showBibtex('tooluniverse'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
219                            </div>
220                            </div>
221                        </div>
222
223                            <div class="publication">
224                                <div class="pub-figure">
225                                    <img src="img/yac_paper.jpg" alt="YAC paper Figure">
226                                </div>
227                                <div class="pub-content">
228                                <div class="pub-title">
229                                    <a href="https://arxiv.org/abs/2509.19182">YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery</a>
230                                </div>
231                                <div class="pub-authors">
232                                    Devin Lange, Shanghua Gao, <strong><u>Pengwei Sui</u></strong>, Austen Money, Priya Misner, Marinka Zitnik, Nils Gehlenborg
233                                </div>
234                                <div class="pub-venue-name">
235                                    <strong>In review for <a href="https://chi2026.acm.org/">
235ACM CHI 2026</a></strong> | <a href="https://visxgenai.github.io/">VIS x GenAI Workshop</a> @ IEEE VIS 2025
236                                </div>
237                                <div class="pub-venue">
238                                    <a href="https://arxiv.org/abs/2509.19182"><i class="ai ai-arxiv"></i>PDF</a> / <a href="#" onclick="showBibtex('yac'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
239                                </div>
240                                </div>
241                            </div>
242
243
244                            <div class="publication">
245                                <div class="pub-figure">
246                                    <img src="img/DQVis.png" alt="DQVis paper Figure">
247                                </div>
248                                <div class="pub-content">
249                                <div class="pub-title">
250                                    <a href="https://www.researchgate.net/publication/392189958_DQVis_Dataset_Natural_Language_to_Biomedical_Visualization">DQVis Dataset: Natural Language to Biomedical Visualization</a>
251                                </div>
252                                <div class="pub-authors">
253                                    Devin Lange, <strong><u>Pengwei Sui</u></strong>, Shanghua Gao, Marinka Zitnik, Nils Gehlenborg
254                                </div>
255                                <div class="pub-venue-name">
256                                    <strong>NeurIPS 2025</strong>: Conference on Neural Information Processing Systems
257                                </div>
258                                <div class="pub-venue">
259                                    <a href="https://sciety.org/articles/activity/10.31219/osf.io/rqb7u_v1"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/hms-dbmi/DQVis-Generation"><i class="fab fa-github"></i>Github</a> / <a href="https://huggingface.co/datasets/HIDIVE/DQVis">🤗 Hugging Face</a> / <a href="#" onclick="showBibtex('dqvis'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
260                                </div>
261                                </div>
262                            </div>
263                            
264                            <div class="publication">
265                                <div class="pub-figure">
266                                    <img src="img/Enabling-Flexible-Multi-LLM-Integration-for-Scalable-Knowledge-Aggregation.png" alt="Multi-LLM Integration Figure">
267                                </div>
268                                <div class="pub-content">
269                                <div class="pub-title">
270                                    <a href="#">Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation</a>
271                                </div>
272                                <div class="pub-authors">
273                                    Zhenglun Kong*, Zheng Zhan*, Shiyue Hou, Yifan Gong, Xin Meng, <strong><u>Pengwei Sui</u></strong>, Peiyan Dong, Xuan Shen, Zifeng Wang, Pu Zhao, Hao Tang, Stratis Ioannidis, Yanzhi Wang
274                                </div>
275                                <div class="pub-venue-name">
276                                    <strong>arXiv preprint</strong>
277                                </div>
278                                <div class="pub-venue">
279                                    <a href="https://arxiv.org/abs/2505.23844"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/ZLKong/LLM_Integration"><i class="fab fa-github"></i>Github</a> / <a href="#" onclick="showBibtex('multillm'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
280                                </div>
281                                </div>
282                            </div>
283                            
284                            <div class="publication">
285                                <div class="pub-figure">
286                                    <img src="img/Kokomind.png" alt="KokoMind Figure">
287                                </div>
288                                <div class="pub-content">
289                                <div class="pub-title">
290                                    <a href="#">KokoMind: Can LLMs Understand Social Interactions?</a>
291                                </div>
292                                <div class="pub-authors">
293                                    Weiyan Shi*, Liang Qiu*, Dehong Xu, <strong><u>Pengwei Sui</u></strong>, Pan Lu, Zhou Yu
294                                </div>
295                                <div class="pub-venue">
296                                    <a href="https://chats-lab.github.io/KokoMind/"><i class="fas fa-globe"></i>Website</a> / <a href="https://github.com/CHATS-lab/KokoMind"><i class="fab fa-github"></i>Github</a> / <a href="https://twitter.com/shi_weiyan/status/1676697071674601473"><i class="fab fa-twitter"></i>Tweet</a> / <a href="#" onclick="showBibtex('kokomind'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
297                                </div>
298                                </div>
299                            </div>
300                            
301                            <div class="publication">
302                                <div class="pub-figure">
303                                    <img src="img/lica-5m6m-cropped.gif" alt="LICA Algorithm Animation">
304                                </div>
305                                <div class="pub-content">
306                                <div class="pub-title">
307                                    <a href="https://arxiv.org/abs/2007.02529">Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning</a>
308                                </div>
309                                <div class="pub-authors">
310                                    Meng Zhou*, Ziyu Liu*, <strong><u>Pengwei Sui</u></strong>, Yixuan Li, Yuk Ying Chung
311                                </div>
312                                <div class="pub-venue-name">
313                                    <strong>NeurIPS 2020</strong> | <a href="https://wensun.github.io/rl_theory_workshop_2020_ICML.github.io/">RL Theory Workshop</a> @ ICML 2020
314                                </div>
315                                <div class="pub-venue">
316                                    <a href="https://arxiv.org/abs/2007.02529"><i class="ai ai-arxiv"></i>PDF</a> / <a href="https://github.com/mzho7212/LICA"><i class="fab fa-github"></i>Github</a> / <a href="#" onclick="showBibtex('lica'); return false;"><i class="fas fa-quote-right"></i>BibTeX</a>
317                                </div>
318                                </div>
319                            </div>
320                        </div>
321            </section>
322
323            <!-- Experience Section -->
324            <section id="experience" class="content-section">
325                <h2>Experience</h2>
326                <div class="experience-content">
327                    <div class="experience-item">
328                        <div class="exp-content">
329                            <h4>Harvard Medical School, <span class="exp-location">Boston MA, United States</span></h4>
330                            <div class="exp-role">Research Associate, DBMI, <span class="exp-date">2024-Present</span></div>
331                        </div>
332                        <div class="exp-image">
333                            <img src="img/hms-logo.png" alt="Harvard Medical School Logo" class="logo-hms">
334                        </div>
335                    </div>
336                    
337                    <div class="experience-item">
338                        <div class="exp-content">
339                            <h4>Insilico Medicine, <span class="exp-location">Shanghai, China</span></h4>
340                            <div class="exp-role">Consultant Intern, Business Development, <span class="exp-date">Spring 2024</span></div>
341                        </div>
342                        <div class="exp-image">
343                            <img src="img/insilico-medicine.svg" alt="Insilico Medicine Logo" class="logo-insilico">
344                        </div>
345                    </div>
346                    
347                    <div class="experience-item">
348                        <div class="exp-content">
349                            <h4>Yale Engineering School, <span class="exp-location">(remote from New York)</span></h4>
350                            <div class="exp-role">Graduate Student Researcher, <span class="exp-date">Fall 2023</span></div>
351                        </div>
352                        <div class="exp-image">
353                            <img src="img/yale-engineering.png" alt="Yale Engineering Logo" class="logo-yale">
354                        </div>
355                    </div>
356                    
357                    <div class="experience-item">
358                        <div class="exp-content">
359                            <h4>Columbia Engineering School, <span class="exp-location">New York, NY, United States</span></h4>
360                            <div class="exp-role">Graduate Student Researcher, Columbia NLP Group, <span class="exp-date">Summer 2023</span></div>
361                        </div>
362                        <div class="exp-image">
363                            <img src="img/Columbia_University.webp" alt="Columbia Engineering Logo" class="logo-columbia">
364                        </div>
365                    </div>
366                </div>
367            </section>
368
369            <!-- Education Section -->
370            <section id="education" class="content-section">
371                <h2>Education</h2>
372                <div class="education-content">
373                    <div class="education-item">
374                        <div class="edu-content">
375                            <h4>
375Columbia University, <span class="edu-location">New York, NY, United States</span></h4>
376                            <div class="edu-degree">Master of Science in Computer Science, <span class="edu-date">2023</span></div>
377                            <!-- <div class="edu-details">Columbia NLP Group • Machine Learning • Natural Language Processing</div> -->
378                        </div>
379                        <div class="edu-image">
380                            <img src="img/Columbia_University.webp" alt="Columbia University Logo" class="logo-columbia-edu">
381                        </div>
382                    </div>
383                    
384                    <div class="education-item">
385                        <div class="edu-content">
386                            <h4>University of Sydney, <span class="edu-location">Sydney, NSW, Australia</span></h4>
387                            <div class="edu-degree">Bachelor of Science (Honours) in Computer Science, <span class="edu-date">2021</span></div>
388                            <!-- <div class="edu-details">First Class Honours</div> -->
389                        </div>
390                        <div class="edu-image">
391                            <img src="img/usyd.png" alt="University of Sydney Logo" class="logo-usyd">
392                        </div>
393                    </div>
394                </div>
395            </section>
396            
397            <!-- Teaching Section -->
398            <section id="teaching" class="content-section">
399                <h2>Teaching</h2>
400                <p>Back in my undergrad days at USyd, I was a teaching assistant for the following classes:</p>
401                <ul class="teaching-list">
402                    <li><a href="#"><strong>COMP2123: Algorithms & Data Structures</strong></a> (Fall 2019)</li>
403                    <li><a href="#"><strong>INFO1113: Object-Oriented Programming</strong></a> (Spring 2019)</li>
404                    <li><a href="#"><strong>INFO1110: Introduction to Programming</strong></a> (Spring 2019)</li>
405                </ul>
406            </section>
407        </main>
408    </div>
409
410    <footer class="site-footer">
411        &copy; 2026 Pengwei Sui
412    </footer>
413
414    
414<script type="module" src="main.js"></script>
414
415</body>
416</html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.