PageSourceSearch

https://mengyu.page/

html mengyu.page collected 2026-10-02 01:07:34 UTC 17,121 bytes, 51 lines download raw bytes

1<!doctype html><html lang=en-us><head><meta charset=utf-8><meta name=viewport content="width=device-width,initial-scale=1"><meta http-equiv=x-ua-compatible content="IE=edge"><meta name=generator content="Wowchemy 5.6.0 for Hugo"><link rel=preconnect href=https://fonts.gstatic.com crossorigin><link rel=preload as=style href="https://fonts.googleapis.com/css2?family=Montserrat:wght@400;700&family=Roboto+Mono&family=Roboto:wght@400;700&display=swap"><link rel=stylesheet href="https://fonts.googleapis.com/css2?family=Montserrat:wght@400;700&family=Roboto+Mono&family=Roboto:wght@400;700&display=swap" media=print onload='this.media="all"'><meta name=author content="Mengyu Yang"><meta name=description content="A highly-customizable Hugo academic resume theme powered by Wowchemy website builder."><link rel=alternate hreflang=en-us href=https://mengyu.page/><meta name=theme-color content="#1565c0"><link rel=stylesheet href=/css/vendor-bundle.min.c7b8d9abd591ba2253ea42747e3ac3f5.css media=print onload='this.media="all"'><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/[email protected]/css/academicons.min.css integrity="sha512-W0xM4mr6dEP9nREo7Z9z+9X70wytKvMGeDsj7ps2+xg5QPrEBXC8tAW1IFnzjR6eoJ90JmCnFzerQJTLzIEHjA==" crossorigin=anonymous media=print onload='this.media="all"'><link rel=stylesheet href=/css/wowchemy.3495fc6150afdd177f1d04fbba9f5e2c.css><link rel=stylesheet href=/css/libs/chroma/github-light.min.css title=hl-light media=print onload='this.media="all"'><link rel=stylesheet href=/css/libs/chroma/dracula.min.css title=hl-dark media=print onload='this.media="all"' disabled>
1<script src=https://identity.netlify.com/v1/netlify-identity-widget.js></script>
1
2<link rel=alternate href=/index.xml type=application/rss+xml title="Mengyu Yang's Page"><link rel=manifest href=/manifest.webmanifest><link rel=icon type=image/png href=/media/icon_hu5c05d2872ca315179d959a351ca79c39_20501_32x32_fill_lanczos_center_3.png><link rel=apple-touch-icon type=image/png href=/media/icon_hu5c05d2872ca315179d959a351ca79c39_20501_180x180_fill_lanczos_center_3.png><link rel=canonical href=https://mengyu.page/><meta property="twitter:card" content="summary"><meta property="twitter:site" content="@wowchemy"><meta property="twitter:creator" content="@wowchemy"><meta property="og:site_name" content="Mengyu Yang's Page"><meta property="og:url" content="https://mengyu.page/"><meta property="og:title" content="Mengyu Yang's Page"><meta property="og:description" content="A highly-customizable Hugo academic resume theme powered by Wowchemy website builder."><meta property="og:image" content="https://mengyu.page/media/icon_hu5c05d2872ca315179d959a351ca79c39_20501_512x512_fill_lanczos_center_3.png"><meta property="twitter:image" content="https://mengyu.page/media/icon_hu5c05d2872ca315179d959a351ca79c39_20501_512x512_fill_lanczos_center_3.png"><meta property="og:locale" content="en-us"><meta property="og:updated_time" content="2025-03-01T00:00:00+00:00">
2<script type=application/ld+json>{"@context":"https://schema.org","@type":"WebSite","potentialAction":{"@type":"SearchAction","target":"https://mengyu.page?q={search_term_string}","query-input":"required name=search_term_string"},"url":"https://mengyu.page"}</script>
2<title>Mengyu Yang's Page</title></head><body id=top data-spy=scroll data-offset=70 data-target=#navbar-main class=page-wrapper>
2<script src=/js/wowchemy-init.min.613040fe4f2c0f007b4dcb64404201cb.js></script>
2<aside class=search-modal id=search><div class=container><section class=search-header><div class="row no-gutters justify-content-between mb-3"><div class=col-6><h1>Search</h1></div><div class="col-6 col-search-close"><a class=js-search href=# aria-label=Close><i class="fas fa-times-circle text-muted" aria-hidden=true></i></a></div></div><div id=search-box><input name=q id=search-query placeholder=Search... autocapitalize=off autocomplete=off autocorrect=off spellcheck=false type=search class=form-control aria-label=Search...></div></section><section class=section-search-results><div id=search-hits></div></section></div></aside><div class=page-header><header class=header--fixed><nav class="navbar navbar-expand-lg navbar-light compensate-for-scrollbar" id=navbar-main><div class=container-xl><div class="d-none d-lg-inline-flex"><a class=navbar-brand href=/>Mengyu Yang's Page</a></div><button type=button class=navbar-toggler data-toggle=collapse data-target=#navbar-content aria-controls=navbar-content aria-expanded=false aria-label="Toggle navigation">
3<span><i class="fas fa-bars"></i></span></button><div class="navbar-brand-mobile-wrapper d-inline-flex d-lg-none"><a class=navbar-brand href=/>Mengyu Yang's Page</a></div><div class="navbar-collapse main-menu-item collapse justify-content-start" id=navbar-content><ul class="navbar-nav d-md-inline-flex"><li class=nav-item><a class=nav-link href=/#about data-target=#about><span>Home</span></a></li><li class=nav-item><a class=nav-link href=/#publications data-target=#publications><span>Publications</span></a></li><li class=nav-item><a class=nav-link href=/#projects data-target=#projects><span>Projects</span></a></li></ul></div><ul class="nav-icons navbar-nav flex-row ml-auto d-flex pl-md-2"><li class="nav-item dropdown theme-dropdown"><a href=# class=nav-link data-toggle=dropdown aria-haspopup=true aria-label="Display preferences"><i class="fas fa-moon" aria-hidden=true></i></a><div class=dropdown-menu><a href=# class="dropdown-item js-set-theme-light"><span>Light</span></a>
4<a href=# class="dropdown-item js-set-theme-dark"><span>Dark</span></a>
5<a href=# class="dropdown-item js-set-theme-auto"><span>Automatic</span></a></div></li></ul></div></nav></header></div><div class=page-body><span class="js-widget-page d-none"></span><section id=about class="home-section wg-about"><div class=home-section-bg></div><div class=container><div class=row><div class="col-12 col-lg-4"><div id=profile><img class="avatar avatar-circle" width=270 height=270 src=/authors/admin/avatar_hua03a3b2151334d4668ce0b10a8585881_1631249_270x270_fill_lanczos_center_3.png alt="Mengyu Yang"><div class=portrait-title><h2>Mengyu Yang</h2><h3>Machine Learning PhD Student at Georgia Tech</h3></div><ul class=network-icon aria-hidden=true><li><a href=mailto:[email protected] aria-label=envelope><i class="fas fa-envelope big-icon"></i></a></li><li><a href="https://scholar.google.com/citations?user=KrA3RcsAAAAJ&hl=en" target=_blank rel=noopener aria-label=google-scholar><i class="ai ai-google-scholar big-icon"></i></a></li><li><a href=https://www.linkedin.com/in/mengyu-yang/ target=_blank rel=noopener aria-label=linkedin><i class="fab fa-linkedin big-icon"></i></a></li></ul></div></div><div class="col-12 col-lg-8"><h1>About Me</h1><div class=article-style><p>Hi! I’m a Machine Learning PhD student at Georgia Tech working with <a href=https://faculty.cc.gatech.edu/~hays/ target=_blank rel=noopener>James Hays</a>. I received my BASc in <a href=https://engsci.utoronto.ca/program/what-is-engsci/ target=_blank rel=noopener>Engineering Science</a> with Honours from the University of Toronto, where I specialized in <a href=https://engsci.utoronto.ca/program/majors/machine-intelligence/ target=_blank rel=noopener>Machine Intelligence</a>. I&rsquo;ve interned at <a href=https://www.dolby.com/en-in/ target=_blank rel=noopener>Dolby</a> during Summer 2025 working on multimodal representation learning for spatial audio and <a href=https://research.google/ target=_blank rel=noopener>Google Research</a> during Fall 2023 working on audio-visual sound source localization.</p><p>I&rsquo;m currently interning at <a href=https://research.adobe.com/ target=_blank rel=noopener>Adobe</a>, working on dense audio-visual correspondence in MLLMs!</p><p><i class="fas fa-download pr-1 fa-fw"></i> Here&rsquo;s my <a href=/uploads/mengyu_yang_cv.pdf target=_blank>CV</a>.</p><h1 id=research-interests>Research Interests</h1><p>I&rsquo;m interested in <strong>multimodal learning</strong>
5 grounded in computer vision, mainly working at the intersection of vision, audio, and language.</p><p>Topics include:</p><ul><li>Representation learning</li><li>Video understanding</li><li>Audio-visual localization</li></ul></div><div class=row></div></div></div></div></section><section id=publications class="home-section wg-pages"><div class=home-section-bg></div><div class=container><div class=row><div class="section-heading col-12 col-lg-4 mb-3 mb-lg-0 d-flex flex-column align-items-center align-items-lg-start"><h1 class=mb-0>Publications</h1></div><div class="col-12 col-lg-8"><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
6<span class="article-metadata li-cite-author"><span class=author-highlighted>Mengyu Yang</span>, <span>Yiming Chen</span>, <span>Haozheng Pei</span>, <span>Siddhant Agarwal</span>, <span>Arun Balajee Vasudevan</span>, <span>James Hays</span></span>
7(2025).
8<a href=/publication/clink-chop-thud/>Clink! Chop! Thud! - Learning Object Sounds from Real-World Interactions</a>.
9ICCV 2025.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://clink-chop-thud.github.io/ target=_blank rel=noopener>Project</a></p></div><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
10<span class="article-metadata li-cite-author"><span class=author-highlighted>Mengyu Yang</span>, <span>Patrick Grady</span>, <span>Samarth Brahmbhatt</span>, <span>Arun Balajee Vasudevan</span>, <span>Charles C. Kemp</span>, <span>James Hays</span></span>
11(2023).
12<a href=/publication/unkidnappable-robot/>The Un-Kidnappable Robot: Acoustic Localization of Sneaking People</a>.
13ICRA 2024.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://arxiv.org/abs/2310.03743 target=_blank rel=noopener>PDF</a>
14<a class="btn btn-outline-primary btn-page-header btn-sm" href=https://sites.google.com/view/unkidnappable-robot target=_blank rel=noopener>Project</a></p></div><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
15<span class="article-metadata li-cite-author"><span>Tanzila Rahman</span>, <span class=author-highlighted>Mengyu Yang</span>, <span>Leonid Sigal</span></span>
16(2021).
17<a href=/publication/tribert/>TriBERT: Human-centric Audio-visual Representation Learning</a>.
18NeurIPS 2021.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://proceedings.neurips.cc/paper/2021/hash/51200d29d1fc15f5a71c1dab4bb54f7c-Abstract.html target=_blank rel=noopener>PDF</a>
19<a class="btn btn-outline-primary btn-page-header btn-sm" href=https://github.com/ubc-vision/TriBERT target=_blank rel=noopener>Code</a></p></div><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
20<span class="article-metadata li-cite-author"><span>Bryan Wang</span>, <span class=author-highlighted>Mengyu Yang</span>, <span>Tovi Grossman</span></span>
21(2021).
22<a href=/publication/soloist/>Soloist: Generating Mixed-Initiative Tutorials from Existing Guitar Instructional Videos Through Audio Processing</a>.
23CHI 2021.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://arxiv.org/abs/2101.08846 target=_blank rel=noopener>PDF</a>
24<a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=JqQCeUPdk2U" target=_blank rel=noopener>Video</a></p></div><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
25<span class="article-metadata li-cite-author"><span class=author-highlighted>Mengyu Yang</span>, <span>David Rokeby</span>, <span>Xavier Snelgrove</span></span>
26(2020).
27<a href=/publication/maskgan/>Mask-Guided Discovery of Semantic Manifolds in Generative Models</a>.
28NeurIPS 2020 Creativity Workshop.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://arxiv.org/abs/2105.07273 target=_blank rel=noopener>PDF</a>
29<a class="btn btn-outline-primary btn-page-header btn-sm" href=https://github.com/bmolab/masked-gan-manifold target=_blank rel=noopener>
29Code</a>
30<a class="btn btn-outline-primary btn-page-header btn-sm" href=https://slideslive.com/38941013/maskguided-discovery-of-semantic-manifolds-in-generative-models target=_blank rel=noopener>Slides</a></p></div><div class="pub-list-item view-citation" style=margin-bottom:1rem><i class="far fa-file-alt pub-icon" aria-hidden=true></i>
31<span class="article-metadata li-cite-author"><span>Jason d’Eon</span><i class="author-notes fas fa-info-circle" data-toggle=tooltip title="Equal contribution"></i>, <span>Sri Harsha Dumpala</span><i class="author-notes fas fa-info-circle" data-toggle=tooltip title="Equal contribution"></i>, <span>Chandramouli Shama Sastry</span><i class="author-notes fas fa-info-circle" data-toggle=tooltip title="Equal contribution"></i>, <span>Daniel Oore</span>, <span class=author-highlighted>Mengyu Yang</span>, <span>Sageev Oore</span></span>
32(2020).
33<a href=/publication/musical-speech/>Musical Speech: A Transformer-based Composition Tool</a>.
34NeurIPS 2020 Demonstration Track.<p><a class="btn btn-outline-primary btn-page-header btn-sm" href=https://neurips.cc/virtual/2020/demonstration/20799 target=_blank rel=noopener>Project</a></p></div></div></div></div></section><section id=projects class="home-section wg-portfolio"><div class=home-section-bg></div><div class=container><div class=row><div class="section-heading col-12 col-lg-4 mb-3 mb-lg-0 d-flex flex-column align-items-center align-items-lg-start"><h1 class=mb-0>Projects</h1></div><div class="col-12 col-lg-8"><div class="row js-layout-row"><div class="col-12 isotope-item"><div class="media stream-item view-compact"><div class=media-body><div class="section-subheading article-title mb-0 mt-0"><a href=/project/undergrad_thesis/>Building a Dataset for Music Analysis and Conditional Generation</a></div><a href=/project/undergrad_thesis/ class=summary-link><div class=article-style>My undergraduate thesis on deep learning for music generation and analysis.</div></a><div class="stream-meta article-metadata"></div><div class=btn-links><a class="btn btn-outline-primary btn-page-header btn-sm" href=/uploads/Thesis_Report.pdf target=_blank rel=noopener>PDF</a></div></div><div class=ml-3></div></div></div></div></div></div></div></section></div><div class=page-footer><div class=container><footer class=site-footer><p class=powered-by>Published with <a href="https://wowchemy.com/?utm_campaign=poweredby" target=_blank rel=noopener>Wowchemy</a> — the free, <a href=https://github.com/wowchemy/wowchemy-hugo-themes target=_blank rel=noopener>open source</a> website builder that empowers creators.</p></footer></div></div>
34<script src=/js/vendor-bundle.min.fab8b449b814cc9f95b22fcf2e45f05b.js></script>
vendor: 1 bytes, line 34
34
35<script src=https://cdn.jsdelivr.net/gh/desandro/[email protected]/imagesloaded.pkgd.min.js integrity="sha512-S5PZ9GxJZO16tT9r3WJp/Safn31eu8uWrzglMahDT4dsmgqWonRY9grk3j+3tfuPr9WJNsfooOR7Gi7HL5W2jw==" crossorigin=anonymous></script>
vendor: 1 bytes, line 35
35
36<script src=https://cdn.jsdelivr.net/gh/metafizzy/[email protected]/dist/isotope.pkgd.min.js integrity="sha512-Zq2BOxyhvnRFXu0+WE6ojpZLOU2jdnqbrM1hmVdGzyeCa1DgM3X5Q4A/Is9xA1IkbUeDd7755dNNI/PzSf2Pew==" crossorigin=anonymous></script>
vendor: 1 bytes, line 36
36
37<script id=search-hit-fuse-template type=text/x-template>
38    <div class="search-hit" id="summary-{{key}}">
39      <div class="search-hit-content">
40        <div class="search-hit-name">
41          <a href="{{relpermalink}}">{{title}}</a>
42          <div class="article-metadata search-hit-type">{{type}}</div>
43          <p class="search-hit-description">{{snippet}}</p>
44        </div>
45      </div>
46    </div>
47  </script>
47<script src=https://cdn.jsdelivr.net/gh/krisk/[email protected]/dist/fuse.min.js integrity="sha512-o38bmzBGX+hD3JHWUFCDA09btWaqrNmoJ3RXLlrysA7PP01Kgs4UlE4MhelE1v5dJR3+cxlR4qQlotsW7jKsnw==" crossorigin=anonymous></script>
vendor: 1 bytes, line 47
47
48<script src=https://cdn.jsdelivr.net/gh/julmot/[email protected]/dist/jquery.mark.min.js integrity="sha512-mhbv5DqBMgrWL+32MmsDOt/OAvqr/cHimk6B8y/bx/xS88MVkYGPiVv2ixKVrkywF2qHplNRUvFsAHUdxZ3Krg==" crossorigin=anonymous></script>
vendor: 1 bytes, line 48
48
49<script id=page-data type=application/json>{"use_headroom":false}</script>
49<script src=/en/js/wowchemy.min.2a14e6cafbd89dd0247015b525702e10.js></script>
49<div id=modal class="modal fade" role=dialog><div class=modal-dialog><div class=modal-content><div class=modal-header><h5 class=modal-title>Cite</h5><button type=button class=close data-dismiss=modal aria-label=Close>
50<span aria-hidden=true>&#215;</span></button></div><div class=modal-body><pre><code></code></pre></div><div class=modal-footer><a class="btn btn-outline-primary my-1 js-copy-cite" href=# target=_blank><i class="fas fa-copy"></i> Copy</a>
51<a class="btn btn-outline-primary my-1 js-download-cite" href=# target=_blank><i class="fas fa-download"></i> Download</a><div id=modal-error></div></div></div></div></div>
51<script src=/js/wowchemy-publication.68f8d7090562ca65fc6d3cb3f8f2d2cb.js type=module></script>
51</body></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.