Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 5,620 results for author: <span class="mathjax">Xu, Z</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/" aria-role="search"> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Xu, Z"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Xu%2C+Z&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Xu, Z"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13549">arXiv:2411.13549</a> <span> [<a href="https://arxiv.org/pdf/2411.13549">pdf</a>, <a href="https://arxiv.org/format/2411.13549">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Generating 3D-Consistent Videos from Unposed Internet Photos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chou%2C+G">Gene Chou</a>, <a href="/search/?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/?searchtype=author&query=Bi%2C+S">Sai Bi</a>, <a href="/search/?searchtype=author&query=Tan%2C+H">Hao Tan</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zexiang Xu</a>, <a href="/search/?searchtype=author&query=Luan%2C+F">Fujun Luan</a>, <a href="/search/?searchtype=author&query=Hariharan%2C+B">Bharath Hariharan</a>, <a href="/search/?searchtype=author&query=Snavely%2C+N">Noah Snavely</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13549v1-abstract-short" style="display: inline;"> We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path moving between the cameras. Given random images, a model's ability to capture underlying geometry, recognize scene identity, and relate frames in terms of camera position and orientation reflects a fundamental understandi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13549v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13549v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13549v1-abstract-full" style="display: none;"> We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path moving between the cameras. Given random images, a model's ability to capture underlying geometry, recognize scene identity, and relate frames in terms of camera position and orientation reflects a fundamental understanding of 3D structure and scene layout. However, existing video models such as Luma Dream Machine fail at this task. We design a self-supervised method that takes advantage of the consistency of videos and variability of multiview internet photos to train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. We validate that our method outperforms all baselines in terms of geometric and appearance consistency. We also show our model benefits applications that enable camera control, such as 3D Gaussian Splatting. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13549v1-abstract-full').style.display = 'none'; document.getElementById('2411.13549v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12915">arXiv:2411.12915</a> <span> [<a href="https://arxiv.org/pdf/2411.12915">pdf</a>, <a href="https://arxiv.org/format/2411.12915">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/?searchtype=author&query=Zheng%2C+M">Mingxin Zheng</a>, <a href="/search/?searchtype=author&query=Lu%2C+Y">Yao Lu</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Zhijian Liu</a>, <a href="/search/?searchtype=author&query=Yin%2C+H">Hongxu Yin</a>, <a href="/search/?searchtype=author&query=Law%2C+Y+M">Yee Man Law</a>, <a href="/search/?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/?searchtype=author&query=Guo%2C+P">Pengfei Guo</a>, <a href="/search/?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/?searchtype=author&query=Heinrich%2C+G">Greg Heinrich</a>, <a href="/search/?searchtype=author&query=Aylward%2C+S">Stephen Aylward</a>, <a href="/search/?searchtype=author&query=Edgar%2C+M">Marc Edgar</a>, <a href="/search/?searchtype=author&query=Zephyr%2C+M">Michael Zephyr</a>, <a href="/search/?searchtype=author&query=Molchanov%2C+P">Pavlo Molchanov</a>, <a href="/search/?searchtype=author&query=Turkbey%2C+B">Baris Turkbey</a>, <a href="/search/?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/?searchtype=author&query=Xu%2C+D">Daguang Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12915v1-abstract-short" style="display: inline;"> Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12915v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12915v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12915v1-abstract-full" style="display: none;"> Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data$-$features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12915v1-abstract-full').style.display = 'none'; document.getElementById('2411.12915v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12260">arXiv:2411.12260</a> <span> [<a href="https://arxiv.org/pdf/2411.12260">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mesoscale and Nanoscale Physics">cond-mat.mes-hall</span> </div> </div> <p class="title is-5 mathjax"> Noncollinear ferroelectric and screw-type antiferroelectric phases in a metal-free hybrid molecular crystal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wang%2C+N">Na Wang</a>, <a href="/search/?searchtype=author&query=Shen%2C+Z">Zhong Shen</a>, <a href="/search/?searchtype=author&query=Luo%2C+W">Wang Luo</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Hua-Kai Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Ze-Jiang Xu</a>, <a href="/search/?searchtype=author&query=Shi%2C+C">Chao Shi</a>, <a href="/search/?searchtype=author&query=Ye%2C+H">Heng-Yun Ye</a>, <a href="/search/?searchtype=author&query=Dong%2C+S">Shuai Dong</a>, <a href="/search/?searchtype=author&query=Miao%2C+L">Le-Ping Miao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12260v1-abstract-short" style="display: inline;"> Noncollinear dipole textures greatly extend the scientific merits and application perspective of ferroic materials. In fact, noncollinear spin textures have been well recognized as one of the core issues of condensed matter, e.g. cycloidal/conical magnets with multiferroicity and magnetic skyrmions with topological properties. However, the counterparts in electrical polarized materials are less st… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12260v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12260v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12260v1-abstract-full" style="display: none;"> Noncollinear dipole textures greatly extend the scientific merits and application perspective of ferroic materials. In fact, noncollinear spin textures have been well recognized as one of the core issues of condensed matter, e.g. cycloidal/conical magnets with multiferroicity and magnetic skyrmions with topological properties. However, the counterparts in electrical polarized materials are less studied and thus urgently needed, since electric dipoles are usually aligned collinearly in most ferroelectrics/antiferroelectrics. Molecular crystals with electric dipoles provide a rich ore to explore the noncollinear polarity. Here we report an organic salt (H2Dabco)BrClO4 (H2Dabco = N,N'-1,4-diazabicyclo[2.2.2]octonium) that shows a transition between the ferroelectric and antiferroelectric phases. Based on experimental characterizations and ab initio calculations, it is found that its electric dipoles present nontrivial noncollinear textures with $60^\circ$-twisting angle between the neighbours. Then the ferroelectric-antiferroelectric transition can be understood as the coding of twisting angle sequence. Our study reveals the unique science of noncollinear electric polarity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12260v1-abstract-full').style.display = 'none'; document.getElementById('2411.12260v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12197">arXiv:2411.12197</a> <span> [<a href="https://arxiv.org/pdf/2411.12197">pdf</a>, <a href="https://arxiv.org/format/2411.12197">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-981-97-8508-7_12">10.1007/978-981-97-8508-7_12 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MTFusion: Reconstructing Any 3D Object from Single Image Using Multi-word Textual Inversion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+Y">Yu Liu</a>, <a href="/search/?searchtype=author&query=Wang%2C+R">Ruowei Wang</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jiaqi Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zixiang Xu</a>, <a href="/search/?searchtype=author&query=Zhao%2C+Q">Qijun Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12197v1-abstract-short" style="display: inline;"> Reconstructing 3D models from single-view images is a long-standing problem in computer vision. The latest advances for single-image 3D reconstruction extract a textual description from the input image and further utilize it to synthesize 3D models. However, existing methods focus on capturing a single key attribute of the image (e.g., object type, artistic style) and fail to consider the multi-pe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12197v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12197v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12197v1-abstract-full" style="display: none;"> Reconstructing 3D models from single-view images is a long-standing problem in computer vision. The latest advances for single-image 3D reconstruction extract a textual description from the input image and further utilize it to synthesize 3D models. However, existing methods focus on capturing a single key attribute of the image (e.g., object type, artistic style) and fail to consider the multi-perspective information required for accurate 3D reconstruction, such as object shape and material properties. Besides, the reliance on Neural Radiance Fields hinders their ability to reconstruct intricate surfaces and texture details. In this work, we propose MTFusion, which leverages both image data and textual descriptions for high-fidelity 3D reconstruction. Our approach consists of two stages. First, we adopt a novel multi-word textual inversion technique to extract a detailed text description capturing the image's characteristics. Then, we use this description and the image to generate a 3D model with FlexiCubes. Additionally, MTFusion enhances FlexiCubes by employing a special decoder network for Signed Distance Functions, leading to faster training and finer surface representation. Extensive evaluations demonstrate that our MTFusion surpasses existing image-to-3D methods on a wide range of synthetic and real-world images. Furthermore, the ablation study proves the effectiveness of our network designs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12197v1-abstract-full').style.display = 'none'; document.getElementById('2411.12197v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">PRCV 2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Pattern Recognition and Computer Vision (2025), Springer Nature Singapore, pages 166-180, ISBN 978-981-97-8508-7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12178">arXiv:2411.12178</a> <span> [<a href="https://arxiv.org/pdf/2411.12178">pdf</a>, <a href="https://arxiv.org/format/2411.12178">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> First evidence for direct CP violation in beauty to charmonium decays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1127 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12178v1-abstract-short" style="display: inline;"> The {\ensuremath{C\!P}}\xspace asymmetry and branching fraction of the CKM-suppressed decay \mbox{\ensuremath{{B^+}\!\to {J\mskip -3mu/\mskip -2mu蠄}{蟺^+}}} are precisely measured relative to the favoured decay \mbox{\ensuremath{{B^+}\!\to {J\mskip -3mu/\mskip -2mu蠄}{{K}^+}}}, using a sample of proton-proton collision data corresponding to an integrated luminosity of $5.4 \text{\,fb}^{-1}$ recorded… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12178v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12178v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12178v1-abstract-full" style="display: none;"> The {\ensuremath{C\!P}}\xspace asymmetry and branching fraction of the CKM-suppressed decay \mbox{\ensuremath{{B^+}\!\to {J\mskip -3mu/\mskip -2mu蠄}{蟺^+}}} are precisely measured relative to the favoured decay \mbox{\ensuremath{{B^+}\!\to {J\mskip -3mu/\mskip -2mu蠄}{{K}^+}}}, using a sample of proton-proton collision data corresponding to an integrated luminosity of $5.4 \text{\,fb}^{-1}$ recorded at center-of-mass energy of $13\text{\,Te\kern -0.1em V}$ during 2016--2018. The results of the {\ensuremath{C\!P}}\xspace asymmetry difference and branching fraction ratio are \begin{align*} 螖\mathcal{A}^{C\!P} &\equiv \mathcal{A}^{C\!P}({B}^+ \to {J}\mskip -3mu/\mskip -2mu蠄\,蟺^+) - \mathcal{A}^{C\!P}({B}^+ \to {J}\mskip -3mu/\mskip -2mu蠄\,K^+) = (1.29 \pm 0.49 \pm 0.08) \times 10^{-2}, \end{align*} \begin{equation*} \mathcal{R}_{蟺/K} \equiv \frac{\mathcal{B}(B^+ \!\to J\mskip -3mu/\mskip -2mu蠄\,蟺^+)} {\mathcal{B}(B^+ \!\to J\mskip -3mu/\mskip -2mu蠄\,K^+)} = (3.852 \pm 0.022 \pm 0.018) \times 10^{-2}. \end{equation*}where the first uncertainties are statistical and the second systematic. A combination with previous LHCb results based on data collected at $7$ and $8~\text{Te\kern -0.1em V}$ in 2011 and 2012 yields {$螖\mathcal{A}^{C\!P} = (1.42 \pm 0.43 \pm 0.08) \times 10^{-2}$ and $\mathcal{R}_{蟺/K} = (3.846 \pm 0.018 \pm 0.018) \times 10^{-2}$}. The combined $螖\mathcal{A}^{C\!P}$ value deviates from zero by 3.2 standard deviations, providing the first evidence for direct {\ensuremath{C\!P}}\xspace violation in the amplitudes of beauty decays to charmonium final states. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12178v1-abstract-full').style.display = 'none'; document.getElementById('2411.12178v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 2 figures, no conference or journal information All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/1623/ (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LHCb-PAPER-2024-031 CERN-EP-2024-286 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11848">arXiv:2411.11848</a> <span> [<a href="https://arxiv.org/pdf/2411.11848">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Robust Graph Neural Networks for Stability Analysis in Dynamic Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhen Xu</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Yue Liu</a>, <a href="/search/?searchtype=author&query=Sun%2C+M">Mengfang Sun</a>, <a href="/search/?searchtype=author&query=Zhou%2C+T">Tong Zhou</a>, <a href="/search/?searchtype=author&query=Sun%2C+W">Wenying Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11848v1-abstract-short" style="display: inline;"> In the current context of accelerated globalization and digitalization, the complexity and uncertainty of financial markets are increasing, and the identification and prevention of economic risks have become a key link in maintaining the stability of the financial system. Traditional risk identification methods often have limitations because they are difficult to cope with the multi-level and dyna… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11848v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11848v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11848v1-abstract-full" style="display: none;"> In the current context of accelerated globalization and digitalization, the complexity and uncertainty of financial markets are increasing, and the identification and prevention of economic risks have become a key link in maintaining the stability of the financial system. Traditional risk identification methods often have limitations because they are difficult to cope with the multi-level and dynamically changing complex relationships in financial networks. With the rapid development of financial technology, graph neural network (GNN) technology, as an emerging deep learning method, has gradually shown great potential in the field of financial risk management. GNN can map transaction behaviors, financial institutions, individuals, and their interactive relationships in financial networks into graph structures, and effectively capture potential patterns and abnormal signals in financial data through embedded representation learning. Using this technology, financial institutions can extract valuable information from complex transaction networks, identify hidden dangers or abnormal behaviors that may cause systemic risks in a timely manner, optimize decision-making processes, and improve the accuracy of risk warnings. This paper explores the economic risk identification algorithm based on the GNN algorithm, aiming to provide financial institutions and regulators with more intelligent technical tools to help maintain the security and stability of the financial market. Improving the efficiency of economic risk identification through innovative technical means is expected to further enhance the risk resistance of the financial system and lay the foundation for building a robust global financial system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11848v1-abstract-full').style.display = 'none'; document.getElementById('2411.11848v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">It was accepted by the 3rd International Conference on Cloud Computing Big Data Application and Software Engineering</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11648">arXiv:2411.11648</a> <span> [<a href="https://arxiv.org/pdf/2411.11648">pdf</a>, <a href="https://arxiv.org/ps/2411.11648">ps</a>, <a href="https://arxiv.org/format/2411.11648">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Phenomenology">hep-ph</span> </div> </div> <p class="title is-5 mathjax"> Evidence for Two Excited $惟^{-}$ Hyperons </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=BESIII+Collaboration"> BESIII Collaboration</a>, <a href="/search/?searchtype=author&query=Ablikim%2C+M">M. Ablikim</a>, <a href="/search/?searchtype=author&query=Achasov%2C+M+N">M. N. Achasov</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Afedulidis%2C+O">O. Afedulidis</a>, <a href="/search/?searchtype=author&query=Ai%2C+X+C">X. C. Ai</a>, <a href="/search/?searchtype=author&query=Aliberti%2C+R">R. Aliberti</a>, <a href="/search/?searchtype=author&query=Amoroso%2C+A">A. Amoroso</a>, <a href="/search/?searchtype=author&query=Bai%2C+Y">Y. Bai</a>, <a href="/search/?searchtype=author&query=Bakina%2C+O">O. Bakina</a>, <a href="/search/?searchtype=author&query=Balossino%2C+I">I. Balossino</a>, <a href="/search/?searchtype=author&query=Ban%2C+Y">Y. Ban</a>, <a href="/search/?searchtype=author&query=Bao%2C+H+-">H. -R. Bao</a>, <a href="/search/?searchtype=author&query=Batozskaya%2C+V">V. Batozskaya</a>, <a href="/search/?searchtype=author&query=Begzsuren%2C+K">K. Begzsuren</a>, <a href="/search/?searchtype=author&query=Berger%2C+N">N. Berger</a>, <a href="/search/?searchtype=author&query=Berlowski%2C+M">M. Berlowski</a>, <a href="/search/?searchtype=author&query=Bertani%2C+M">M. Bertani</a>, <a href="/search/?searchtype=author&query=Bettoni%2C+D">D. Bettoni</a>, <a href="/search/?searchtype=author&query=Bianchi%2C+F">F. Bianchi</a>, <a href="/search/?searchtype=author&query=Bianco%2C+E">E. Bianco</a>, <a href="/search/?searchtype=author&query=Bortone%2C+A">A. Bortone</a>, <a href="/search/?searchtype=author&query=Boyko%2C+I">I. Boyko</a>, <a href="/search/?searchtype=author&query=Briere%2C+R+A">R. A. Briere</a>, <a href="/search/?searchtype=author&query=Brueggemann%2C+A">A. Brueggemann</a> , et al. (650 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11648v1-abstract-short" style="display: inline;"> Using $e^+e^-$ collision data corresponding to an integrated luminosity of 19 fb$^{-1}$ collected by the BESIII detector at center-of-mass energies ranging from 4.13 to 4.70 GeV, we report the first evidence for a new excited $惟^{-}$ hyperon, the $惟^*(2109)^{-}$, through the process $e^+ e^- \to 惟^*(2109)^{-} \bar惟^{+} +c.c.$ with a significance of 3.7 $蟽$. The mass and width of $惟^*(2109)^{-}$ ar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11648v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11648v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11648v1-abstract-full" style="display: none;"> Using $e^+e^-$ collision data corresponding to an integrated luminosity of 19 fb$^{-1}$ collected by the BESIII detector at center-of-mass energies ranging from 4.13 to 4.70 GeV, we report the first evidence for a new excited $惟^{-}$ hyperon, the $惟^*(2109)^{-}$, through the process $e^+ e^- \to 惟^*(2109)^{-} \bar惟^{+} +c.c.$ with a significance of 3.7 $蟽$. The mass and width of $惟^*(2109)^{-}$ are measured to be $2108.8 \pm 5.5_{\rm stat} \pm 1.5_{\rm syst} {\rm MeV}/c^{2}$ and $21.6 \pm 17.7_{\rm stat} \pm 9.4_{\rm syst} {\rm MeV}$, respectively. We also present evidence for production of the $惟^*(2012)^{-}$ in the process $e^+ e^- \to 惟^*(2012)^{-} \bar惟^{+} +c.c.$ with a significance of 3.7 $蟽$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11648v1-abstract-full').style.display = 'none'; document.getElementById('2411.11648v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11595">arXiv:2411.11595</a> <span> [<a href="https://arxiv.org/pdf/2411.11595">pdf</a>, <a href="https://arxiv.org/format/2411.11595">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Phenomenology">hep-ph</span> </div> </div> <p class="title is-5 mathjax"> Threshold Resummation for Semi-Inclusive Single-Hadron Production with Effective Field Theory </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhen Xu</a>, <a href="/search/?searchtype=author&query=Zhu%2C+H+X">Hua Xing Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11595v1-abstract-short" style="display: inline;"> Large double-logarithmic corrections are induced by soft gluon emissions near threshold in the semi-inclusive $e^+e^-$ annihilation (SIA) distributions, and must be resummed to all-orders in perturbation theory for reliable theoretical predictions. Building on strategy developed for threshold resummation for DIS structure function in momentum space using soft-collinear effective theory (SCET), we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11595v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11595v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11595v1-abstract-full" style="display: none;"> Large double-logarithmic corrections are induced by soft gluon emissions near threshold in the semi-inclusive $e^+e^-$ annihilation (SIA) distributions, and must be resummed to all-orders in perturbation theory for reliable theoretical predictions. Building on strategy developed for threshold resummation for DIS structure function in momentum space using soft-collinear effective theory (SCET), we present the explicit formalism for SIA cross section. We then perform the resummation directly in momentum space for $纬^* \to q \bar q$, $H \to gg$ and $H \to b\bar b$ to N$^4$LL accuracy and demonstrate good convergence. We anticipate that these results will benefit the extraction of the light-quark, the heavy-quark as well as the gluon fragmentation functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11595v1-abstract-full').style.display = 'none'; document.getElementById('2411.11595v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11406">arXiv:2411.11406</a> <span> [<a href="https://arxiv.org/pdf/2411.11406">pdf</a>, <a href="https://arxiv.org/format/2411.11406">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ge%2C+H">Haizhou Ge</a>, <a href="/search/?searchtype=author&query=Wang%2C+R">Ruixiang Wang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhu-ang Xu</a>, <a href="/search/?searchtype=author&query=Zhu%2C+H">Hongrui Zhu</a>, <a href="/search/?searchtype=author&query=Deng%2C+R">Ruichen Deng</a>, <a href="/search/?searchtype=author&query=Dong%2C+Y">Yuhang Dong</a>, <a href="/search/?searchtype=author&query=Pang%2C+Z">Zeyu Pang</a>, <a href="/search/?searchtype=author&query=Zhou%2C+G">Guyue Zhou</a>, <a href="/search/?searchtype=author&query=Zhang%2C+J">Junyu Zhang</a>, <a href="/search/?searchtype=author&query=Shi%2C+L">Lu Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11406v1-abstract-short" style="display: inline;"> Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we propose a pipeline that facilitates the migration of advanced imitation learning algorithms to edge devices. The process is achieved via an efficient model compressio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11406v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11406v1-abstract-full" style="display: none;"> Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we propose a pipeline that facilitates the migration of advanced imitation learning algorithms to edge devices. The process is achieved via an efficient model compression method and a practical asynchronous parallel method Temporal Ensemble with Dropped Actions (TEDA) that enhances the smoothness of operations. To show the efficiency of the proposed pipeline, large-scale imitation learning models are trained on a server and deployed on an edge device to complete various manipulation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11406v1-abstract-full').style.display = 'none'; document.getElementById('2411.11406v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the 2024 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11223">arXiv:2411.11223</a> <span> [<a href="https://arxiv.org/pdf/2411.11223">pdf</a>, <a href="https://arxiv.org/format/2411.11223">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Efficient Transfer Learning for Video-language Foundation Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+H">Haoxing Chen</a>, <a href="/search/?searchtype=author&query=Huang%2C+Z">Zizheng Huang</a>, <a href="/search/?searchtype=author&query=Hong%2C+Y">Yan Hong</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yanshuo Wang</a>, <a href="/search/?searchtype=author&query=Lyu%2C+Z">Zhongcai Lyu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhuoer Xu</a>, <a href="/search/?searchtype=author&query=Lan%2C+J">Jun Lan</a>, <a href="/search/?searchtype=author&query=Gu%2C+Z">Zhangxuan Gu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11223v1-abstract-short" style="display: inline;"> Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional parameter modules to capture temporal information. While the increased model capacity brought by these additional parameters helps better fit the video-specific inductive biases, ex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11223v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11223v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11223v1-abstract-full" style="display: none;"> Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional parameter modules to capture temporal information. While the increased model capacity brought by these additional parameters helps better fit the video-specific inductive biases, existing methods require learning a large number of parameters and are prone to catastrophic forgetting of the original generalizable knowledge. In this paper, we propose a simple yet effective Multi-modal Spatio-Temporal Adapter (MSTA) to improve the alignment between representations in the text and vision branches, achieving a balance between general knowledge and task-specific knowledge. Furthermore, to mitigate over-fitting and enhance generalizability, we introduce a spatio-temporal description-guided consistency constraint. This constraint involves feeding template inputs (i.e., ``a video of $\{\textbf{cls}\}$'') into the trainable language branch, while LLM-generated spatio-temporal descriptions are input into the pre-trained language branch, enforcing consistency between the outputs of the two branches. This mechanism prevents over-fitting to downstream tasks and improves the distinguishability of the trainable branch within the spatio-temporal semantic space. We evaluate the effectiveness of our approach across four tasks: zero-shot transfer, few-shot learning, base-to-novel generalization, and fully-supervised learning. Compared to many state-of-the-art methods, our MSTA achieves outstanding performance across all evaluations, while using only 2-7\% of the trainable parameters in the original model. Code will be avaliable at https://github.com/chenhaoxing/ETL4Video. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11223v1-abstract-full').style.display = 'none'; document.getElementById('2411.11223v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10938">arXiv:2411.10938</a> <span> [<a href="https://arxiv.org/pdf/2411.10938">pdf</a>, <a href="https://arxiv.org/ps/2411.10938">ps</a>, <a href="https://arxiv.org/format/2411.10938">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Low-Complexity Algorithms for Multichannel Spectral Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wu%2C+X">Xunmeng Wu</a>, <a href="/search/?searchtype=author&query=Yang%2C+Z">Zai Yang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zongben Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10938v1-abstract-short" style="display: inline;"> This paper studies the problem of multichannel spectral super-resolution with either constant amplitude (CA) or not. We propose two optimization problems based on low-rank Hankel-Toeplitz matrix factorization. The two problems effectively leverage the multichannel and CA structures, while also enabling the design of low-complexity gradient descent algorithms for their solutions. Extensive simulati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10938v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10938v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10938v1-abstract-full" style="display: none;"> This paper studies the problem of multichannel spectral super-resolution with either constant amplitude (CA) or not. We propose two optimization problems based on low-rank Hankel-Toeplitz matrix factorization. The two problems effectively leverage the multichannel and CA structures, while also enabling the design of low-complexity gradient descent algorithms for their solutions. Extensive simulations show the superior performance of the proposed algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10938v1-abstract-full').style.display = 'none'; document.getElementById('2411.10938v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10781">arXiv:2411.10781</a> <span> [<a href="https://arxiv.org/pdf/2411.10781">pdf</a>, <a href="https://arxiv.org/format/2411.10781">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Shao%2C+S">Shitong Shao</a>, <a href="/search/?searchtype=author&query=Zhou%2C+Z">Zikai Zhou</a>, <a href="/search/?searchtype=author&query=Ye%2C+T">Tian Ye</a>, <a href="/search/?searchtype=author&query=Bai%2C+L">Lichen Bai</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiqiang Xu</a>, <a href="/search/?searchtype=author&query=Xie%2C+Z">Zeke Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10781v1-abstract-short" style="display: inline;"> Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) complicates the path toward achieving the goal of unified vision and language generation. Recently, the masked generative Transformer (MGT) serves as a promising intermediary between… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10781v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10781v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10781v1-abstract-full" style="display: none;"> Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) complicates the path toward achieving the goal of unified vision and language generation. Recently, the masked generative Transformer (MGT) serves as a promising intermediary between DM and ARM by predicting randomly masked image tokens (i.e., masked image modeling), combining the efficiency of DM with the discrete token nature of ARM. However, we find that the comprehensive analyses regarding the inference for MGT are virtually non-existent, and thus we aim to present positive design choices to fill this gap. We modify and re-design a set of DM-based inference techniques for MGT and further elucidate their performance on MGT. We also discuss the approach to correcting token's distribution to enhance inference. Extensive experiments and empirical analyses lead to concrete and effective design choices, and these design choices can be merged to achieve further performance gains. For instance, in terms of enhanced inference, we achieve winning rates of approximately 70% compared to vanilla sampling on HPS v2 with the recent SOTA MGT Meissonic. Our contributions have the potential to further enhance the capabilities and future development of MGTs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10781v1-abstract-full').style.display = 'none'; document.getElementById('2411.10781v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10618">arXiv:2411.10618</a> <span> [<a href="https://arxiv.org/pdf/2411.10618">pdf</a>, <a href="https://arxiv.org/format/2411.10618">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> D-Flow: Multi-modality Flow Matching for D-peptide Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wu%2C+F">Fang Wu</a>, <a href="/search/?searchtype=author&query=Xu%2C+T">Tinson Xu</a>, <a href="/search/?searchtype=author&query=Jin%2C+S">Shuting Jin</a>, <a href="/search/?searchtype=author&query=Tang%2C+X">Xiangru Tang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zerui Xu</a>, <a href="/search/?searchtype=author&query=Zou%2C+J">James Zou</a>, <a href="/search/?searchtype=author&query=Hie%2C+B">Brian Hie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10618v1-abstract-short" style="display: inline;"> Proteins play crucial roles in biological processes, with therapeutic peptides emerging as promising pharmaceutical agents. They allow new possibilities to leverage target binding sites that were previously undruggable. While deep learning (DL) has advanced peptide discovery, generating D-proteins composed of D-amino acids remains challenging due to the scarcity of natural examples. This paper pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10618v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10618v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10618v1-abstract-full" style="display: none;"> Proteins play crucial roles in biological processes, with therapeutic peptides emerging as promising pharmaceutical agents. They allow new possibilities to leverage target binding sites that were previously undruggable. While deep learning (DL) has advanced peptide discovery, generating D-proteins composed of D-amino acids remains challenging due to the scarcity of natural examples. This paper proposes D-Flow, a full-atom flow-based framework for {de novo} D-peptide design. D-Flow is conditioned on receptor binding and utilizes a comprehensive representation of peptide structure, incorporating backbone frames, side-chain angles, and discrete amino acid types. A mirror-image algorithm is implemented to address the lack of training data for D-proteins, which converts L-receptors' chirality. Furthermore, we enhance D-Flow's capacity by integrating large protein language models (PLMs) with structural awareness through a lightweight structural adapter. A two-stage training pipeline and a controlling toolkit also enable D-Flow to transition from general protein design to targeted binder design while preserving pretraining knowledge. Extensive experimental results on the PepMerge benchmark demonstrate D-Flow's effectiveness, particularly in developing peptides with entire D-residues. This approach represents a significant advancement in computational D-peptide design, offering unique opportunities for bioorthogonal and stable molecular tools and diagnostics. The code is available in~\url{https://github.com/smiles724/PeptideDesign}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10618v1-abstract-full').style.display = 'none'; document.getElementById('2411.10618v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10219">arXiv:2411.10219</a> <span> [<a href="https://arxiv.org/pdf/2411.10219">pdf</a>, <a href="https://arxiv.org/format/2411.10219">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Constraints on the photon polarisation in $b \to s 纬$ transitions using $B_s^0 \rightarrow 蠁e^+e^-$ decays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1120 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10219v2-abstract-short" style="display: inline;"> An angular analysis of the $B_s^0 \rightarrow 蠁e^+e^-$ decay is performed using the proton-proton collision dataset collected between 2011 and 2018 by the LHCb experiment, corresponding to an integrated luminosity of $9\,{\rm fb}^{-1}$ at centre-of-mass energies of 7, 8 and $13\,{\rm TeV}$. The analysis is performed in the very low dielectron invariant mass-squared region between $0.0009$ and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10219v2-abstract-full').style.display = 'inline'; document.getElementById('2411.10219v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10219v2-abstract-full" style="display: none;"> An angular analysis of the $B_s^0 \rightarrow 蠁e^+e^-$ decay is performed using the proton-proton collision dataset collected between 2011 and 2018 by the LHCb experiment, corresponding to an integrated luminosity of $9\,{\rm fb}^{-1}$ at centre-of-mass energies of 7, 8 and $13\,{\rm TeV}$. The analysis is performed in the very low dielectron invariant mass-squared region between $0.0009$ and $0.2615\,{\rm GeV}^2\!/c^4$. The longitudinal polarisation fraction of the $蠁$ meson is measured to be less than $11.5\%$ at $90\%$ confidence level. The $A_{\mathrm{T}}^{\mathcal{R}e C\!P}$ observable, which is related to the lepton forward-backward asymmetry, is measured to be $0.116 \pm 0.155 \pm 0.006$, where the first uncertainty is statistical and the second systematic. The transverse asymmetries, $A_{\mathrm{T}}^{(2)}$ and $A_{\mathrm{T}}^{\mathcal{I}m C\!P}$ , which are sensitive to the virtual photon polarisation, are found to be $-0.045 \pm 0.235 \pm 0.014$ and $0.002 \pm 0.247 \pm 0.016$, respectively. The results are consistent with Standard Model predictions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10219v2-abstract-full').style.display = 'none'; document.getElementById('2411.10219v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages, 4 figures. All figures and tables, along with any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3433/ (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LHCb-PAPER-2024-030, CERN-EP-2024-276 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09554">arXiv:2411.09554</a> <span> [<a href="https://arxiv.org/pdf/2411.09554">pdf</a>, <a href="https://arxiv.org/ps/2411.09554">ps</a>, <a href="https://arxiv.org/format/2411.09554">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Distributed Recursion Revisited </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+W">Wei-Yang Zhang</a>, <a href="/search/?searchtype=author&query=Dong%2C+F">Feng-Lian Dong</a>, <a href="/search/?searchtype=author&query=Wei%2C+Z">Zhi-Wei Wei</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yan-Ru Wang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Ze-Jin Xu</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Wei-Kun Chen</a>, <a href="/search/?searchtype=author&query=Dai%2C+Y">Yu-Hong Dai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09554v1-abstract-short" style="display: inline;"> The distributed recursion (DR) algorithm is an effective method for solving the pooling problem that arises in many applications. It is based on the well-known P-formulation of the pooling problem, which involves the flow and quality variables; and it can be seen as a variant of the successive linear programming (SLP) algorithm, where the linear programming (LP) approximation problem can be transf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09554v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09554v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09554v1-abstract-full" style="display: none;"> The distributed recursion (DR) algorithm is an effective method for solving the pooling problem that arises in many applications. It is based on the well-known P-formulation of the pooling problem, which involves the flow and quality variables; and it can be seen as a variant of the successive linear programming (SLP) algorithm, where the linear programming (LP) approximation problem can be transformed from the LP approximation problem derived by using the first-order Taylor series expansion technique. In this paper, we first propose a new nonlinear programming (NLP) formulation for the pooling problem involving only the flow variables, and show that the DR algorithm can be seen as a direct application of the SLP algorithm to the newly proposed formulation. With this new useful theoretical insight, we then develop a new variant of DR algorithm, called penalty DR (PDR) algorithm, based on the proposed formulation. The proposed PDR algorithm is a penalty algorithm where violations of the (linearized) nonlinear constraints are penalized in the objective function of the LP approximation problem with the penalty terms increasing when the constraint violations tend to be large. Compared with the LP approximation problem in the classic DR algorithm, the LP approximation problem in the proposed PDR algorithm can return a solution with a better objective value, which makes it more suitable for finding high-quality solutions for the pooling problem. Numerical experiments on benchmark and randomly constructed instances show that the proposed PDR algorithm is more effective than the classic SLP and DR algorithms in terms of finding a better solution for the pooling problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09554v1-abstract-full').style.display = 'none'; document.getElementById('2411.09554v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 2 figures, submitted for possible publication</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 90C59 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09502">arXiv:2411.09502</a> <span> [<a href="https://arxiv.org/pdf/2411.09502">pdf</a>, <a href="https://arxiv.org/format/2411.09502">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Golden Noise for Diffusion Models: A Learning Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhou%2C+Z">Zikai Zhou</a>, <a href="/search/?searchtype=author&query=Shao%2C+S">Shitong Shao</a>, <a href="/search/?searchtype=author&query=Bai%2C+L">Lichen Bai</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiqiang Xu</a>, <a href="/search/?searchtype=author&query=Han%2C+B">Bo Han</a>, <a href="/search/?searchtype=author&query=Xie%2C+Z">Zeke Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09502v1-abstract-short" style="display: inline;"> Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment and higher human preference than others, we still lack a machine learning framework to obtain those golden noises. To learn golden noises for diffusio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09502v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09502v1-abstract-full" style="display: none;"> Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment and higher human preference than others, we still lack a machine learning framework to obtain those golden noises. To learn golden noises for diffusion sampling, we mainly make three contributions in this paper. First, we identify a new concept termed the \textit{noise prompt}, which aims at turning a random Gaussian noise into a golden noise by adding a small desirable perturbation derived from the text prompt. Following the concept, we first formulate the \textit{noise prompt learning} framework that systematically learns ``prompted'' golden noise associated with a text prompt for diffusion models. Second, we design a noise prompt data collection pipeline and collect a large-scale \textit{noise prompt dataset}~(NPD) that contains 100k pairs of random noises and golden noises with the associated text prompts. With the prepared NPD as the training dataset, we trained a small \textit{noise prompt network}~(NPNet) that can directly learn to transform a random noise into a golden noise. The learned golden noise perturbation can be considered as a kind of prompt for noise, as it is rich in semantic information and tailored to the given text prompt. Third, our extensive experiments demonstrate the impressive effectiveness and generalization of NPNet on improving the quality of synthesized images across various diffusion models, including SDXL, DreamShaper-xl-v2-turbo, and Hunyuan-DiT. Moreover, NPNet is a small and efficient controller that acts as a plug-and-play module with very limited additional inference and computational costs, as it just provides a golden noise instead of a random noise without accessing the original pipeline. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09502v1-abstract-full').style.display = 'none'; document.getElementById('2411.09502v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09343">arXiv:2411.09343</a> <span> [<a href="https://arxiv.org/pdf/2411.09343">pdf</a>, <a href="https://arxiv.org/format/2411.09343">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Nuclear Experiment">nucl-ex</span> </div> </div> <p class="title is-5 mathjax"> Measurement of $蠁(1020)$ meson production in fixed-target $\textit{p}$Ne collisions at $\sqrt{s_{NN}}$ = 68.5 GeV </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1127 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.09343v1-abstract-short" style="display: inline;"> The first measurement of $蠁(1020)$ meson production in fixed-target $p$Ne collisions at $\sqrt{s_{NN}}=68.5$ GeV is presented. The $蠁(1020)$ mesons are reconstructed in their $K^{+}K^{-}$ decay in a data sample consisting of proton collisions on neon nuclei at rest, corresponding to an integrated luminosity of $21.7 \pm 1.4$ nb$^{-1}$, collected by the LHCb detector at CERN. The $蠁(1020)$ producti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09343v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09343v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09343v1-abstract-full" style="display: none;"> The first measurement of $蠁(1020)$ meson production in fixed-target $p$Ne collisions at $\sqrt{s_{NN}}=68.5$ GeV is presented. The $蠁(1020)$ mesons are reconstructed in their $K^{+}K^{-}$ decay in a data sample consisting of proton collisions on neon nuclei at rest, corresponding to an integrated luminosity of $21.7 \pm 1.4$ nb$^{-1}$, collected by the LHCb detector at CERN. The $蠁(1020)$ production cross-section in the centre-of-mass rapidity range of $-1.8<y^*<0$ and transverse momentum range of $800<p_{T}<6500$ MeV/c is found to be $蟽=182.7\pm2.7~\text{(stat.)}\pm14.1~\text{(syst)}~渭$b/nucleon. A double-differential measurement of the cross-section is also provided in four regions of rapidity and six regions of transverse momentum of the $蠁(1020)$ meson and compared with the predictions from Pythia and EPOS4, which are found to underestimate the experimental values. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09343v1-abstract-full').style.display = 'none'; document.getElementById('2411.09343v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3673/ (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LHCb-PAPER-2024-036, CERN-EP-2024-274 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08178">arXiv:2411.08178</a> <span> [<a href="https://arxiv.org/pdf/2411.08178">pdf</a>, <a href="https://arxiv.org/format/2411.08178">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> On Adapting Randomized Nystr枚m Preconditioners to Accelerate Variational Image Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hong%2C+T">Tao Hong</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhaoyi Xu</a>, <a href="/search/?searchtype=author&query=Hu%2C+J">Jason Hu</a>, <a href="/search/?searchtype=author&query=Fessler%2C+J+A">Jeffrey A. Fessler</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08178v1-abstract-short" style="display: inline;"> Model-based iterative reconstruction plays a key role in solving inverse problems. However, the associated minimization problems are generally large-scale, ill-posed, nonsmooth, and sometimes even nonconvex, which present challenges in designing efficient iterative solvers and often prevent their practical use. Preconditioning methods can significantly accelerate the convergence of iterative metho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08178v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08178v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08178v1-abstract-full" style="display: none;"> Model-based iterative reconstruction plays a key role in solving inverse problems. However, the associated minimization problems are generally large-scale, ill-posed, nonsmooth, and sometimes even nonconvex, which present challenges in designing efficient iterative solvers and often prevent their practical use. Preconditioning methods can significantly accelerate the convergence of iterative methods. In some applications, computing preconditioners on-the-fly is beneficial. Moreover, forward models in image reconstruction are typically represented as operators, and the corresponding explicit matrices are often unavailable, which brings additional challenges in designing preconditioners. Therefore, for practical use, computing and applying preconditioners should be computationally inexpensive. This paper adapts the randomized Nystr枚m approximation to compute effective preconditioners that accelerate image reconstruction without requiring an explicit matrix for the forward model. We leverage modern GPU computational platforms to compute the preconditioner on-the-fly. Moreover, we propose efficient approaches for applying the preconditioner to problems with nonsmooth regularizers. Our numerical results on image deblurring, super-resolution with impulsive noise, and computed tomography reconstruction demonstrate the efficiency and effectiveness of the proposed preconditioner. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08178v1-abstract-full').style.display = 'none'; document.getElementById('2411.08178v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 11 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08151">arXiv:2411.08151</a> <span> [<a href="https://arxiv.org/pdf/2411.08151">pdf</a>, <a href="https://arxiv.org/ps/2411.08151">ps</a>, <a href="https://arxiv.org/format/2411.08151">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> New Separations and Reductions for Directed Preservers and Hopsets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hoppenworth%2C+G">Gary Hoppenworth</a>, <a href="/search/?searchtype=author&query=Xu%2C+Y">Yinzhan Xu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zixuan Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.08151v1-abstract-short" style="display: inline;"> We study distance preservers, hopsets, and shortcut sets in $n$-node, $m$-edge directed graphs, and show improved bounds and new reductions for various settings of these problems. Our first set of results is about exact and approximate distance preservers. We give the following bounds on the size of directed distance preservers with $p$ demand pairs: 1) $\tilde{O}(n^{5/6}p^{2/3} + n)$ edges for ex… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08151v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08151v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08151v1-abstract-full" style="display: none;"> We study distance preservers, hopsets, and shortcut sets in $n$-node, $m$-edge directed graphs, and show improved bounds and new reductions for various settings of these problems. Our first set of results is about exact and approximate distance preservers. We give the following bounds on the size of directed distance preservers with $p$ demand pairs: 1) $\tilde{O}(n^{5/6}p^{2/3} + n)$ edges for exact distance preservers in unweighted graphs; and 2) $惟(n^{2/3}p^{2/3})$ edges for approximate distance preservers with any given finite stretch, in graphs with arbitrary aspect ratio. Additionally, we establish a new directed-to-undirected reduction for exact distance preservers. We show that if undirected distance preservers have size $O(n^位p^渭 + n)$ for constants $位, 渭> 0$, then directed distance preservers have size $O\left( n^{\frac{1}{2-位}}p^{\frac{1+渭-位}{2-位}} + n^{1/2}p + n\right).$ As a consequence of the reduction, if current upper bounds for undirected preservers can be improved for some $p \leq n$, then so can current upper bounds for directed preservers. Our second set of results is about directed hopsets and shortcut sets. For hopsets in directed graphs, we prove that the hopbound is: 1) $惟(n^{2/9})$ for $O(m)$-size shortcut sets, improving the previous $惟(n^{1/5})$ bound [Vassilevska Williams, Xu and Xu, SODA 2024]; 2) $惟(n^{2/7})$ for $O(m)$-size exact hopsets in unweighted graphs, improving the previous $惟(n^{1/4})$ bound [Bodwin and Hoppenworth, FOCS 2023]; and 3) $惟(n^{1/2})$ for $O(n)$-size approximate hopsets with any given finite stretch, in graphs with arbitrary aspect ratio. This result establishes a separation between this setting and $O(n)$-size approximate hopsets for graphs with polynomial aspect ratio, which have hopbound $\widetilde{O}(n^{1/3})$ [Bernstein and Wein, SODA 2023]. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08151v1-abstract-full').style.display = 'none'; document.getElementById('2411.08151v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">SODA25</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07921">arXiv:2411.07921</a> <span> [<a href="https://arxiv.org/pdf/2411.07921">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> </div> </div> <p class="title is-5 mathjax"> Atomic-scale study on core-shell Cu precipitation in steels: atom probe tomography and ab initio calculations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Shen%2C+X">Xiao Shen</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">YiXu Wang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zigan Xu</a>, <a href="/search/?searchtype=author&query=Zou%2C+B">Bowen Zou</a>, <a href="/search/?searchtype=author&query=Liotti%2C+E">Enzo Liotti</a>, <a href="/search/?searchtype=author&query=Dronskowski%2C+R">Richard Dronskowski</a>, <a href="/search/?searchtype=author&query=Song%2C+W">Wenwen Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07921v1-abstract-short" style="display: inline;"> The present work investigates the atomic interactions among Cu, Al, and Ni elements in bcc-iron matrix, focusing on the formation mechanism of nano-sized core-shell Cu precipitates. Using a combination of atom probe tomography (APT), density functional theory (DFT) cal-culations, and molecular dynamics (MD) simulations, the study provides insights into the atomic-scale migration tendencies of thes… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07921v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07921v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07921v1-abstract-full" style="display: none;"> The present work investigates the atomic interactions among Cu, Al, and Ni elements in bcc-iron matrix, focusing on the formation mechanism of nano-sized core-shell Cu precipitates. Using a combination of atom probe tomography (APT), density functional theory (DFT) cal-culations, and molecular dynamics (MD) simulations, the study provides insights into the atomic-scale migration tendencies of these elements in the supersaturated solid solution sur-rounding Cu precipitate in the martensite phase of a medium-Mn steel. The results show that Ni and Al atoms were not expelled by Cu atoms but were instead attracted to the bcc iron matrix, forming a stable co-segregation in the outer shell. This phase effectively surrounded the nano-sized Cu precipitate and prevented its rapid growth, contributing to improved me-chanical properties. The findings offer a theoretical method for developing Cu-contaminated circular steels by utilizing DFT calculations to unravel bonding preferences and assess the po-tential for forming a stable precipitation phase around nano-sized Cu precipitates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07921v1-abstract-full').style.display = 'none'; document.getElementById('2411.07921v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07730">arXiv:2411.07730</a> <span> [<a href="https://arxiv.org/pdf/2411.07730">pdf</a>, <a href="https://arxiv.org/ps/2411.07730">ps</a>, <a href="https://arxiv.org/format/2411.07730">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Study of the light scalar $a_{0}(980)$ through the decay $D^{0} \to a_{0}(980)^-e^{+} 谓_{e}$ with $a_{0}(980)^- \to 畏蟺^-$ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=BESIII+Collaboration"> BESIII Collaboration</a>, <a href="/search/?searchtype=author&query=Ablikim%2C+M">M. Ablikim</a>, <a href="/search/?searchtype=author&query=Achasov%2C+M+N">M. N. Achasov</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Afedulidis%2C+O">O. Afedulidis</a>, <a href="/search/?searchtype=author&query=Ai%2C+X+C">X. C. Ai</a>, <a href="/search/?searchtype=author&query=Aliberti%2C+R">R. Aliberti</a>, <a href="/search/?searchtype=author&query=Amoroso%2C+A">A. Amoroso</a>, <a href="/search/?searchtype=author&query=An%2C+Q">Q. An</a>, <a href="/search/?searchtype=author&query=Bai%2C+Y">Y. Bai</a>, <a href="/search/?searchtype=author&query=Bakina%2C+O">O. Bakina</a>, <a href="/search/?searchtype=author&query=Balossino%2C+I">I. Balossino</a>, <a href="/search/?searchtype=author&query=Ban%2C+Y">Y. Ban</a>, <a href="/search/?searchtype=author&query=Bao%2C+H+-">H. -R. Bao</a>, <a href="/search/?searchtype=author&query=Batozskaya%2C+V">V. Batozskaya</a>, <a href="/search/?searchtype=author&query=Begzsuren%2C+K">K. Begzsuren</a>, <a href="/search/?searchtype=author&query=Berger%2C+N">N. Berger</a>, <a href="/search/?searchtype=author&query=Berlowski%2C+M">M. Berlowski</a>, <a href="/search/?searchtype=author&query=Bertani%2C+M">M. Bertani</a>, <a href="/search/?searchtype=author&query=Bettoni%2C+D">D. Bettoni</a>, <a href="/search/?searchtype=author&query=Bianchi%2C+F">F. Bianchi</a>, <a href="/search/?searchtype=author&query=Bianco%2C+E">E. Bianco</a>, <a href="/search/?searchtype=author&query=Bortone%2C+A">A. Bortone</a>, <a href="/search/?searchtype=author&query=Boyko%2C+I">I. Boyko</a>, <a href="/search/?searchtype=author&query=Briere%2C+R+A">R. A. Briere</a> , et al. (649 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07730v1-abstract-short" style="display: inline;"> Using 7.93 ${\rm fb^{-1}}$ of $e^+e^-$ collision data collected at a center-of-mass energy of 3.773 ${\rm GeV}$ with the BESIII detector, we present an analysis of the decay $D^{0} \to 畏蟺^- e^+ 谓_{e}$. The branching fraction of the decay $D^{0} \to a_{0}(980)^{-} e^+ 谓_{e}$ with $a_{0}(980)^{-} \to 畏蟺^{-}$ is measured to be $(0.86\pm0.17_{\text{stat}}\pm0.05_{\text{syst}})\times 10^{-4}$. The deca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07730v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07730v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07730v1-abstract-full" style="display: none;"> Using 7.93 ${\rm fb^{-1}}$ of $e^+e^-$ collision data collected at a center-of-mass energy of 3.773 ${\rm GeV}$ with the BESIII detector, we present an analysis of the decay $D^{0} \to 畏蟺^- e^+ 谓_{e}$. The branching fraction of the decay $D^{0} \to a_{0}(980)^{-} e^+ 谓_{e}$ with $a_{0}(980)^{-} \to 畏蟺^{-}$ is measured to be $(0.86\pm0.17_{\text{stat}}\pm0.05_{\text{syst}})\times 10^{-4}$. The decay dynamics of this process is studied with a single-pole parameterization of the hadronic form factor and the Flatt茅 formula describing the $a_0(980)$ line shape in the differential decay rate. The product of the form factor $f^{ a_0}_{+}(0)$ and the Cabibbo-Kobayashi-Maskawa matrix element $|V_{cd}|$ is determined for the first time with the result $f^{ a_0}_+(0)|V_{cd}|=0.126\pm0.013_{\rm stat}\pm0.003_{\rm syst}$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07730v1-abstract-full').style.display = 'none'; document.getElementById('2411.07730v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07489">arXiv:2411.07489</a> <span> [<a href="https://arxiv.org/pdf/2411.07489">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> </div> </div> <p class="title is-5 mathjax"> An Exploration of Parallel Imaging System for Very-low Field (50mT) MRI Scanner </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yang%2C+L">Lei Yang</a>, <a href="/search/?searchtype=author&query=He%2C+W">Wei He</a>, <a href="/search/?searchtype=author&query=Shen%2C+S">Sheng Shen</a>, <a href="/search/?searchtype=author&query=He%2C+Y">Yucheng He</a>, <a href="/search/?searchtype=author&query=Wu%2C+J">Jiamin Wu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zheng Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07489v1-abstract-short" style="display: inline;"> Reducing the scanning time of very-low field (VLF) magnetic resonance imaging (MRI) scanners, commonly employed for stroke diagnosis, can enhance patient comfort and operational efficiency. The conventional parallel imaging (PI) technique for high-field MRI should be tailored to apply here, considering the differences in the direction of the main magnetic field and the presence of noise. A VLF-spe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07489v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07489v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07489v1-abstract-full" style="display: none;"> Reducing the scanning time of very-low field (VLF) magnetic resonance imaging (MRI) scanners, commonly employed for stroke diagnosis, can enhance patient comfort and operational efficiency. The conventional parallel imaging (PI) technique for high-field MRI should be tailored to apply here, considering the differences in the direction of the main magnetic field and the presence of noise. A VLF-specific PI algorithm and phased-array coil are proposed, marking the first application of PI in VLF MRI. Reconstruction quality is enhanced by denoising undersampled k-space data using a linear-prediction based Kalman filter. Subsequently, the denoised k-space data are nonlinearly mapped from the original space onto a high-dimensional feature space, utilizing a polynomial feature mapping defined nonlinear frame. Frame parameters are calculated using auto-calibration signals (ACS) from the center k-space, and missing phase-encoding lines in the original space are estimated using acquired lines in the feature space. An 8-channel phased-array coil, designed for a vertical main magnetic field, is decoupled using geometric overlap and a low input impedance (LII) preamplifier. Healthy volunteer head imaging experiments using the proposed PI technique exhibit the lowest mean-squared-error (MSE) value and the highest peak-signal-to-noise (PSNR) and structural similarity index (SSIM) values compared to two widely used PI methods. The proposed PI technique enables the VLF MRI scanner to achieve similar image quality and a 72.5% improvement in signal-to-noise ratio (SNR) compared to fully sampled images while requiring less than 50% of the scan time. We present a PI technique tailored for VLF MRI scanner for the first time, along with potential research direction to achieve greater reduction factor. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07489v1-abstract-full').style.display = 'none'; document.getElementById('2411.07489v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Instrumentation and Measurement</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07183">arXiv:2411.07183</a> <span> [<a href="https://arxiv.org/pdf/2411.07183">pdf</a>, <a href="https://arxiv.org/format/2411.07183">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Probabilistic approach to feedback control enhances multi-legged locomotion on rugged landscapes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=He%2C+J">Juntao He</a>, <a href="/search/?searchtype=author&query=Chong%2C+B">Baxi Chong</a>, <a href="/search/?searchtype=author&query=Lin%2C+J">Jianfeng Lin</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhaochen Xu</a>, <a href="/search/?searchtype=author&query=Bagheri%2C+H">Hosain Bagheri</a>, <a href="/search/?searchtype=author&query=Flores%2C+E">Esteban Flores</a>, <a href="/search/?searchtype=author&query=Goldman%2C+D+I">Daniel I. Goldman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07183v1-abstract-short" style="display: inline;"> Achieving robust legged locomotion on complex terrains poses challenges due to the high uncertainty in robot-environment interactions. Recent advances in bipedal and quadrupedal robots demonstrate good mobility on rugged terrains but rely heavily on sensors for stability due to low static stability from a high center of mass and a narrow base of support. We hypothesize that a multi-legged robotic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07183v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07183v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07183v1-abstract-full" style="display: none;"> Achieving robust legged locomotion on complex terrains poses challenges due to the high uncertainty in robot-environment interactions. Recent advances in bipedal and quadrupedal robots demonstrate good mobility on rugged terrains but rely heavily on sensors for stability due to low static stability from a high center of mass and a narrow base of support. We hypothesize that a multi-legged robotic system can leverage morphological redundancy from additional legs to minimize sensing requirements when traversing challenging terrains. Studies suggest that a multi-legged system with sufficient legs can reliably navigate noisy landscapes without sensing and control, albeit at a low speed of up to 0.1 body lengths per cycle (BLC). However, the control framework to enhance speed on challenging terrains remains underexplored due to the complex environmental interactions, making it difficult to identify the key parameters to control in these high-degree-of-freedom systems. Here, we present a bio-inspired vertical body undulation wave as a novel approach to mitigate environmental disturbances affecting robot speed, supported by experiments and probabilistic models. Finally, we introduce a control framework which monitors foot-ground contact patterns on rugose landscapes using binary foot-ground contact sensors to estimate terrain rugosity. The controller adjusts the vertical body wave based on the deviation of the limb's averaged actual-to-ideal foot-ground contact ratio, achieving a significant enhancement of up to 0.235 BLC on rugose laboratory terrain. We observed a $\sim$ 50\% increase in speed and a $\sim$ 40\% reduction in speed variance compared to the open-loop controller. Additionally, the controller operates in complex terrains outside the lab, including pine straw, robot-sized rocks, mud, and leaves. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07183v1-abstract-full').style.display = 'none'; document.getElementById('2411.07183v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Robotics (T-RO)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07133">arXiv:2411.07133</a> <span> [<a href="https://arxiv.org/pdf/2411.07133">pdf</a>, <a href="https://arxiv.org/format/2411.07133">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Stronger Models are NOT Stronger Teachers for Instruction Tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhangchen Xu</a>, <a href="/search/?searchtype=author&query=Jiang%2C+F">Fengqing Jiang</a>, <a href="/search/?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/?searchtype=author&query=Lin%2C+B+Y">Bill Yuchen Lin</a>, <a href="/search/?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07133v2-abstract-short" style="display: inline;"> Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs heavily rely on the instruction datasets used for tuning. Recently, synthetic instruction datasets have emerged as an economically viable solution to provide LLMs diverse and high-quality instructions. However, existing app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07133v2-abstract-full').style.display = 'inline'; document.getElementById('2411.07133v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07133v2-abstract-full" style="display: none;"> Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs heavily rely on the instruction datasets used for tuning. Recently, synthetic instruction datasets have emerged as an economically viable solution to provide LLMs diverse and high-quality instructions. However, existing approaches typically assume that larger or stronger models are stronger teachers for instruction tuning, and hence simply adopt these models as response generators to the synthetic instructions. In this paper, we challenge this commonly-adopted assumption. Our extensive experiments across five base models and twenty response generators reveal that larger and stronger models are not necessarily stronger teachers of smaller models. We refer to this phenomenon as the Larger Models' Paradox. We observe that existing metrics cannot precisely predict the effectiveness of response generators since they ignore the compatibility between teachers and base models being fine-tuned. We thus develop a novel metric, named as Compatibility-Adjusted Reward (CAR) to measure the effectiveness of response generators. Our experiments across five base models demonstrate that CAR outperforms almost all baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07133v2-abstract-full').style.display = 'none'; document.getElementById('2411.07133v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07050">arXiv:2411.07050</a> <span> [<a href="https://arxiv.org/pdf/2411.07050">pdf</a>, <a href="https://arxiv.org/format/2411.07050">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> FedCVD: The First Real-World Federated Learning Benchmark on Cardiovascular Disease Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yukun Zhang</a>, <a href="/search/?searchtype=author&query=Chen%2C+G">Guanzhong Chen</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zenglin Xu</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jianyong Wang</a>, <a href="/search/?searchtype=author&query=Zeng%2C+D">Dun Zeng</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Junfan Li</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jinghua Wang</a>, <a href="/search/?searchtype=author&query=Qi%2C+Y">Yuan Qi</a>, <a href="/search/?searchtype=author&query=King%2C+I">Irwin King</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07050v1-abstract-short" style="display: inline;"> Cardiovascular diseases (CVDs) are currently the leading cause of death worldwide, highlighting the critical need for early diagnosis and treatment. Machine learning (ML) methods can help diagnose CVDs early, but their performance relies on access to substantial data with high quality. However, the sensitive nature of healthcare data often restricts individual clinical institutions from sharing da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07050v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07050v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07050v1-abstract-full" style="display: none;"> Cardiovascular diseases (CVDs) are currently the leading cause of death worldwide, highlighting the critical need for early diagnosis and treatment. Machine learning (ML) methods can help diagnose CVDs early, but their performance relies on access to substantial data with high quality. However, the sensitive nature of healthcare data often restricts individual clinical institutions from sharing data to train sufficiently generalized and unbiased ML models. Federated Learning (FL) is an emerging approach, which offers a promising solution by enabling collaborative model training across multiple participants without compromising the privacy of the individual data owners. However, to the best of our knowledge, there has been limited prior research applying FL to the cardiovascular disease domain. Moreover, existing FL benchmarks and datasets are typically simulated and may fall short of replicating the complexity of natural heterogeneity found in realistic datasets that challenges current FL algorithms. To address these gaps, this paper presents the first real-world FL benchmark for cardiovascular disease detection, named FedCVD. This benchmark comprises two major tasks: electrocardiogram (ECG) classification and echocardiogram (ECHO) segmentation, based on naturally scattered datasets constructed from the CVD data of seven institutions. Our extensive experiments on these datasets reveal that FL faces new challenges with real-world non-IID and long-tail data. The code and datasets of FedCVD are available https://github.com/SMILELab-FL/FedCVD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07050v1-abstract-full').style.display = 'none'; document.getElementById('2411.07050v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06899">arXiv:2411.06899</a> <span> [<a href="https://arxiv.org/pdf/2411.06899">pdf</a>, <a href="https://arxiv.org/format/2411.06899">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> LongSafetyBench: Long-Context LLMs Struggle with Safety Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Huang%2C+M">Mianqiu Huang</a>, <a href="/search/?searchtype=author&query=Liu%2C+X">Xiaoran Liu</a>, <a href="/search/?searchtype=author&query=Zhou%2C+S">Shaojun Zhou</a>, <a href="/search/?searchtype=author&query=Zhang%2C+M">Mozhi Zhang</a>, <a href="/search/?searchtype=author&query=Tan%2C+C">Chenkun Tan</a>, <a href="/search/?searchtype=author&query=Wang%2C+P">Pengyu Wang</a>, <a href="/search/?searchtype=author&query=Guo%2C+Q">Qipeng Guo</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhe Xu</a>, <a href="/search/?searchtype=author&query=Li%2C+L">Linyang Li</a>, <a href="/search/?searchtype=author&query=Lei%2C+Z">Zhikai Lei</a>, <a href="/search/?searchtype=author&query=Li%2C+L">Linlin Li</a>, <a href="/search/?searchtype=author&query=Liu%2C+Q">Qun Liu</a>, <a href="/search/?searchtype=author&query=Zhou%2C+Y">Yaqian Zhou</a>, <a href="/search/?searchtype=author&query=Qiu%2C+X">Xipeng Qiu</a>, <a href="/search/?searchtype=author&query=Huang%2C+X">Xuanjing Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06899v1-abstract-short" style="display: inline;"> With the development of large language models (LLMs), the sequence length of these models continues to increase, drawing significant attention to long-context language models. However, the evaluation of these models has been primarily limited to their capabilities, with a lack of research focusing on their safety. Existing work, such as ManyShotJailbreak, has to some extent demonstrated that long-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06899v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06899v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06899v1-abstract-full" style="display: none;"> With the development of large language models (LLMs), the sequence length of these models continues to increase, drawing significant attention to long-context language models. However, the evaluation of these models has been primarily limited to their capabilities, with a lack of research focusing on their safety. Existing work, such as ManyShotJailbreak, has to some extent demonstrated that long-context language models can exhibit safety concerns. However, the methods used are limited and lack comprehensiveness. In response, we introduce \textbf{LongSafetyBench}, the first benchmark designed to objectively and comprehensively evaluate the safety of long-context models. LongSafetyBench consists of 10 task categories, with an average length of 41,889 words. After testing eight long-context language models on LongSafetyBench, we found that existing models generally exhibit insufficient safety capabilities. The proportion of safe responses from most mainstream long-context LLMs is below 50\%. Moreover, models' safety performance in long-context scenarios does not always align with that in short-context scenarios. Further investigation revealed that long-context models tend to overlook harmful content within lengthy texts. We also proposed a simple yet effective solution, allowing open-source models to achieve performance comparable to that of top-tier closed-source models. We believe that LongSafetyBench can serve as a valuable benchmark for evaluating the safety capabilities of long-context language models. We hope that our work will encourage the broader community to pay attention to the safety of long-context models and contribute to the development of solutions to improve the safety of long-context LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06899v1-abstract-full').style.display = 'none'; document.getElementById('2411.06899v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06407">arXiv:2411.06407</a> <span> [<a href="https://arxiv.org/pdf/2411.06407">pdf</a>, <a href="https://arxiv.org/format/2411.06407">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Error-mitigated initialization of surface codes with non-Pauli stabilizers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=He%2C+Z">Zhi-Cheng He</a>, <a href="/search/?searchtype=author&query=Xue%2C+Z">Zheng-Yuan Xue</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06407v2-abstract-short" style="display: inline;"> Quantum error correction represents a significant milestone in large-scale quantum computing, with the surface code being a prominent strategy due to its high error threshold and experimental feasibility. However, it is challenging to implement non-Clifford logical gates in a fault-tolerant way with low overhead, through the conventional magic state distillation technique. Here, we enhance the per… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06407v2-abstract-full').style.display = 'inline'; document.getElementById('2411.06407v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06407v2-abstract-full" style="display: none;"> Quantum error correction represents a significant milestone in large-scale quantum computing, with the surface code being a prominent strategy due to its high error threshold and experimental feasibility. However, it is challenging to implement non-Clifford logical gates in a fault-tolerant way with low overhead, through the conventional magic state distillation technique. Here, we enhance the performance of the conventional surface code by incorporating non-Pauli stabilizers and introduce two innovative initialization protocols. Our approach enhances the fidelity of the initialization of non-Clifford logical state by avoiding unprotected operations before the encoding process. This improved fidelity of the initialization of non-Clifford logical states reduces the necessary number of logical qubits for precise state distillation, ultimately decreasing the overall resource overhead. Furthermore, we demonstrate the ability to entangle logical qubits in non-Pauli and Pauli bases via the lattice surgery technique. This integration enables the use of Pauli-based surface codes for computation while non-Pauli codes are employed for auxiliary qubit initialization, thus compatible with the conventional wisdom of logical Clifford operation based on the Pauli-based surface code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06407v2-abstract-full').style.display = 'none'; document.getElementById('2411.06407v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06379">arXiv:2411.06379</a> <span> [<a href="https://arxiv.org/pdf/2411.06379">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Mesoscale and Nanoscale Physics">cond-mat.mes-hall</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1063/5.0223716">10.1063/5.0223716 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Orthogonal Spin-Orbit Torque-Induced Deterministic Switching in NiO </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Qiao%2C+Y">Yixiao Qiao</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhengde Xu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhuo Xu</a>, <a href="/search/?searchtype=author&query=Yang%2C+Y">Yumeng Yang</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Z">Zhifeng Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06379v1-abstract-short" style="display: inline;"> The electrical switching of antiferromagnet (AFM) is very important for the development of ultrafast magnetic random-access memory (MRAM). This task becomes more difficult in antiferromagnetic oxide NiO which has complex anisotropy. We show that by utilizing two spin-orbit torques (SOT) from orthogonal currents, one can deterministically switch the magnetic moments of NiO in two electrical disting… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06379v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06379v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06379v1-abstract-full" style="display: none;"> The electrical switching of antiferromagnet (AFM) is very important for the development of ultrafast magnetic random-access memory (MRAM). This task becomes more difficult in antiferromagnetic oxide NiO which has complex anisotropy. We show that by utilizing two spin-orbit torques (SOT) from orthogonal currents, one can deterministically switch the magnetic moments of NiO in two electrical distinguishable states that can be read out using the spin Hall magnetoresistance. This deterministic switching relies on the symmetry of SOT on different sublattices, where the sign reversal of magnetic moments leads to constructive torques in the beginning and balanced torques in the end. In addition, we show that the easy-plane anisotropy plays a key role in the switching, which has been ignored in some previous works. The uniform magnetic dynamics in this work provides a clear physical picture in understanding the SOT switching of NiO. Furthermore, the electrical writing and reading function in our device advances the development of AFM-MRAM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06379v1-abstract-full').style.display = 'none'; document.getElementById('2411.06379v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Appl. Phys. Lett. 125, 182403 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06321">arXiv:2411.06321</a> <span> [<a href="https://arxiv.org/pdf/2411.06321">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Mesoscale and Nanoscale Physics">cond-mat.mes-hall</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.jmmm.2024.172614">10.1016/j.jmmm.2024.172614 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Anomalous switching pattern in the ferrimagnetic memory cell </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhuo Xu</a>, <a href="/search/?searchtype=author&query=Yuan%2C+Z">Zhengping Yuan</a>, <a href="/search/?searchtype=author&query=Zhang%2C+X">Xue Zhang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhengde Xu</a>, <a href="/search/?searchtype=author&query=Qiao%2C+Y">Yixiao Qiao</a>, <a href="/search/?searchtype=author&query=Yang%2C+Y">Yumeng Yang</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Z">Zhifeng Zhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06321v1-abstract-short" style="display: inline;"> Replacing the ferromagnet with ferrimagnet (FiM) in the magnetic tunnel junction (MTJ) allows faster magnetization switching in picoseconds. The operation of a memory cell that consists of the MTJ and a transistor requires reversable magnetization switching. When a constant voltage is applied, we find that the spin-transfer torque can only switch the FiM-MTJ from parallel to antiparallel state. Th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06321v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06321v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06321v1-abstract-full" style="display: none;"> Replacing the ferromagnet with ferrimagnet (FiM) in the magnetic tunnel junction (MTJ) allows faster magnetization switching in picoseconds. The operation of a memory cell that consists of the MTJ and a transistor requires reversable magnetization switching. When a constant voltage is applied, we find that the spin-transfer torque can only switch the FiM-MTJ from parallel to antiparallel state. This stems from the small switching window of FiM and the dynamic resistance variation during the magnetization switching. We find the resulting current variation can be suppressed by reducing the magnetoresistance ratio. Furthermore, we demonstrate that the switching window can be expanded by adjusting the amount of Gd in FiM. We predict that the polarity of both switching current (Jc,switch) and oscillation current (Jc,osc) reverses at the angular momentum compensation point but not the magnetization compensation point. This anomalous dynamic behavior is attributed to the different physical nature of magnetization switching and oscillation in FiM, which must be considered when designing FiM-based MRAM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06321v1-abstract-full').style.display = 'none'; document.getElementById('2411.06321v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Magnetism and Magnetic Materials 611 (2024) 172614 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06220">arXiv:2411.06220</a> <span> [<a href="https://arxiv.org/pdf/2411.06220">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applied Physics">physics.app-ph</span> </div> </div> <p class="title is-5 mathjax"> Billion-Fold Enhancement of Room-Temperature Ionic Conductivity in h-RMnO3/YSZ Heterostructures via Electric-Field-Assisted Oxygen Deficiency Engineering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yang%2C+D">Detian Yang</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Yaohua Liu</a>, <a href="/search/?searchtype=author&query=Dai%2C+L">Liang Dai</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhihang Xu</a>, <a href="/search/?searchtype=author&query=Xu%2C+X">Xiaoshan Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06220v1-abstract-short" style="display: inline;"> Oxide heterostructures provide versatile platforms for manipulating electronic and ionic conductive states. In this study, we demonstrate a remarkable billion-fold enhancement in room-temperature ionic conductivity within h-RMnO3/YSZ heterostructures, achieved through electric-field-assisted oxygen deficiency engineering. This enhancement is closely linked to substantial oxygen depletion in YSZ an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06220v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06220v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06220v1-abstract-full" style="display: none;"> Oxide heterostructures provide versatile platforms for manipulating electronic and ionic conductive states. In this study, we demonstrate a remarkable billion-fold enhancement in room-temperature ionic conductivity within h-RMnO3/YSZ heterostructures, achieved through electric-field-assisted oxygen deficiency engineering. This enhancement is closely linked to substantial oxygen depletion in YSZ and is tunable by varying the thickness of the h-RMnO3 film layer and the applied voltage bias. Our findings underscore the critical importance of interfacial design and vacancy control in enhancing ionic transport capabilities, paving the way for advanced applications in low-temperature energy harvesting, storage, and conversion technologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06220v1-abstract-full').style.display = 'none'; document.getElementById('2411.06220v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Main text: 11 pages, 5 figures; Supplmental materials: 17 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06155">arXiv:2411.06155</a> <span> [<a href="https://arxiv.org/pdf/2411.06155">pdf</a>, <a href="https://arxiv.org/format/2411.06155">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Atmospheric and Oceanic Physics">physics.ao-ph</span> </div> </div> <p class="title is-5 mathjax"> HiHa: Introducing Hierarchical Harmonic Decomposition to Implicit Neural Compression for Atmospheric Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhewen Xu</a>, <a href="/search/?searchtype=author&query=Pan%2C+B">Baoxiang Pan</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Hongliang Li</a>, <a href="/search/?searchtype=author&query=Wei%2C+X">Xiaohui Wei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06155v1-abstract-short" style="display: inline;"> The rapid development of large climate models has created the requirement of storing and transferring massive atmospheric data worldwide. Therefore, data compression is essential for meteorological research, but an efficient compression scheme capable of keeping high accuracy with high compressibility is still lacking. As an emerging technique, Implicit Neural Representation (INR) has recently acq… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06155v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06155v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06155v1-abstract-full" style="display: none;"> The rapid development of large climate models has created the requirement of storing and transferring massive atmospheric data worldwide. Therefore, data compression is essential for meteorological research, but an efficient compression scheme capable of keeping high accuracy with high compressibility is still lacking. As an emerging technique, Implicit Neural Representation (INR) has recently acquired impressive momentum and demonstrates high promise for compressing diverse natural data. However, the INR-based compression encounters a bottleneck due to the sophisticated spatio-temporal properties and variability. To address this issue, we propose Hierarchical Harmonic decomposition implicit neural compression (HiHa) for atmospheric data. HiHa firstly segments the data into multi-frequency signals through decomposition of multiple complex harmonic, and then tackles each harmonic respectively with a frequency-based hierarchical compression module consisting of sparse storage, multi-scale INR and iterative decomposition sub-modules. We additionally design a temporal residual compression module to accelerate compression by utilizing temporal continuity. Experiments depict that HiHa outperforms both mainstream compressors and other INR-based methods in both compression fidelity and capabilities, and also demonstrate that using compressed data in existing data-driven models can achieve the same accuracy as raw data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06155v1-abstract-full').style.display = 'none'; document.getElementById('2411.06155v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06135">arXiv:2411.06135</a> <span> [<a href="https://arxiv.org/pdf/2411.06135">pdf</a>, <a href="https://arxiv.org/format/2411.06135">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Online Parallel Multi-Task Relationship Learning via Alternating Direction Method of Multipliers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Li%2C+R">Ruiyu Li</a>, <a href="/search/?searchtype=author&query=Zhao%2C+P">Peilin Zhao</a>, <a href="/search/?searchtype=author&query=Li%2C+G">Guangxia Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiqiang Xu</a>, <a href="/search/?searchtype=author&query=Li%2C+X">Xuewei Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06135v1-abstract-short" style="display: inline;"> Online multi-task learning (OMTL) enhances streaming data processing by leveraging the inherent relations among multiple tasks. It can be described as an optimization problem in which a single loss function is defined for multiple tasks. Existing gradient-descent-based methods for this problem might suffer from gradient vanishing and poor conditioning issues. Furthermore, the centralized setting h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06135v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06135v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06135v1-abstract-full" style="display: none;"> Online multi-task learning (OMTL) enhances streaming data processing by leveraging the inherent relations among multiple tasks. It can be described as an optimization problem in which a single loss function is defined for multiple tasks. Existing gradient-descent-based methods for this problem might suffer from gradient vanishing and poor conditioning issues. Furthermore, the centralized setting hinders their application to online parallel optimization, which is vital to big data analytics. Therefore, this study proposes a novel OMTL framework based on the alternating direction multiplier method (ADMM), a recent breakthrough in optimization suitable for the distributed computing environment because of its decomposable and easy-to-implement nature. The relations among multiple tasks are modeled dynamically to fit the constant changes in an online scenario. In a classical distributed computing architecture with a central server, the proposed OMTL algorithm with the ADMM optimizer outperforms SGD-based approaches in terms of accuracy and efficiency. Because the central server might become a bottleneck when the data scale grows, we further tailor the algorithm to a decentralized setting, so that each node can work by only exchanging information with local neighbors. Experimental results on a synthetic and several real-world datasets demonstrate the efficiency of our methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06135v1-abstract-full').style.display = 'none'; document.getElementById('2411.06135v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accpeted by Neurocomputing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05697">arXiv:2411.05697</a> <span> [<a href="https://arxiv.org/pdf/2411.05697">pdf</a>, <a href="https://arxiv.org/format/2411.05697">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> IPMN Risk Assessment under Federated Learning Paradigm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Pan%2C+H">Hongyi Pan</a>, <a href="/search/?searchtype=author&query=Hong%2C+Z">Ziliang Hong</a>, <a href="/search/?searchtype=author&query=Durak%2C+G">Gorkem Durak</a>, <a href="/search/?searchtype=author&query=Keles%2C+E">Elif Keles</a>, <a href="/search/?searchtype=author&query=Aktas%2C+H+E">Halil Ertugrul Aktas</a>, <a href="/search/?searchtype=author&query=Taktak%2C+Y">Yavuz Taktak</a>, <a href="/search/?searchtype=author&query=Medetalibeyoglu%2C+A">Alpay Medetalibeyoglu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zheyuan Zhang</a>, <a href="/search/?searchtype=author&query=Velichko%2C+Y">Yury Velichko</a>, <a href="/search/?searchtype=author&query=Spampinato%2C+C">Concetto Spampinato</a>, <a href="/search/?searchtype=author&query=Schoots%2C+I">Ivo Schoots</a>, <a href="/search/?searchtype=author&query=Bruno%2C+M+J">Marco J. Bruno</a>, <a href="/search/?searchtype=author&query=Tiwari%2C+P">Pallavi Tiwari</a>, <a href="/search/?searchtype=author&query=Bolan%2C+C">Candice Bolan</a>, <a href="/search/?searchtype=author&query=Gonda%2C+T">Tamas Gonda</a>, <a href="/search/?searchtype=author&query=Miller%2C+F">Frank Miller</a>, <a href="/search/?searchtype=author&query=Keswani%2C+R+N">Rajesh N. Keswani</a>, <a href="/search/?searchtype=author&query=Wallace%2C+M+B">Michael B. Wallace</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/?searchtype=author&query=Bagci%2C+U">Ulas Bagci</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05697v1-abstract-short" style="display: inline;"> Accurate classification of Intraductal Papillary Mucinous Neoplasms (IPMN) is essential for identifying high-risk cases that require timely intervention. In this study, we develop a federated learning framework for multi-center IPMN classification utilizing a comprehensive pancreas MRI dataset. This dataset includes 653 T1-weighted and 656 T2-weighted MRI images, accompanied by corresponding IPMN… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05697v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05697v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05697v1-abstract-full" style="display: none;"> Accurate classification of Intraductal Papillary Mucinous Neoplasms (IPMN) is essential for identifying high-risk cases that require timely intervention. In this study, we develop a federated learning framework for multi-center IPMN classification utilizing a comprehensive pancreas MRI dataset. This dataset includes 653 T1-weighted and 656 T2-weighted MRI images, accompanied by corresponding IPMN risk scores from 7 leading medical institutions, making it the largest and most diverse dataset for IPMN classification to date. We assess the performance of DenseNet-121 in both centralized and federated settings for training on distributed data. Our results demonstrate that the federated learning approach achieves high classification accuracy comparable to centralized learning while ensuring data privacy across institutions. This work marks a significant advancement in collaborative IPMN classification, facilitating secure and high-accuracy model training across multiple centers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05697v1-abstract-full').style.display = 'none'; document.getElementById('2411.05697v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05669">arXiv:2411.05669</a> <span> [<a href="https://arxiv.org/pdf/2411.05669">pdf</a>, <a href="https://arxiv.org/format/2411.05669">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Nuclear Experiment">nucl-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Measurement of the $蠄(2S)$ to $J/蠄$ cross-section ratio as a function of centrality in PbPb collisions at $\sqrt{s_{\text{NN}}}$ = 5.02 TeV </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1128 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05669v1-abstract-short" style="display: inline;"> The dissociation of quarkonium states with different binding energies produced in heavy-ion collisions is a powerful probe for investigating the formation and properties of the quark-gluon plasma. The ratio of production cross-sections of $蠄(2S)$ and $J/蠄$ mesons times the ratio of their branching fractions into the dimuon final state is measured as a function of centrality using data collected by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05669v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05669v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05669v1-abstract-full" style="display: none;"> The dissociation of quarkonium states with different binding energies produced in heavy-ion collisions is a powerful probe for investigating the formation and properties of the quark-gluon plasma. The ratio of production cross-sections of $蠄(2S)$ and $J/蠄$ mesons times the ratio of their branching fractions into the dimuon final state is measured as a function of centrality using data collected by the LHCb detector in PbPb collisions at $\sqrt{s_{\text{NN}}}$ = 5.02 TeV. The measured ratio shows no dependence on the collision centrality, and is compared to the latest theory predictions and to the recent measurements in literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05669v1-abstract-full').style.display = 'none'; document.getElementById('2411.05669v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">All figures and tables, along with any supplementary material and additional information, are available at https://cern.ch/lhcbproject/Publications/p/LHCb-PAPER-2024-041.html (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> CERN-EP-2024-272, LHCb-PAPER-2024-041 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05571">arXiv:2411.05571</a> <span> [<a href="https://arxiv.org/pdf/2411.05571">pdf</a>, <a href="https://arxiv.org/ps/2411.05571">ps</a>, <a href="https://arxiv.org/format/2411.05571">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Complex Variables">math.CV</span> </div> </div> <p class="title is-5 mathjax"> Almansi-type decomposition and Fueter-Sce theorem for generalized partial-slice regular functions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Huo%2C+Q">Qinghai Huo</a>, <a href="/search/?searchtype=author&query=Lian%2C+P">Pan Lian</a>, <a href="/search/?searchtype=author&query=Si%2C+J">Jiajia Si</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhenghua Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05571v2-abstract-short" style="display: inline;"> Very recently, the concept of generalized partial-slice monogenic (or regular) functions has been introduced to unify the theory of monogenic functions and of slice monogenic functions over Clifford algebras. Inspired by the work of A. Perotti, in this paper we provide two analogous versions of the Almansi decomposition in this new setting. Additionally, two enhancements of the Fueter-Sce theorem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05571v2-abstract-full').style.display = 'inline'; document.getElementById('2411.05571v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05571v2-abstract-full" style="display: none;"> Very recently, the concept of generalized partial-slice monogenic (or regular) functions has been introduced to unify the theory of monogenic functions and of slice monogenic functions over Clifford algebras. Inspired by the work of A. Perotti, in this paper we provide two analogous versions of the Almansi decomposition in this new setting. Additionally, two enhancements of the Fueter-Sce theorem have been obtained for generalized partial-slice regular functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05571v2-abstract-full').style.display = 'none'; document.getElementById('2411.05571v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05546">arXiv:2411.05546</a> <span> [<a href="https://arxiv.org/pdf/2411.05546">pdf</a>, <a href="https://arxiv.org/format/2411.05546">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Plasma Physics">physics.plasm-ph</span> </div> </div> <p class="title is-5 mathjax"> Isolated Attosecond $纬$-Ray Pulse Generation with Transverse Orbital Angular Momentum Using Intense Spatiotemporal Optical Vortex Lasers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Sun%2C+F">Fengyu Sun</a>, <a href="/search/?searchtype=author&query=Xie%2C+X">Xinyu Xie</a>, <a href="/search/?searchtype=author&query=Wang%2C+W">Wenpeng Wang</a>, <a href="/search/?searchtype=author&query=Weber%2C+S">Stefan Weber</a>, <a href="/search/?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/?searchtype=author&query=Leng%2C+Y">Yuxin Leng</a>, <a href="/search/?searchtype=author&query=Li%2C+R">Ruxin Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhizhan Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05546v1-abstract-short" style="display: inline;"> An isolated attosecond vortex $纬$-ray pulse is generated by using a relativistic spatiotemporal optical vortex (STOV) laser in particle-in-cell simulations. A $\sim$ 300-attosecond electron slice with transverse orbital angular momentum (TOAM) is initially selected and accelerated by the central spatiotemporal singularity of the STOV laser. This slice then collides with the laser's reflected Gauss… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05546v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05546v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05546v1-abstract-full" style="display: none;"> An isolated attosecond vortex $纬$-ray pulse is generated by using a relativistic spatiotemporal optical vortex (STOV) laser in particle-in-cell simulations. A $\sim$ 300-attosecond electron slice with transverse orbital angular momentum (TOAM) is initially selected and accelerated by the central spatiotemporal singularity of the STOV laser. This slice then collides with the laser's reflected Gaussian-like front from a planar target, initiating nonlinear Compton scattering and resulting in an isolated, attosecond ($\sim$ 300 as), highly collimated ($\sim$ 4$\degree$), ultra-brilliant ($\sim 5\times 10^{24}$ photons/s/mm$^2$/mrad$^2$/0.1\%BW at 1 MeV) $纬$-ray pulse. This STOV-driven approach overcomes the significant beam divergence and complex two-laser requirements of prior Gaussian-based methods while introducting TOAM to the attosecond $纬$-ray pulse, which opens avenues for ultrafast imaging, nuclear excitation, and detection applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05546v1-abstract-full').style.display = 'none'; document.getElementById('2411.05546v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05281">arXiv:2411.05281</a> <span> [<a href="https://arxiv.org/pdf/2411.05281">pdf</a>, <a href="https://arxiv.org/format/2411.05281">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Fox-1 Technical Report </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hu%2C+Z">Zijian Hu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+J">Jipeng Zhang</a>, <a href="/search/?searchtype=author&query=Pan%2C+R">Rui Pan</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhaozhuo Xu</a>, <a href="/search/?searchtype=author&query=Han%2C+S">Shanshan Han</a>, <a href="/search/?searchtype=author&query=Jin%2C+H">Han Jin</a>, <a href="/search/?searchtype=author&query=Shah%2C+A+D">Alay Dilipbhai Shah</a>, <a href="/search/?searchtype=author&query=Stripelis%2C+D">Dimitris Stripelis</a>, <a href="/search/?searchtype=author&query=Yao%2C+Y">Yuhang Yao</a>, <a href="/search/?searchtype=author&query=Avestimehr%2C+S">Salman Avestimehr</a>, <a href="/search/?searchtype=author&query=He%2C+C">Chaoyang He</a>, <a href="/search/?searchtype=author&query=Zhang%2C+T">Tong Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05281v2-abstract-short" style="display: inline;"> We present Fox-1, a series of small language models (SLMs) consisting of Fox-1-1.6B and Fox-1-1.6B-Instruct-v0.1. These models are pre-trained on 3 trillion tokens of web-scraped document data and fine-tuned with 5 billion tokens of instruction-following and multi-turn conversation data. Aiming to improve the pre-training efficiency, Fox-1-1.6B model introduces a novel 3-stage data curriculum acro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05281v2-abstract-full').style.display = 'inline'; document.getElementById('2411.05281v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05281v2-abstract-full" style="display: none;"> We present Fox-1, a series of small language models (SLMs) consisting of Fox-1-1.6B and Fox-1-1.6B-Instruct-v0.1. These models are pre-trained on 3 trillion tokens of web-scraped document data and fine-tuned with 5 billion tokens of instruction-following and multi-turn conversation data. Aiming to improve the pre-training efficiency, Fox-1-1.6B model introduces a novel 3-stage data curriculum across all the training data with 2K-8K sequence length. In architecture design, Fox-1 features a deeper layer structure, an expanded vocabulary, and utilizes Grouped Query Attention (GQA), offering a performant and efficient architecture compared to other SLMs. Fox-1 achieves better or on-par performance in various benchmarks compared to StableLM-2-1.6B, Gemma-2B, Qwen1.5-1.8B, and OpenELM1.1B, with competitive inference speed and throughput. The model weights have been released under the Apache 2.0 license, where we aim to promote the democratization of LLMs and make them fully accessible to the whole open-source community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05281v2-abstract-full').style.display = 'none'; document.getElementById('2411.05281v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Base model is available at https://huggingface.co/tensoropera/Fox-1-1.6B and the instruction-tuned version is available at https://huggingface.co/tensoropera/Fox-1-1.6B-Instruct-v0.1</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05209">arXiv:2411.05209</a> <span> [<a href="https://arxiv.org/pdf/2411.05209">pdf</a>, <a href="https://arxiv.org/format/2411.05209">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ran%2C+Y">Yide Ran</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhaozhuo Xu</a>, <a href="/search/?searchtype=author&query=Yao%2C+Y">Yuhang Yao</a>, <a href="/search/?searchtype=author&query=Hu%2C+Z">Zijian Hu</a>, <a href="/search/?searchtype=author&query=Han%2C+S">Shanshan Han</a>, <a href="/search/?searchtype=author&query=Jin%2C+H">Han Jin</a>, <a href="/search/?searchtype=author&query=Shah%2C+A+D">Alay Dilipbhai Shah</a>, <a href="/search/?searchtype=author&query=Zhang%2C+J">Jipeng Zhang</a>, <a href="/search/?searchtype=author&query=Stripelis%2C+D">Dimitris Stripelis</a>, <a href="/search/?searchtype=author&query=Zhang%2C+T">Tong Zhang</a>, <a href="/search/?searchtype=author&query=Avestimehr%2C+S">Salman Avestimehr</a>, <a href="/search/?searchtype=author&query=He%2C+C">Chaoyang He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.05209v1-abstract-short" style="display: inline;"> The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external API functions to enhance their performance. However, challenges such as data scarcity, ineffective question formatting, and catastrophic forgetting hinder the development of on-device LLM agents. To tackle these issues, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05209v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05209v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05209v1-abstract-full" style="display: none;"> The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external API functions to enhance their performance. However, challenges such as data scarcity, ineffective question formatting, and catastrophic forgetting hinder the development of on-device LLM agents. To tackle these issues, we propose Alopex, a framework that enables precise on-device function calls using the Fox LLM. Alopex introduces a logic-based method for generating high-quality training data and a novel ``description-question-output'' format for fine-tuning, reducing risks of function information leakage. Additionally, a data mixing strategy is used to mitigate catastrophic forgetting, combining function call data with textbook datasets to enhance performance in various tasks. Experimental results show that Alopex improves function call accuracy and significantly reduces catastrophic forgetting, providing a robust solution for integrating function call capabilities into LLMs without manual intervention. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05209v1-abstract-full').style.display = 'none'; document.getElementById('2411.05209v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04665">arXiv:2411.04665</a> <span> [<a href="https://arxiv.org/pdf/2411.04665">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optics">physics.optics</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applied Physics">physics.app-ph</span> </div> </div> <p class="title is-5 mathjax"> PZT Optical Memristors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Li%2C+C">Chenlei Li</a>, <a href="/search/?searchtype=author&query=Yu%2C+H">Hongyan Yu</a>, <a href="/search/?searchtype=author&query=Shu%2C+T">Tao Shu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yueyang Zhang</a>, <a href="/search/?searchtype=author&query=Wen%2C+C">Chengfeng Wen</a>, <a href="/search/?searchtype=author&query=Cao%2C+H">Hengzhen Cao</a>, <a href="/search/?searchtype=author&query=Xie%2C+J">Jin Xie</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Hanwen Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zixu Xu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+G">Gong Zhang</a>, <a href="/search/?searchtype=author&query=Yu%2C+Z">Zejie Yu</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Huan Li</a>, <a href="/search/?searchtype=author&query=Liu%2C+L">Liu Liu</a>, <a href="/search/?searchtype=author&query=Shi%2C+Y">Yaocheng Shi</a>, <a href="/search/?searchtype=author&query=Qiu%2C+F">Feng Qiu</a>, <a href="/search/?searchtype=author&query=Dai%2C+D">Daoxin Dai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04665v4-abstract-short" style="display: inline;"> Optical memristors represent a monumental leap in the fusion of photonics and electronics, heralding a new era of applications from neuromorphic computing to artificial intelligence. However, current technologies are hindered by complex fabrication, limited endurance, high optical loss or low modulation depth. For the first time, we reveal optical non-volatility in thin-film Lead Zirconate Titanat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04665v4-abstract-full').style.display = 'inline'; document.getElementById('2411.04665v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04665v4-abstract-full" style="display: none;"> Optical memristors represent a monumental leap in the fusion of photonics and electronics, heralding a new era of applications from neuromorphic computing to artificial intelligence. However, current technologies are hindered by complex fabrication, limited endurance, high optical loss or low modulation depth. For the first time, we reveal optical non-volatility in thin-film Lead Zirconate Titanate (PZT) by electrically manipulating the ferroelectric domains to control the refractive index, providing a brand-new routine for optical memristors. The developed PZT optical memristors offer unprecedented advantages more than exceptional performance metrics like low loss of <2 dB/cm, high precision exceeding 6-bits, large modulation depth with an index change as large as 4.6x10-3. Additionally, these devices offer impressive stability, maintaining minimal wavelength variation for over three weeks and enduring more than 10,000 cycles, and require a mere 0.8 pJ of energy for non-volatile operation. The wafer-scale sol-gel fabrication process also ensures compatible with standardized mass fabrication processes and high scalability for photonic integration. Specially, these devices also demonstrate unique functional duality: setting above a threshold voltage enables non-volatile behaviors, below this threshold allows volatile high-speed optical modulation. This marks the first-ever optical memristor capable of performing high-speed (48 Gbps) and energy-efficient (450 fJ/bit) signal processing and non-volatile retention on a single platform, and is also the inaugural demonstration of scalable functional systems. The PZT optical memristors developed here facilitate the realization of novel paradigms for high-speed and energy-efficient optical interconnects, programmable PICs, quantum computing, neural networks, in-memory computing and brain-like architecture. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04665v4-abstract-full').style.display = 'none'; document.getElementById('2411.04665v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04549">arXiv:2411.04549</a> <span> [<a href="https://arxiv.org/pdf/2411.04549">pdf</a>, <a href="https://arxiv.org/format/2411.04549">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Vision Language Models are In-Context Value Learners </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ma%2C+Y+J">Yecheng Jason Ma</a>, <a href="/search/?searchtype=author&query=Hejna%2C+J">Joey Hejna</a>, <a href="/search/?searchtype=author&query=Wahid%2C+A">Ayzaan Wahid</a>, <a href="/search/?searchtype=author&query=Fu%2C+C">Chuyuan Fu</a>, <a href="/search/?searchtype=author&query=Shah%2C+D">Dhruv Shah</a>, <a href="/search/?searchtype=author&query=Liang%2C+J">Jacky Liang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhuo Xu</a>, <a href="/search/?searchtype=author&query=Kirmani%2C+S">Sean Kirmani</a>, <a href="/search/?searchtype=author&query=Xu%2C+P">Peng Xu</a>, <a href="/search/?searchtype=author&query=Driess%2C+D">Danny Driess</a>, <a href="/search/?searchtype=author&query=Xiao%2C+T">Ted Xiao</a>, <a href="/search/?searchtype=author&query=Tompson%2C+J">Jonathan Tompson</a>, <a href="/search/?searchtype=author&query=Bastani%2C+O">Osbert Bastani</a>, <a href="/search/?searchtype=author&query=Jayaraman%2C+D">Dinesh Jayaraman</a>, <a href="/search/?searchtype=author&query=Yu%2C+W">Wenhao Yu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+T">Tingnan Zhang</a>, <a href="/search/?searchtype=author&query=Sadigh%2C+D">Dorsa Sadigh</a>, <a href="/search/?searchtype=author&query=Xia%2C+F">Fei Xia</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04549v1-abstract-short" style="display: inline;"> Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can scale and generalize. To address these challenges, we present Generative Value Learning (\GVL), a uni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04549v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04549v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04549v1-abstract-full" style="display: none;"> Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can scale and generalize. To address these challenges, we present Generative Value Learning (\GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Naively asking a VLM to predict values for a video sequence performs poorly due to the strong temporal correlation between successive frames. Instead, GVL poses value estimation as a temporal ordering problem over shuffled video frames; this seemingly more challenging task encourages VLMs to more fully exploit their underlying semantic and temporal grounding capabilities to differentiate frames based on their perceived task progress, consequently producing significantly better value predictions. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks across diverse robot platforms, including challenging bimanual manipulation tasks. Furthermore, we demonstrate that GVL permits flexible multi-modal in-context learning via examples from heterogeneous tasks and embodiments, such as human videos. The generality of GVL enables various downstream applications pertinent to visuomotor policy learning, including dataset filtering, success detection, and advantage-weighted regression -- all without any model training or finetuning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04549v1-abstract-full').style.display = 'none'; document.getElementById('2411.04549v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project website and demo: https://generative-value-learning.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04219">arXiv:2411.04219</a> <span> [<a href="https://arxiv.org/pdf/2411.04219">pdf</a>, <a href="https://arxiv.org/format/2411.04219">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhao Xu</a>, <a href="/search/?searchtype=author&query=Yu%2C+H">Haiyang Yu</a>, <a href="/search/?searchtype=author&query=Bohde%2C+M">Montgomery Bohde</a>, <a href="/search/?searchtype=author&query=Ji%2C+S">Shuiwang Ji</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04219v1-abstract-short" style="display: inline;"> Recent advancements in equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. Using spherical harmonics (SH) and tensor products (TP), these equivariant networks gain enhanced physical understanding, like symmetries and many-body interactions. Beyond encoding physical insights, SH and TP are also crucial to represen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04219v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04219v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04219v1-abstract-full" style="display: none;"> Recent advancements in equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. Using spherical harmonics (SH) and tensor products (TP), these equivariant networks gain enhanced physical understanding, like symmetries and many-body interactions. Beyond encoding physical insights, SH and TP are also crucial to represent equivariant polynomial functions. In this work, we analyze the equivariant polynomial functions for the equivariant architecture, and introduce a novel equivariant network, named PACE. The proposed PACE utilizes edge booster and the Atomic Cluster Expansion (ACE) technique to approximate a greater number of $SE(3) \times S_n$ equivariant polynomial functions with enhanced degrees. As experimented in commonly used benchmarks, PACE demonstrates state-of-the-art performance in predicting atomic energy and force fields, with robust generalization capability across various geometric distributions under molecular dynamics (MD) across different temperature conditions. Our code is publicly available as part of the AIRS library https://github.com/divelab/AIRS/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04219v1-abstract-full').style.display = 'none'; document.getElementById('2411.04219v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Transactions on Machine Learning Research, 2024. Featured Certification </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03669">arXiv:2411.03669</a> <span> [<a href="https://arxiv.org/pdf/2411.03669">pdf</a>, <a href="https://arxiv.org/format/2411.03669">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Imagined Potential Games: A Framework for Simulating, Learning and Evaluating Interactive Behaviors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Sun%2C+L">Lingfeng Sun</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yixiao Wang</a>, <a href="/search/?searchtype=author&query=Hung%2C+P">Pin-Yun Hung</a>, <a href="/search/?searchtype=author&query=Wang%2C+C">Changhao Wang</a>, <a href="/search/?searchtype=author&query=Zhang%2C+X">Xiang Zhang</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhuo Xu</a>, <a href="/search/?searchtype=author&query=Tomizuka%2C+M">Masayoshi Tomizuka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03669v1-abstract-short" style="display: inline;"> Interacting with human agents in complex scenarios presents a significant challenge for robotic navigation, particularly in environments that necessitate both collision avoidance and collaborative interaction, such as indoor spaces. Unlike static or predictably moving obstacles, human behavior is inherently complex and unpredictable, stemming from dynamic interactions with other agents. Existing s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03669v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03669v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03669v1-abstract-full" style="display: none;"> Interacting with human agents in complex scenarios presents a significant challenge for robotic navigation, particularly in environments that necessitate both collision avoidance and collaborative interaction, such as indoor spaces. Unlike static or predictably moving obstacles, human behavior is inherently complex and unpredictable, stemming from dynamic interactions with other agents. Existing simulation tools frequently fail to adequately model such reactive and collaborative behaviors, impeding the development and evaluation of robust social navigation strategies. This paper introduces a novel framework utilizing distributed potential games to simulate human-like interactions in highly interactive scenarios. Within this framework, each agent imagines a virtual cooperative game with others based on its estimation. We demonstrate this formulation can facilitate the generation of diverse and realistic interaction patterns in a configurable manner across various scenarios. Additionally, we have developed a gym-like environment leveraging our interactive agent model to facilitate the learning and evaluation of interactive navigation algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03669v1-abstract-full').style.display = 'none'; document.getElementById('2411.03669v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 10 figures. arXiv admin note: substantial text overlap with arXiv:2310.01614</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03417">arXiv:2411.03417</a> <span> [<a href="https://arxiv.org/pdf/2411.03417">pdf</a>, <a href="https://arxiv.org/format/2411.03417">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Goldberg%2C+A">Alexander Goldberg</a>, <a href="/search/?searchtype=author&query=Ullah%2C+I">Ihsan Ullah</a>, <a href="/search/?searchtype=author&query=Khuong%2C+T+G+H">Thanh Gia Hieu Khuong</a>, <a href="/search/?searchtype=author&query=Rachmat%2C+B+K">Benedictus Kent Rachmat</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhen Xu</a>, <a href="/search/?searchtype=author&query=Guyon%2C+I">Isabelle Guyon</a>, <a href="/search/?searchtype=author&query=Shah%2C+N+B">Nihar B. Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03417v2-abstract-short" style="display: inline;"> Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an "LLM-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03417v2-abstract-full').style.display = 'inline'; document.getElementById('2411.03417v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03417v2-abstract-full" style="display: none;"> Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an "LLM-based Checklist Assistant." This assistant validates whether papers adhere to the author checklist used by NeurIPS, which includes questions to ensure compliance with research and manuscript preparation standards. Evaluation of the assistant by NeurIPS paper authors suggests that the LLM-based assistant was generally helpful in verifying checklist completion. In post-usage surveys, over 70% of authors found the assistant useful, and 70% indicate that they would revise their papers or checklist responses based on its feedback. While causal attribution to the assistant is not definitive, qualitative evidence suggests that the LLM contributed to improving some submissions. Survey responses and analysis of re-submissions indicate that authors made substantive revisions to their submissions in response to specific feedback from the LLM. The experiment also highlights common issues with LLMs: inaccuracy (20/52) and excessive strictness (14/52) were the most frequent issues flagged by authors. We also conduct experiments to understand potential gaming of the system, which reveal that the assistant could be manipulated to enhance scores through fabricated justifications, highlighting potential vulnerabilities of automated review tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03417v2-abstract-full').style.display = 'none'; document.getElementById('2411.03417v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03399">arXiv:2411.03399</a> <span> [<a href="https://arxiv.org/pdf/2411.03399">pdf</a>, <a href="https://arxiv.org/format/2411.03399">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Study of $D_{s1}(2460)^{+}\to D_{s}^{+}蟺^{+}蟺^{-}$ in $B\to {\bar{D}}^{(*)}D_{s}^{+}蟺^{+}蟺^{-}$ decays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=LHCb+collaboration"> LHCb collaboration</a>, <a href="/search/?searchtype=author&query=Aaij%2C+R">R. Aaij</a>, <a href="/search/?searchtype=author&query=Abdelmotteleb%2C+A+S+W">A. S. W. Abdelmotteleb</a>, <a href="/search/?searchtype=author&query=Beteta%2C+C+A">C. Abellan Beteta</a>, <a href="/search/?searchtype=author&query=Abudin%C3%A9n%2C+F">F. Abudin茅n</a>, <a href="/search/?searchtype=author&query=Ackernley%2C+T">T. Ackernley</a>, <a href="/search/?searchtype=author&query=Adefisoye%2C+A+A">A. A. Adefisoye</a>, <a href="/search/?searchtype=author&query=Adeva%2C+B">B. Adeva</a>, <a href="/search/?searchtype=author&query=Adinolfi%2C+M">M. Adinolfi</a>, <a href="/search/?searchtype=author&query=Adlarson%2C+P">P. Adlarson</a>, <a href="/search/?searchtype=author&query=Agapopoulou%2C+C">C. Agapopoulou</a>, <a href="/search/?searchtype=author&query=Aidala%2C+C+A">C. A. Aidala</a>, <a href="/search/?searchtype=author&query=Ajaltouni%2C+Z">Z. Ajaltouni</a>, <a href="/search/?searchtype=author&query=Akar%2C+S">S. Akar</a>, <a href="/search/?searchtype=author&query=Akiba%2C+K">K. Akiba</a>, <a href="/search/?searchtype=author&query=Albicocco%2C+P">P. Albicocco</a>, <a href="/search/?searchtype=author&query=Albrecht%2C+J">J. Albrecht</a>, <a href="/search/?searchtype=author&query=Alessio%2C+F">F. Alessio</a>, <a href="/search/?searchtype=author&query=Alexander%2C+M">M. Alexander</a>, <a href="/search/?searchtype=author&query=Aliouche%2C+Z">Z. Aliouche</a>, <a href="/search/?searchtype=author&query=Cartelle%2C+P+A">P. Alvarez Cartelle</a>, <a href="/search/?searchtype=author&query=Amalric%2C+R">R. Amalric</a>, <a href="/search/?searchtype=author&query=Amato%2C+S">S. Amato</a>, <a href="/search/?searchtype=author&query=Amey%2C+J+L">J. L. Amey</a>, <a href="/search/?searchtype=author&query=Amhis%2C+Y">Y. Amhis</a> , et al. (1124 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03399v1-abstract-short" style="display: inline;"> An amplitude analysis of the $D_{s1}(2460)^+\to D_{s}^{+}蟺^{+}蟺^{-}$ transition is performed simultaneously in $B^{0}\to D^{-}D_{s}^{+}蟺^{+}蟺^{-}$, $B^{+}\to{\bar{D}}^{0} D_{s}^{+}蟺^{+}蟺^{-}$, and $B^{0}\to D^{*-}D_{s}^{+}蟺^{+}蟺^{-}$ decays. The study is based on a data sample of proton-proton collisions recorded with the LHCb detector at centre-of-mass energies of $\sqrt{s}=7,8,$ and $13\,$TeV, c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03399v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03399v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03399v1-abstract-full" style="display: none;"> An amplitude analysis of the $D_{s1}(2460)^+\to D_{s}^{+}蟺^{+}蟺^{-}$ transition is performed simultaneously in $B^{0}\to D^{-}D_{s}^{+}蟺^{+}蟺^{-}$, $B^{+}\to{\bar{D}}^{0} D_{s}^{+}蟺^{+}蟺^{-}$, and $B^{0}\to D^{*-}D_{s}^{+}蟺^{+}蟺^{-}$ decays. The study is based on a data sample of proton-proton collisions recorded with the LHCb detector at centre-of-mass energies of $\sqrt{s}=7,8,$ and $13\,$TeV, corresponding to a total integrated luminosity of $9\,\rm{fb}^{-1}$. A clear double-peak structure is observed in the $m(蟺^{+}蟺^{-})$ spectrum of the $D_{s1}(2460)^{+}\to D_{s}^{+}蟺^{+}蟺^{-}$ decay. The data can be described either with a model including $f_0(500)$, $f_0(980)$ and $f_2(1270)$ resonances, in which the contributions of $f_0(980)$ and $f_2(1270)$ are unexpectedly large, or with a model including $f_0(500)$, a doubly charged open-charm tetraquark state $T_{c\bar{s}}^{++}$ and its isospin partner $T_{c\bar{s}}^{0}$. If the former is considered implausible, the $T_{c\bar{s}}$ states are observed with high significance, and the data are consistent with isospin symmetry. When imposing isospin constraints between the two $T_{c\bar{s}}$ states, their mass and width are determined to be $2327\pm13\pm13\,$MeV and $96\pm16\,^{+170}_{-23}\,$MeV, respectively, where the first uncertainty is statistical and the second is systematic. The mass is slightly below the $DK$ threshold, and a spin-parity of $0^+$ is favoured with high significance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03399v1-abstract-full').style.display = 'none'; document.getElementById('2411.03399v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3280/ (LHCb public pages)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LHCb-PAPER-2024-033, CERN-EP-2024-264 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03314">arXiv:2411.03314</a> <span> [<a href="https://arxiv.org/pdf/2411.03314">pdf</a>, <a href="https://arxiv.org/format/2411.03314">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Gan%2C+Z">Ziliang Gan</a>, <a href="/search/?searchtype=author&query=Lu%2C+Y">Yu Lu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+D">Dong Zhang</a>, <a href="/search/?searchtype=author&query=Li%2C+H">Haohan Li</a>, <a href="/search/?searchtype=author&query=Liu%2C+C">Che Liu</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Jian Liu</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Ji Liu</a>, <a href="/search/?searchtype=author&query=Wu%2C+H">Haipang Wu</a>, <a href="/search/?searchtype=author&query=Fu%2C+C">Chaoyou Fu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zenglin Xu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+R">Rongjunchen Zhang</a>, <a href="/search/?searchtype=author&query=Dai%2C+Y">Yong Dai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03314v1-abstract-short" style="display: inline;"> In recent years, multimodal benchmarks for general domains have guided the rapid development of multimodal models on general tasks. However, the financial field has its peculiarities. It features unique graphical images (e.g., candlestick charts, technical indicator charts) and possesses a wealth of specialized financial knowledge (e.g., futures, turnover rate). Therefore, benchmarks from general… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03314v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03314v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03314v1-abstract-full" style="display: none;"> In recent years, multimodal benchmarks for general domains have guided the rapid development of multimodal models on general tasks. However, the financial field has its peculiarities. It features unique graphical images (e.g., candlestick charts, technical indicator charts) and possesses a wealth of specialized financial knowledge (e.g., futures, turnover rate). Therefore, benchmarks from general fields often fail to measure the performance of multimodal models in the financial domain, and thus cannot effectively guide the rapid development of large financial models. To promote the development of large financial multimodal models, we propose MME-Finance, an bilingual open-ended and practical usage-oriented Visual Question Answering (VQA) benchmark. The characteristics of our benchmark are finance and expertise, which include constructing charts that reflect the actual usage needs of users (e.g., computer screenshots and mobile photography), creating questions according to the preferences in financial domain inquiries, and annotating questions by experts with 10+ years of experience in the financial industry. Additionally, we have developed a custom-designed financial evaluation system in which visual information is first introduced in the multi-modal evaluation process. Extensive experimental evaluations of 19 mainstream MLLMs are conducted to test their perception, reasoning, and cognition capabilities. The results indicate that models performing well on general benchmarks cannot do well on MME-Finance; for instance, the top-performing open-source and closed-source models obtain 65.69 (Qwen2VL-72B) and 63.18 (GPT-4o), respectively. Their performance is particularly poor in categories most relevant to finance, such as candlestick charts and technical indicator charts. In addition, we propose a Chinese version, which helps compare performance of MLLMs under a Chinese context. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03314v1-abstract-full').style.display = 'none'; document.getElementById('2411.03314v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project Page: https://hithink-research.github.io/MME-Finance/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03292">arXiv:2411.03292</a> <span> [<a href="https://arxiv.org/pdf/2411.03292">pdf</a>, <a href="https://arxiv.org/format/2411.03292">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Interaction2Code: How Far Are We From Automatic Interactive Webpage Generation? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xiao%2C+J">Jingyu Xiao</a>, <a href="/search/?searchtype=author&query=Wan%2C+Y">Yuxuan Wan</a>, <a href="/search/?searchtype=author&query=Huo%2C+Y">Yintong Huo</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiyao Xu</a>, <a href="/search/?searchtype=author&query=Lyu%2C+M+R">Michael R. Lyu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03292v1-abstract-short" style="display: inline;"> Converting webpage design into functional UI code is a critical step for building websites, which can be labor-intensive and time-consuming. To automate this design-to-code transformation process, various automated methods using learning-based networks and multi-modal large language models (MLLMs) have been proposed. However, these studies were merely evaluated on a narrow range of static web page… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03292v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03292v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03292v1-abstract-full" style="display: none;"> Converting webpage design into functional UI code is a critical step for building websites, which can be labor-intensive and time-consuming. To automate this design-to-code transformation process, various automated methods using learning-based networks and multi-modal large language models (MLLMs) have been proposed. However, these studies were merely evaluated on a narrow range of static web pages and ignored dynamic interaction elements, making them less practical for real-world website deployment. To fill in the blank, we present the first systematic investigation of MLLMs in generating interactive webpages. Specifically, we first formulate the Interaction-to-Code task and build the Interaction2Code benchmark that contains 97 unique web pages and 213 distinct interactions, spanning 15 webpage types and 30 interaction categories. We then conduct comprehensive experiments on three state-of-the-art (SOTA) MLLMs using both automatic metrics and human evaluations, thereby summarizing six findings accordingly. Our experimental results highlight the limitations of MLLMs in generating fine-grained interactive features and managing interactions with complex transformations and subtle visual modifications. We further analyze failure cases and their underlying causes, identifying 10 common failure types and assessing their severity. Additionally, our findings reveal three critical influencing factors, i.e., prompts, visual saliency, and textual descriptions, that can enhance the interaction generation performance of MLLMs. Based on these findings, we elicit implications for researchers and developers, providing a foundation for future advancements in this field. Datasets and source code are available at https://github.com/WebPAI/Interaction2Code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03292v1-abstract-full').style.display = 'none'; document.getElementById('2411.03292v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02837">arXiv:2411.02837</a> <span> [<a href="https://arxiv.org/pdf/2411.02837">pdf</a>, <a href="https://arxiv.org/format/2411.02837">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> On the Comparison between Multi-modal and Single-modal Contrastive Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Huang%2C+W">Wei Huang</a>, <a href="/search/?searchtype=author&query=Han%2C+A">Andi Han</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yongqiang Chen</a>, <a href="/search/?searchtype=author&query=Cao%2C+Y">Yuan Cao</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiqiang Xu</a>, <a href="/search/?searchtype=author&query=Suzuki%2C+T">Taiji Suzuki</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02837v1-abstract-short" style="display: inline;"> Multi-modal contrastive learning with language supervision has presented a paradigm shift in modern machine learning. By pre-training on a web-scale dataset, multi-modal contrastive learning can learn high-quality representations that exhibit impressive robustness and transferability. Despite its empirical success, the theoretical understanding is still in its infancy, especially regarding its com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02837v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02837v1-abstract-full" style="display: none;"> Multi-modal contrastive learning with language supervision has presented a paradigm shift in modern machine learning. By pre-training on a web-scale dataset, multi-modal contrastive learning can learn high-quality representations that exhibit impressive robustness and transferability. Despite its empirical success, the theoretical understanding is still in its infancy, especially regarding its comparison with single-modal contrastive learning. In this work, we introduce a feature learning theory framework that provides a theoretical foundation for understanding the differences between multi-modal and single-modal contrastive learning. Based on a data generation model consisting of signal and noise, our analysis is performed on a ReLU network trained with the InfoMax objective function. Through a trajectory-based optimization analysis and generalization characterization on downstream tasks, we identify the critical factor, which is the signal-to-noise ratio (SNR), that impacts the generalizability in downstream tasks of both multi-modal and single-modal contrastive learning. Through the cooperation between the two modalities, multi-modal learning can achieve better feature learning, leading to improvements in performance in downstream tasks compared to single-modal learning. Our analysis provides a unified framework that can characterize the optimization and generalization of both single-modal and multi-modal contrastive learning. Empirical experiments on both synthetic and real-world datasets further consolidate our theoretical findings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02837v1-abstract-full').style.display = 'none'; document.getElementById('2411.02837v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">51pages, 1 figure, 1 table</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> NeurIPS 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02796">arXiv:2411.02796</a> <span> [<a href="https://arxiv.org/pdf/2411.02796">pdf</a>, <a href="https://arxiv.org/format/2411.02796">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> </div> </div> <p class="title is-5 mathjax"> Specialized Foundation Models Struggle to Beat Supervised Baselines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Zongzhe Xu</a>, <a href="/search/?searchtype=author&query=Gupta%2C+R">Ritvik Gupta</a>, <a href="/search/?searchtype=author&query=Cheng%2C+W">Wenduo Cheng</a>, <a href="/search/?searchtype=author&query=Shen%2C+A">Alexander Shen</a>, <a href="/search/?searchtype=author&query=Shen%2C+J">Junhong Shen</a>, <a href="/search/?searchtype=author&query=Talwalkar%2C+A">Ameet Talwalkar</a>, <a href="/search/?searchtype=author&query=Khodak%2C+M">Mikhail Khodak</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02796v1-abstract-short" style="display: inline;"> Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and beyond. Has this achieved what the original FMs accomplished, i.e. the supplanting of traditional supervised learning in their domains? To answer we look at thre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02796v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02796v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02796v1-abstract-full" style="display: none;"> Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and beyond. Has this achieved what the original FMs accomplished, i.e. the supplanting of traditional supervised learning in their domains? To answer we look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow: model development, hyperparameter tuning, and training, all using only data from the target task. Across these three specialized domains, we find that it is consistently possible to train simple supervised models -- no more complicated than a lightly modified wide ResNet or UNet -- that match or even outperform the latest foundation models. Our work demonstrates that the benefits of large-scale pretraining have yet to be realized in many specialized areas, reinforces the need to compare new FMs to strong, well-tuned baselines, and introduces two new, easy-to-use, open-source, and automated workflows for doing so. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02796v1-abstract-full').style.display = 'none'; document.getElementById('2411.02796v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The first two authors contributed equally. The order was determined by coin flip</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02414">arXiv:2411.02414</a> <span> [<a href="https://arxiv.org/pdf/2411.02414">pdf</a>, <a href="https://arxiv.org/format/2411.02414">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Fairness Evaluation with Item Response Theory </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Xu%2C+Z">Ziqi Xu</a>, <a href="/search/?searchtype=author&query=Kandanaarachchi%2C+S">Sevvandi Kandanaarachchi</a>, <a href="/search/?searchtype=author&query=Ong%2C+C+S">Cheng Soon Ong</a>, <a href="/search/?searchtype=author&query=Ntoutsi%2C+E">Eirini Ntoutsi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.02414v1-abstract-short" style="display: inline;"> Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this context, discrimination specifically refers to how effectively a question distinguishes between students of different ability levels, and it does not carry any connotation related to fairness. In recent years, IRT has been s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02414v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02414v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02414v1-abstract-full" style="display: none;"> Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this context, discrimination specifically refers to how effectively a question distinguishes between students of different ability levels, and it does not carry any connotation related to fairness. In recent years, IRT has been successfully used to evaluate the predictive performance of Machine Learning (ML) models, but this paper marks its first application in fairness evaluation. In this paper, we propose a novel Fair-IRT framework to evaluate a set of predictive models on a set of individuals, while simultaneously eliciting specific parameters, namely, the ability to make fair predictions (a feature of predictive models), as well as the discrimination and difficulty of individuals that affect the prediction results. Furthermore, we conduct a series of experiments to comprehensively understand the implications of these parameters for fairness evaluation. Detailed explanations for item characteristic curves (ICCs) are provided for particular individuals. We propose the flatness of ICCs to disentangle the unfairness between individuals and predictive models. The experiments demonstrate the effectiveness of this framework as a fairness evaluation tool. Two real-world case studies illustrate its potential application in evaluating fairness in both classification and regression tasks. Our paper aligns well with the Responsible Web track by proposing a Fair-IRT framework to evaluate fairness in ML models, which directly contributes to the development of a more inclusive, equitable, and trustworthy AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02414v1-abstract-full').style.display = 'none'; document.getElementById('2411.02414v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01992">arXiv:2411.01992</a> <span> [<a href="https://arxiv.org/pdf/2411.01992">pdf</a>, <a href="https://arxiv.org/ps/2411.01992">ps</a>, <a href="https://arxiv.org/format/2411.01992">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> </div> </div> <p class="title is-5 mathjax"> Ask, and it shall be given: Turing completeness of prompting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Qiu%2C+R">Ruizhong Qiu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhe Xu</a>, <a href="/search/?searchtype=author&query=Bao%2C+W">Wenxuan Bao</a>, <a href="/search/?searchtype=author&query=Tong%2C+H">Hanghang Tong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01992v1-abstract-short" style="display: inline;"> Since the success of GPT, large language models (LLMs) have been revolutionizing machine learning and have initiated the so-called LLM prompting paradigm. In the era of LLMs, people train a single general-purpose LLM and provide the LLM with different prompts to perform different tasks. However, such empirical success largely lacks theoretical understanding. Here, we present the first theoretical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01992v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01992v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01992v1-abstract-full" style="display: none;"> Since the success of GPT, large language models (LLMs) have been revolutionizing machine learning and have initiated the so-called LLM prompting paradigm. In the era of LLMs, people train a single general-purpose LLM and provide the LLM with different prompts to perform different tasks. However, such empirical success largely lacks theoretical understanding. Here, we present the first theoretical study on the LLM prompting paradigm to the best of our knowledge. In this work, we show that prompting is in fact Turing-complete: there exists a finite-size Transformer such that for any computable function, there exists a corresponding prompt following which the Transformer computes the function. Furthermore, we show that even though we use only a single finite-size Transformer, it can still achieve nearly the same complexity bounds as that of the class of all unbounded-size Transformers. Overall, our result reveals that prompting can enable a single finite-size Transformer to be efficiently universal, which establishes a theoretical underpinning for prompt engineering in practice. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01992v1-abstract-full').style.display = 'none'; document.getElementById('2411.01992v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Xu%2C+Z&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository