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 1,876 results for author: <span class="mathjax">Liu, Q</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/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Liu%2C+Q">Search in all archives.</a> <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="Liu, Q"> </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=Liu%2C+Q&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="Liu, Q"> <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=Liu%2C+Q&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&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/2411.14384">arXiv:2411.14384</a> <span> [<a href="https://arxiv.org/pdf/2411.14384">pdf</a>, <a href="https://arxiv.org/format/2411.14384">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="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cai%2C+Y">Yuanhao Cai</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">He Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yixun Liang</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+M">Mengwei Ren</a>, <a href="/search/cs?searchtype=author&query=Luan%2C+F">Fujun Luan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qing Liu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S+Y">Soo Ye Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianming Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhifei Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yuqian Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zhe Lin</a>, <a href="/search/cs?searchtype=author&query=Yuille%2C+A">Alan Yuille</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="2411.14384v1-abstract-short" style="display: inline;"> Existing feed-forward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric prompt images. In this paper, we propose a novel single-stage 3D diffusion model, DiffusionGS, for object and scene generation from a single view. DiffusionGS directly out… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14384v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14384v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14384v1-abstract-full" style="display: none;"> Existing feed-forward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric prompt images. In this paper, we propose a novel single-stage 3D diffusion model, DiffusionGS, for object and scene generation from a single view. DiffusionGS directly outputs 3D Gaussian point clouds at each timestep to enforce view consistency and allow the model to generate robustly given prompt views of any directions, beyond object-centric inputs. Plus, to improve the capability and generalization ability of DiffusionGS, we scale up 3D training data by developing a scene-object mixed training strategy. Experiments show that our method enjoys better generation quality (2.20 dB higher in PSNR and 23.25 lower in FID) and over 5x faster speed (~6s on an A100 GPU) than SOTA methods. The user study and text-to-3D applications also reveals the practical values of our method. Our Project page at https://caiyuanhao1998.github.io/project/DiffusionGS/ shows the video and interactive generation results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14384v1-abstract-full').style.display = 'none'; document.getElementById('2411.14384v1-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> 21 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">A novel one-stage 3DGS-based diffusion generates objects and scenes from a single view in ~6 seconds</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14046">arXiv:2411.14046</a> <span> [<a href="https://arxiv.org/pdf/2411.14046">pdf</a>, <a href="https://arxiv.org/format/2411.14046">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"> REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qingxiang Liu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+S">Sheng Sun</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiaolong Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Min Liu</a>, <a href="/search/cs?searchtype=author&query=Bilal%2C+M">Muhammad Bilal</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuwei Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xujing Li</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Y">Yu Zheng</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="2411.14046v1-abstract-short" style="display: inline;"> Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods adopt offline learning which may yield subpar performance, when concept drift occurs, i.e., distributions of historical and future data vary. Online learning can… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14046v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14046v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14046v1-abstract-full" style="display: none;"> Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods adopt offline learning which may yield subpar performance, when concept drift occurs, i.e., distributions of historical and future data vary. Online learning can detect concept drift during model training, thus more applicable to TFF. Nevertheless, the existing federated online learning method for TFF fails to efficiently solve the concept drift problem and causes tremendous computing and communication overhead. Therefore, we propose a novel method named Resource-Efficient Federated Online Learning (REFOL) for TFF, which guarantees prediction performance in a communication-lightweight and computation-efficient way. Specifically, we design a data-driven client participation mechanism to detect the occurrence of concept drift and determine clients' participation necessity. Subsequently, we propose an adaptive online optimization strategy, which guarantees prediction performance and meanwhile avoids meaningless model updates. Then, a graph convolution-based model aggregation mechanism is designed, aiming to assess participants' contribution based on spatial correlation without importing extra communication and computing consumption on clients. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of REFOL in terms of prediction improvement and resource economization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14046v1-abstract-full').style.display = 'none'; document.getElementById('2411.14046v1-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> 21 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/2411.13902">arXiv:2411.13902</a> <span> [<a href="https://arxiv.org/pdf/2411.13902">pdf</a>, <a href="https://arxiv.org/format/2411.13902">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> </div> </div> <p class="title is-5 mathjax"> PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bao%2C+Z">Zhijie Bao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qingyun Liu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Y">Ying Guo</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Z">Zhengqiang Ye</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+J">Jun Shen</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+S">Shirong Xie</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Jiajie Peng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xuanjing Huang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Z">Zhongyu 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="2411.13902v1-abstract-short" style="display: inline;"> In China, receptionist nurses face overwhelming workloads in outpatient settings, limiting their time and attention for each patient and ultimately reducing service quality. In this paper, we present the Personalized Intelligent Outpatient Reception System (PIORS). This system integrates an LLM-based reception nurse and a collaboration between LLM and hospital information system (HIS) into real ou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13902v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13902v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13902v1-abstract-full" style="display: none;"> In China, receptionist nurses face overwhelming workloads in outpatient settings, limiting their time and attention for each patient and ultimately reducing service quality. In this paper, we present the Personalized Intelligent Outpatient Reception System (PIORS). This system integrates an LLM-based reception nurse and a collaboration between LLM and hospital information system (HIS) into real outpatient reception setting, aiming to deliver personalized, high-quality, and efficient reception services. Additionally, to enhance the performance of LLMs in real-world healthcare scenarios, we propose a medical conversational data generation framework named Service Flow aware Medical Scenario Simulation (SFMSS), aiming to adapt the LLM to the real-world environments and PIORS settings. We evaluate the effectiveness of PIORS and SFMSS through automatic and human assessments involving 15 users and 15 clinical experts. The results demonstrate that PIORS-Nurse outperforms all baselines, including the current state-of-the-art model GPT-4o, and aligns with human preferences and clinical needs. Further details and demo can be found at https://github.com/FudanDISC/PIORS <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13902v1-abstract-full').style.display = 'none'; document.getElementById('2411.13902v1-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> 21 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/2411.13580">arXiv:2411.13580</a> <span> [<a href="https://arxiv.org/pdf/2411.13580">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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.autcon.2017.06.021">10.1016/j.autcon.2017.06.021 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Multi-Server Information-Sharing Environment for Cross-Party Collaboration on A Private Cloud </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianping Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiang Liu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhenzhong Hu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J">Jiarui Lin</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+F">Fangqiang Yu</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="2411.13580v1-abstract-short" style="display: inline;"> Interoperability remains the key problem in multi-discipline collaboration based on building information modeling (BIM). Although various methods have been proposed to solve the technical issues of interoperability, such as data sharing and data consistency; organizational issues, including data ownership and data privacy, remain unresolved to date. These organizational issues prevent different st… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13580v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13580v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13580v1-abstract-full" style="display: none;"> Interoperability remains the key problem in multi-discipline collaboration based on building information modeling (BIM). Although various methods have been proposed to solve the technical issues of interoperability, such as data sharing and data consistency; organizational issues, including data ownership and data privacy, remain unresolved to date. These organizational issues prevent different stakeholders from sharing their data due to concerns regarding losing control of the data. This study proposes a multi-server information-sharing approach on a private cloud after analyzing the requirements for cross-party collaboration to address the aforementioned issues and prepare for massive data handling in the near future. This approach adopts a global controller to track the location, ownership and privacy of the data, which are stored in different servers that are controlled by different parties. Furthermore, data consistency conventions, parallel sub-model extraction, and sub-model integration with model verification are investigated in depth to support information sharing in a distributed environment and to maintain data consistency. Thus, with this approach, the ownership and privacy of the data can be controlled by its owner while still enabling certain required data to be shared with other parties. Application of the multi-server approach for information interoperability and cross-party collaboration is illustrated using a real construction project of an airport terminal. Validation shows that the proposed approach is feasible for maintaining the ownership and privacy of the data while supporting cross-party data sharing and collaboration at the same time, thus avoiding possible legal problems regarding data copyrights or other legal issues. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13580v1-abstract-full').style.display = 'none'; document.getElementById('2411.13580v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Automation in Construction,2017 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13476">arXiv:2411.13476</a> <span> [<a href="https://arxiv.org/pdf/2411.13476">pdf</a>, <a href="https://arxiv.org/format/2411.13476">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> </div> </div> <p class="title is-5 mathjax"> When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haonan Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+C">Chao Du</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tongyao Zhu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+C">Cunxiao Du</a>, <a href="/search/cs?searchtype=author&query=Kawaguchi%2C+K">Kenji Kawaguchi</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+T">Tianyu Pang</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="2411.13476v1-abstract-short" style="display: inline;"> Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding properties that benefit long-context training. However, we observe that using RoPE with BFloat16 format results in numerical issues, causing it to deviate from its in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13476v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13476v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13476v1-abstract-full" style="display: none;"> Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding properties that benefit long-context training. However, we observe that using RoPE with BFloat16 format results in numerical issues, causing it to deviate from its intended relative positional encoding, especially in long-context scenarios. This issue arises from BFloat16's limited precision and accumulates as context length increases, with the first token contributing significantly to this problem. To address this, we develop AnchorAttention, a plug-and-play attention method that alleviates numerical issues caused by BFloat16, improves long-context capabilities, and speeds up training. AnchorAttention reduces unnecessary attention computations, maintains semantic coherence, and boosts computational efficiency by treating the first token as a shared anchor with a consistent position ID, making it visible to all documents within the training context. Experiments on three types of LLMs demonstrate that AnchorAttention significantly improves long-context performance and reduces training time by over 50\% compared to standard full attention mechanisms, while preserving the original LLM's capabilities on general tasks. Our code is available at https://github.com/haonan3/AnchorContext. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13476v1-abstract-full').style.display = 'none'; document.getElementById('2411.13476v1-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/2411.13057">arXiv:2411.13057</a> <span> [<a href="https://arxiv.org/pdf/2411.13057">pdf</a>, <a href="https://arxiv.org/format/2411.13057">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> Branches, Assemble! Multi-Branch Cooperation Network for Large-Scale Click-Through Rate Prediction at Taobao </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xu Chen</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Z">Zida Cheng</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+Y">Yuangang Pan</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+S">Shuai Xiao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoming Liu</a>, <a href="/search/cs?searchtype=author&query=Lan%2C+J">Jinsong Lan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qingwen Liu</a>, <a href="/search/cs?searchtype=author&query=Tsang%2C+I+W">Ivor W. Tsang</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="2411.13057v1-abstract-short" style="display: inline;"> Existing click-through rate (CTR) prediction works have studied the role of feature interaction through a variety of techniques. Each interaction technique exhibits its own strength, and solely using one type could constrain the model's capability to capture the complex feature relationships, especially for industrial large-scale data with enormous users and items. Recent research shows that effec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13057v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13057v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13057v1-abstract-full" style="display: none;"> Existing click-through rate (CTR) prediction works have studied the role of feature interaction through a variety of techniques. Each interaction technique exhibits its own strength, and solely using one type could constrain the model's capability to capture the complex feature relationships, especially for industrial large-scale data with enormous users and items. Recent research shows that effective CTR models often combine an MLP network with a dedicated feature interaction network in a two-parallel structure. However, the interplay and cooperative dynamics between different streams or branches remain under-researched. In this work, we introduce a novel Multi-Branch Cooperation Network (MBCnet) which enables multiple branch networks to collaborate with each other for better complex feature interaction modeling. Specifically, MBCnet consists of three branches: the Expert-based Feature Grouping and Crossing (EFGC) branch that promotes the model's memorization ability of specific feature fields, the low rank Cross Net branch and Deep branch to enhance both explicit and implicit feature crossing for improved generalization. Among branches, a novel cooperation scheme is proposed based on two principles: branch co-teaching and moderate differentiation. Branch co-teaching encourages well-learned branches to support poorly-learned ones on specific training samples. Moderate differentiation advocates branches to maintain a reasonable level of difference in their feature representations. The cooperation strategy improves learning through mutual knowledge sharing via co-teaching and boosts the discovery of diverse feature interactions across branches. Extensive experiments on large-scale industrial datasets and online A/B test demonstrate MBCnet's superior performance, delivering a 0.09 point increase in CTR, 1.49% growth in deals, and 1.62% rise in GMV. Core codes will be released soon. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13057v1-abstract-full').style.display = 'none'; document.getElementById('2411.13057v1-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> <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</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11752">arXiv:2411.11752</a> <span> [<a href="https://arxiv.org/pdf/2411.11752">pdf</a>, <a href="https://arxiv.org/format/2411.11752">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> sMoRe: Enhancing Object Manipulation and Organization in Mixed Reality Spaces with LLMs and Generative AI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xing%2C+Y">Yunhao Xing</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Que Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingwu Wang</a>, <a href="/search/cs?searchtype=author&query=Gomez-Zara%2C+D">Diego Gomez-Zara</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="2411.11752v1-abstract-short" style="display: inline;"> In mixed reality (MR) environments, understanding space and creating virtual objects is crucial to providing an intuitive and rich user experience. This paper introduces sMoRe (Spatial Mapping and Object Rendering Environment), an MR application that combines Generative AI (GenAI) with large language models (LLMs) to assist users in creating, placing, and managing virtual objects within physical s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11752v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11752v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11752v1-abstract-full" style="display: none;"> In mixed reality (MR) environments, understanding space and creating virtual objects is crucial to providing an intuitive and rich user experience. This paper introduces sMoRe (Spatial Mapping and Object Rendering Environment), an MR application that combines Generative AI (GenAI) with large language models (LLMs) to assist users in creating, placing, and managing virtual objects within physical spaces. sMoRe allows users to use voice or typed text commands to create and place virtual objects using GenAI while specifying spatial constraints. The system leverages LLMs to interpret users' commands, analyze the current scene, and identify optimal locations. Additionally, sMoRe integrates text-to-3D generative AI to dynamically create 3D objects based on users' descriptions. Our user study demonstrates the effectiveness of sMoRe in enhancing user comprehension, interaction, and organization of the MR environment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11752v1-abstract-full').style.display = 'none'; document.getElementById('2411.11752v1-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/2411.11646">arXiv:2411.11646</a> <span> [<a href="https://arxiv.org/pdf/2411.11646">pdf</a>, <a href="https://arxiv.org/format/2411.11646">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Can Highlighting Help GitHub Maintainers Track Security Fixes? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xueqing Liu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Y">Yuchen Xiong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiushi Liu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+J">Jiangrui Zheng</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="2411.11646v1-abstract-short" style="display: inline;"> In recent years, the rapid growth of security vulnerabilities poses great challenges to tracing and managing them. For example, it was reported that the NVD database experienced significant delays due to the shortage of maintainers. Such delay creates challenges for third-party security personnel (e.g., administrators) to trace the information related to the CVE. To help security personnel trace a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11646v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11646v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11646v1-abstract-full" style="display: none;"> In recent years, the rapid growth of security vulnerabilities poses great challenges to tracing and managing them. For example, it was reported that the NVD database experienced significant delays due to the shortage of maintainers. Such delay creates challenges for third-party security personnel (e.g., administrators) to trace the information related to the CVE. To help security personnel trace a vulnerability patch, we build a retrieval system that automatically retrieves the patch in the repository. Inspired by existing work on explainable machine learning, we ask the following research question: can explanations help security maintainers make decisions in patch tracing? First, we investigate using LIME (a widely used explainable machine learning method) to highlight the rationale tokens in the commit message and code. In addition, we propose an explanation method called TfIdf-Highlight, which leverages the Tf-Idf statistics to select the most informative words in the repository and the dataset. We evaluate the effectiveness of highlighting using two experiments. First, we compare LIME and TfIdf-Highlight using a faithfulness score (i.e., sufficiency and comprehensiveness) defined for ranking. We find that TfIdf-Highlight significantly outperforms LIME's sufficiency scores by 15\% and slightly outperforms the comprehensiveness scores. Second, we conduct a blind human labeling experiment by asking the annotators to guess the patch under 3 settings (TfIdf-Highlight, LIME, and no highlight). We find that the helpfulness score for TfIdf-Highlight is higher than LIME while the labeling accuracies of LIME and TfIdf-Highlight are similar. Nevertheless, highlighting does not improve the accuracy over non-highlighting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11646v1-abstract-full').style.display = 'none'; document.getElementById('2411.11646v1-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/2411.10258">arXiv:2411.10258</a> <span> [<a href="https://arxiv.org/pdf/2411.10258">pdf</a>, <a href="https://arxiv.org/format/2411.10258">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> MDHP-Net: Detecting Injection Attacks on In-vehicle Network using Multi-Dimensional Hawkes Process and Temporal Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yanchen Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruifeng Li</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+C">Chenhong Cao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yufeng Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xingyu Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Peng Wang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+R">Runhan Feng</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="2411.10258v1-abstract-short" style="display: inline;"> The integration of intelligent and connected technologies in modern vehicles, while offering enhanced functionalities through Electronic Control Unit and interfaces like OBD-II and telematics, also exposes the vehicle's in-vehicle network (IVN) to potential cyberattacks. In this paper, we consider a specific type of cyberattack known as the injection attack. As demonstrated by empirical data from… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10258v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10258v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10258v1-abstract-full" style="display: none;"> The integration of intelligent and connected technologies in modern vehicles, while offering enhanced functionalities through Electronic Control Unit and interfaces like OBD-II and telematics, also exposes the vehicle's in-vehicle network (IVN) to potential cyberattacks. In this paper, we consider a specific type of cyberattack known as the injection attack. As demonstrated by empirical data from real-world cybersecurity adversarial competitions(available at https://mimic2024.xctf.org.cn/race/qwmimic2024 ), these injection attacks have excitation effect over time, gradually manipulating network traffic and disrupting the vehicle's normal functioning, ultimately compromising both its stability and safety. To profile the abnormal behavior of attackers, we propose a novel injection attack detector to extract long-term features of attack behavior. Specifically, we first provide a theoretical analysis of modeling the time-excitation effects of the attack using Multi-Dimensional Hawkes Process (MDHP). A gradient descent solver specifically tailored for MDHP, MDHP-GDS, is developed to accurately estimate optimal MDHP parameters. We then propose an injection attack detector, MDHP-Net, which integrates optimal MDHP parameters with MDHP-LSTM blocks to enhance temporal feature extraction. By introducing MDHP parameters, MDHP-Net captures complex temporal features that standard Long Short-Term Memory (LSTM) cannot, enriching temporal dependencies within our customized structure. Extensive evaluations demonstrate the effectiveness of our proposed detection approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10258v1-abstract-full').style.display = 'none'; document.getElementById('2411.10258v1-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/2411.08446">arXiv:2411.08446</a> <span> [<a href="https://arxiv.org/pdf/2411.08446">pdf</a>, <a href="https://arxiv.org/format/2411.08446">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nie%2C+X">Xiaonan Nie</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qibin Liu</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+F">Fangcheng Fu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shenhan Zhu</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+X">Xupeng Miao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoyang Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shouda Liu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+B">Bin Cui</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="2411.08446v1-abstract-short" style="display: inline;"> Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-of-experts (MoE) architecture is widely adopted, which consists of a gate network and a series of experts and keep the training cost constant by routing the input data to a fixed number of experts instead of all. In existing large-scale MoE… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08446v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08446v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08446v1-abstract-full" style="display: none;"> Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-of-experts (MoE) architecture is widely adopted, which consists of a gate network and a series of experts and keep the training cost constant by routing the input data to a fixed number of experts instead of all. In existing large-scale MoE training systems, experts would be distributed among different GPUs for parallelization, and thus input data requires additional all-to-all communications to access the target experts and conduct corresponding computations. However, upon evaluating the training process of three mainstream MoE models on commonly used GPU clusters, we found that the all-to-all communication ratio averaged around 45%, which significantly hinders the efficiency and scalability of training MoE models. In this paper, we propose LSH-MoE, a communication-efficient MoE training framework using locality-sensitive hashing (LSH). We first present the problems of scaling MoE training in existing systems and highlight the potential of exploiting token similarity to facilitate data compression. Then, we introduce an efficient LSH-based compression technique, which utilizes the cross-polytope hashing for rapid clustering and implements a residual-based error compensation scheme to alleviate the adverse impact of compression. To verify the effectiveness of our methods, we conduct experiments on both language models (e.g., RoBERTa, GPT, and T5) and vision models (e.g., Swin) for pre-training and fine-tuning tasks. The results demonstrate that our method substantially outperforms its counterparts across different tasks by 1.28x - 2.2x of speedup. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08446v1-abstract-full').style.display = 'none'; document.getElementById('2411.08446v1-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> 13 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 NeurIPS 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/2411.07763">arXiv:2411.07763</a> <span> [<a href="https://arxiv.org/pdf/2411.07763">pdf</a>, <a href="https://arxiv.org/format/2411.07763">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="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+F">Fangyu Lei</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jixuan Chen</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yuxiao Ye</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+R">Ruisheng Cao</a>, <a href="/search/cs?searchtype=author&query=Shin%2C+D">Dongchan Shin</a>, <a href="/search/cs?searchtype=author&query=Su%2C+H">Hongjin Su</a>, <a href="/search/cs?searchtype=author&query=Suo%2C+Z">Zhaoqing Suo</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+H">Hongcheng Gao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+W">Wenjing Hu</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+P">Pengcheng Yin</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+V">Victor Zhong</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+C">Caiming Xiong</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+R">Ruoxi Sun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sida Wang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tao Yu</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="2411.07763v1-abstract-short" style="display: inline;"> Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce Spider 2.0, an evaluation framework comprising 632 real-world text-to-SQL workflow problems derived from enterprise-level database use cases. The databases in Spide… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07763v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07763v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07763v1-abstract-full" style="display: none;"> Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce Spider 2.0, an evaluation framework comprising 632 real-world text-to-SQL workflow problems derived from enterprise-level database use cases. The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake. We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-level codebases. This challenge calls for models to interact with complex SQL workflow environments, process extremely long contexts, perform intricate reasoning, and generate multiple SQL queries with diverse operations, often exceeding 100 lines, which goes far beyond traditional text-to-SQL challenges. Our evaluations indicate that based on o1-preview, our code agent framework successfully solves only 17.0% of the tasks, compared with 91.2% on Spider 1.0 and 73.0% on BIRD. Our results on Spider 2.0 show that while language models have demonstrated remarkable performance in code generation -- especially in prior text-to-SQL benchmarks -- they require significant improvement in order to achieve adequate performance for real-world enterprise usage. Progress on Spider 2.0 represents crucial steps towards developing intelligent, autonomous, code agents for real-world enterprise settings. Our code, baseline models, and data are available at https://spider2-sql.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07763v1-abstract-full').style.display = 'none'; document.getElementById('2411.07763v1-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/2411.07740">arXiv:2411.07740</a> <span> [<a href="https://arxiv.org/pdf/2411.07740">pdf</a>, <a href="https://arxiv.org/format/2411.07740">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"> 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Liyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Hui%2C+L">Le Hui</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bo Li</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+Y">Yuchao 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="2411.07740v1-abstract-short" style="display: inline;"> Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene. Existing methods all adopt the strategy of first obtaining the global correspondence and then clustering to obtain the pose of each instance. However, due to the cluttered and occluded objects in the scene, it is difficult to obtain an accurate correspondence between the mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07740v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07740v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07740v1-abstract-full" style="display: none;"> Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene. Existing methods all adopt the strategy of first obtaining the global correspondence and then clustering to obtain the pose of each instance. However, due to the cluttered and occluded objects in the scene, it is difficult to obtain an accurate correspondence between the model point cloud and all instances in the scene. To this end, we propose a simple yet powerful 3D focusing-and-matching network for multi-instance point cloud registration by learning the multiple pair-wise point cloud registration. Specifically, we first present a 3D multi-object focusing module to locate the center of each object and generate object proposals. By using self-attention and cross-attention to associate the model point cloud with structurally similar objects, we can locate potential matching instances by regressing object centers. Then, we propose a 3D dual masking instance matching module to estimate the pose between the model point cloud and each object proposal. It performs instance mask and overlap mask masks to accurately predict the pair-wise correspondence. Extensive experiments on two public benchmarks, Scan2CAD and ROBI, show that our method achieves a new state-of-the-art performance on the multi-instance point cloud registration task. Code is available at https://github.com/zlynpu/3DFMNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07740v1-abstract-full').style.display = 'none'; document.getElementById('2411.07740v1-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">Accepted to NeurIPS 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/2411.07446">arXiv:2411.07446</a> <span> [<a href="https://arxiv.org/pdf/2411.07446">pdf</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> </div> </div> <p class="title is-5 mathjax"> Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+C">Cilin Yan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingyun Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lin Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+R">Ruihui Zhao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiaopu Wu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+K">Kai Xiong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qingsong Liu</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+G">Guoliang Kang</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+Y">Yangyang Kang</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="2411.07446v1-abstract-short" style="display: inline;"> Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve several semantically-related exemplars and concatenate them to the optimized prompts to improve the performance. However, those works only utilize the feedback… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07446v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07446v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07446v1-abstract-full" style="display: none;"> Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve several semantically-related exemplars and concatenate them to the optimized prompts to improve the performance. However, those works only utilize the feedback at the current step, ignoring historical and unseleccted feedbacks which are potentially beneficial. Moreover, the selection of exemplars only considers the general semantic relationship and may not be optimal in terms of task performance and matching with the optimized prompt. In this work, we propose an Exemplar-Guided Reflection with Memory mechanism (ERM) to realize more efficient and accurate prompt optimization. Specifically, we design an exemplar-guided reflection mechanism where the feedback generation is additionally guided by the generated exemplars. We further build two kinds of memory to fully utilize the historical feedback information and support more effective exemplar retrieval. Empirical evaluations show our method surpasses previous state-of-the-arts with less optimization steps, i.e., improving F1 score by 10.1 on LIAR dataset, and reducing half of the optimization steps on ProTeGi. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07446v1-abstract-full').style.display = 'none'; document.getElementById('2411.07446v1-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/2411.06899">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/cs?searchtype=author&query=Huang%2C+M">Mianqiu Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoran Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shaojun Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mozhi Zhang</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+C">Chenkun Tan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pengyu Wang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Q">Qipeng Guo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhe Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Linyang Li</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Z">Zhikai Lei</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Linlin Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qun Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yaqian Zhou</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+X">Xipeng Qiu</a>, <a href="/search/cs?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/2411.05354">arXiv:2411.05354</a> <span> [<a href="https://arxiv.org/pdf/2411.05354">pdf</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"> RED: Residual Estimation Diffusion for Low-Dose PET Sinogram Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ai%2C+X">Xingyu Ai</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+B">Bin Huang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+F">Fang Chen</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+L">Liu Shi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Binxuan Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shaoyu Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiegen Liu</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="2411.05354v1-abstract-short" style="display: inline;"> Recent advances in diffusion models have demonstrated exceptional performance in generative tasks across vari-ous fields. In positron emission tomography (PET), the reduction in tracer dose leads to information loss in sino-grams. Using diffusion models to reconstruct missing in-formation can improve imaging quality. Traditional diffu-sion models effectively use Gaussian noise for image re-constru… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05354v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05354v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05354v1-abstract-full" style="display: none;"> Recent advances in diffusion models have demonstrated exceptional performance in generative tasks across vari-ous fields. In positron emission tomography (PET), the reduction in tracer dose leads to information loss in sino-grams. Using diffusion models to reconstruct missing in-formation can improve imaging quality. Traditional diffu-sion models effectively use Gaussian noise for image re-constructions. However, in low-dose PET reconstruction, Gaussian noise can worsen the already sparse data by introducing artifacts and inconsistencies. To address this issue, we propose a diffusion model named residual esti-mation diffusion (RED). From the perspective of diffusion mechanism, RED uses the residual between sinograms to replace Gaussian noise in diffusion process, respectively sets the low-dose and full-dose sinograms as the starting point and endpoint of reconstruction. This mechanism helps preserve the original information in the low-dose sinogram, thereby enhancing reconstruction reliability. From the perspective of data consistency, RED introduces a drift correction strategy to reduce accumulated prediction errors during the reverse process. Calibrating the inter-mediate results of reverse iterations helps maintain the data consistency and enhances the stability of reconstruc-tion process. Experimental results show that RED effec-tively improves the quality of low-dose sinograms as well as the reconstruction results. The code is available at: https://github.com/yqx7150/RED. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05354v1-abstract-full').style.display = 'none'; document.getElementById('2411.05354v1-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/2411.05333">arXiv:2411.05333</a> <span> [<a href="https://arxiv.org/pdf/2411.05333">pdf</a>, <a href="https://arxiv.org/format/2411.05333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Error-controlled Progressive Retrieval of Scientific Data under Derivable Quantities of Interest </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xuan Wu</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+Q">Qian Gong</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jieyang Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qing Liu</a>, <a href="/search/cs?searchtype=author&query=Podhorszki%2C+N">Norbert Podhorszki</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xin Liang</a>, <a href="/search/cs?searchtype=author&query=Klasky%2C+S">Scott Klasky</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="2411.05333v1-abstract-short" style="display: inline;"> The unprecedented amount of scientific data has introduced heavy pressure on the current data storage and transmission systems. Progressive compression has been proposed to mitigate this problem, which offers data access with on-demand precision. However, existing approaches only consider precision control on primary data, leaving uncertainties on the quantities of interest (QoIs) derived from it.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05333v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05333v1-abstract-full" style="display: none;"> The unprecedented amount of scientific data has introduced heavy pressure on the current data storage and transmission systems. Progressive compression has been proposed to mitigate this problem, which offers data access with on-demand precision. However, existing approaches only consider precision control on primary data, leaving uncertainties on the quantities of interest (QoIs) derived from it. In this work, we present a progressive data retrieval framework with guaranteed error control on derivable QoIs. Our contributions are three-fold. (1) We carefully derive the theories to strictly control QoI errors during progressive retrieval. Our theory is generic and can be applied to any QoIs that can be composited by the basis of derivable QoIs proved in the paper. (2) We design and develop a generic progressive retrieval framework based on the proposed theories, and optimize it by exploring feasible progressive representations. (3) We evaluate our framework using five real-world datasets with a diverse set of QoIs. Experiments demonstrate that our framework can faithfully respect any user-specified QoI error bounds in the evaluated applications. This leads to over 2.02x performance gain in data transfer tasks compared to transferring the primary data while guaranteeing a QoI error that is less than 1E-5. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05333v1-abstract-full').style.display = 'none'; document.getElementById('2411.05333v1-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">SC'24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04905">arXiv:2411.04905</a> <span> [<a href="https://arxiv.org/pdf/2411.04905">pdf</a>, <a href="https://arxiv.org/format/2411.04905">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="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+S">Siming Huang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+T">Tianhao Cheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+K">J. K. Liu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+J">Jiaran Hao</a>, <a href="/search/cs?searchtype=author&query=Song%2C+L">Liuyihan Song</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yang Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">J. Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J+H">J. H. Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenchen Zhang</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+L">Linzheng Chai</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+R">Ruifeng Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+J">Jie Fu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Ge Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zili Wang</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+Y">Yuan Qi</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yinghui Xu</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+W">Wei Chu</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="2411.04905v2-abstract-short" style="display: inline;"> Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04905v2-abstract-full').style.display = 'inline'; document.getElementById('2411.04905v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04905v2-abstract-full" style="display: none;"> Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent training protocols, remain limited. The scarcity is due to various challenges, including resource constraints, ethical considerations, and the competitive advantages of keeping models advanced. To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community. Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental ablation results, and detailed training protocols for open scientific research. Through this comprehensive release, we identify the key ingredients for building a top-tier code LLM: (1) code optimized heuristic rules for data cleaning and methods for data deduplication, (2) recall of text corpus related to code and (3) high-quality synthetic data in both annealing and supervised fine-tuning stages. By offering this level of openness, we aim to broaden access to all aspects of a top-tier code LLM, with OpenCoder serving as both a powerful model and an open foundation to accelerate research, and enable reproducible advancements in code AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04905v2-abstract-full').style.display = 'none'; document.getElementById('2411.04905v2-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">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/2411.04899">arXiv:2411.04899</a> <span> [<a href="https://arxiv.org/pdf/2411.04899">pdf</a>, <a href="https://arxiv.org/format/2411.04899">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"> Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaoyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Ziqi Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiao Liu</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+J">Jinhan Xie</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+H">Hongtu 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="2411.04899v1-abstract-short" style="display: inline;"> In this paper, we propose a novel framework, the Sampling-guided Heterogeneous Graph Neural Network (SHT-GNN), to effectively tackle the challenge of missing data imputation in longitudinal studies. Unlike traditional methods, which often require extensive preprocessing to handle irregular or inconsistent missing data, our approach accommodates arbitrary missing data patterns while maintaining com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04899v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04899v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04899v1-abstract-full" style="display: none;"> In this paper, we propose a novel framework, the Sampling-guided Heterogeneous Graph Neural Network (SHT-GNN), to effectively tackle the challenge of missing data imputation in longitudinal studies. Unlike traditional methods, which often require extensive preprocessing to handle irregular or inconsistent missing data, our approach accommodates arbitrary missing data patterns while maintaining computational efficiency. SHT-GNN models both observations and covariates as distinct node types, connecting observation nodes at successive time points through subject-specific longitudinal subnetworks, while covariate-observation interactions are represented by attributed edges within bipartite graphs. By leveraging subject-wise mini-batch sampling and a multi-layer temporal smoothing mechanism, SHT-GNN efficiently scales to large datasets, while effectively learning node representations and imputing missing data. Extensive experiments on both synthetic and real-world datasets, including the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, demonstrate that SHT-GNN significantly outperforms existing imputation methods, even with high missing data rates. The empirical results highlight SHT-GNN's robust imputation capabilities and superior performance, particularly in the context of complex, large-scale longitudinal data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04899v1-abstract-full').style.display = 'none'; document.getElementById('2411.04899v1-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/2411.04568">arXiv:2411.04568</a> <span> [<a href="https://arxiv.org/pdf/2411.04568">pdf</a>, <a href="https://arxiv.org/format/2411.04568">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Dynamic-Attention-based EEG State Transition Modeling for Emotion Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xinke Shen</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+R">Runmin Gan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kaixuan Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Shuyi Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qingzhu Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quanying Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Dan Zhang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+S">Sen 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="2411.04568v1-abstract-short" style="display: inline;"> Electroencephalogram (EEG)-based emotion decoding can objectively quantify people's emotional state and has broad application prospects in human-computer interaction and early detection of emotional disorders. Recently emerging deep learning architectures have significantly improved the performance of EEG emotion decoding. However, existing methods still fall short of fully capturing the complex s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04568v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04568v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04568v1-abstract-full" style="display: none;"> Electroencephalogram (EEG)-based emotion decoding can objectively quantify people's emotional state and has broad application prospects in human-computer interaction and early detection of emotional disorders. Recently emerging deep learning architectures have significantly improved the performance of EEG emotion decoding. However, existing methods still fall short of fully capturing the complex spatiotemporal dynamics of neural signals, which are crucial for representing emotion processing. This study proposes a Dynamic-Attention-based EEG State Transition (DAEST) modeling method to characterize EEG spatiotemporal dynamics. The model extracts spatiotemporal components of EEG that represent multiple parallel neural processes and estimates dynamic attention weights on these components to capture transitions in brain states. The model is optimized within a contrastive learning framework for cross-subject emotion recognition. The proposed method achieved state-of-the-art performance on three publicly available datasets: FACED, SEED, and SEED-V. It achieved 75.4% accuracy in the binary classification of positive and negative emotions and 59.3% in nine-class discrete emotion classification on the FACED dataset, 88.1% in the three-class classification of positive, negative, and neutral emotions on the SEED dataset, and 73.6% in five-class discrete emotion classification on the SEED-V dataset. The learned EEG spatiotemporal patterns and dynamic transition properties offer valuable insights into neural dynamics underlying emotion processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04568v1-abstract-full').style.display = 'none'; document.getElementById('2411.04568v1-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">14 pages, 6 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/2411.03976">arXiv:2411.03976</a> <span> [<a href="https://arxiv.org/pdf/2411.03976">pdf</a>, <a href="https://arxiv.org/format/2411.03976">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"> HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ding%2C+Z">Ziyuan Ding</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yixiong Liang</a>, <a href="/search/cs?searchtype=author&query=Kan%2C+S">Shichao Kan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qing Liu</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="2411.03976v1-abstract-short" style="display: inline;"> High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling the challenge of segmenting tiny objects, recent studies have explored local-global fusion methods. These methods preserve fine details using local regions and c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03976v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03976v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03976v1-abstract-full" style="display: none;"> High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling the challenge of segmenting tiny objects, recent studies have explored local-global fusion methods. These methods preserve fine details using local regions and capture long-range context information from downscaled global images. However, the necessity of multiple forward passes inevitably incurs significant computational overhead, adversely affecting inference speed. In this paper, we propose HRDecoder, a simple High-Resolution Decoder network for fundus lesion segmentation. It integrates a high-resolution representation learning module to capture fine-grained local features and a high-resolution fusion module to fuse multi-scale predictions. Our method effectively improves the overall segmentation accuracy of fundus lesions while consuming reasonable memory and computational overhead, and maintaining satisfying inference speed. Experimental results on the IDRID and DDR datasets demonstrate the effectiveness of our method. Code is available at https://github.com/CVIU-CSU/HRDecoder. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03976v1-abstract-full').style.display = 'none'; document.getElementById('2411.03976v1-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">11 pages, 3 figures, accepted by MICCAI 2024, the revised version</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03758">arXiv:2411.03758</a> <span> [<a href="https://arxiv.org/pdf/2411.03758">pdf</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="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> </div> </div> <p class="title is-5 mathjax"> Sub-DM:Subspace Diffusion Model with Orthogonal Decomposition for MRI Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guan%2C+Y">Yu Guan</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Q">Qinrong Cai</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wei Li</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+Q">Qiuyun Fan</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+D">Dong Liang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiegen Liu</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="2411.03758v1-abstract-short" style="display: inline;"> Diffusion model-based approaches recently achieved re-markable success in MRI reconstruction, but integration into clinical routine remains challenging due to its time-consuming convergence. This phenomenon is partic-ularly notable when directly apply conventional diffusion process to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03758v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03758v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03758v1-abstract-full" style="display: none;"> Diffusion model-based approaches recently achieved re-markable success in MRI reconstruction, but integration into clinical routine remains challenging due to its time-consuming convergence. This phenomenon is partic-ularly notable when directly apply conventional diffusion process to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency and image reconstruction quality. To tackle these challenges, we introduce subspace diffusion model with orthogonal decomposition, a method (referred to as Sub-DM) that restrict the diffusion process via projections onto subspace as the k-space data distribution evolves toward noise. Particularly, the subspace diffusion model circumvents the inference challenges posed by the com-plex and high-dimensional characteristics of k-space data, so the highly compact subspace ensures that diffusion process requires only a few simple iterations to produce accurate prior information. Furthermore, the orthogonal decomposition strategy based on wavelet transform hin-ders the information loss during the migration of the vanilla diffusion process to the subspace. Considering the strate-gy is approximately reversible, such that the entire pro-cess can be reversed. As a result, it allows the diffusion processes in different spaces to refine models through a mutual feedback mechanism, enabling the learning of ac-curate prior even when dealing with complex k-space data. Comprehensive experiments on different datasets clearly demonstrate that the superiority of Sub-DM against state of-the-art methods in terms of reconstruction speed and quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03758v1-abstract-full').style.display = 'none'; document.getElementById('2411.03758v1-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">10 pages, 11 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/2411.03723">arXiv:2411.03723</a> <span> [<a href="https://arxiv.org/pdf/2411.03723">pdf</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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Zero-shot Dynamic MRI Reconstruction with Global-to-local Diffusion Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guan%2C+Y">Yu Guan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kunlong Zhang</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+Q">Qi Qi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Dong Wang</a>, <a href="/search/cs?searchtype=author&query=Ke%2C+Z">Ziwen Ke</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shaoyu Wang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+D">Dong Liang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiegen Liu</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="2411.03723v1-abstract-short" style="display: inline;"> Diffusion models have recently demonstrated considerable advancement in the generation and reconstruction of magnetic resonance imaging (MRI) data. These models exhibit great potential in handling unsampled data and reducing noise, highlighting their promise as generative models. However, their application in dynamic MRI remains relatively underexplored. This is primarily due to the substantial am… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03723v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03723v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03723v1-abstract-full" style="display: none;"> Diffusion models have recently demonstrated considerable advancement in the generation and reconstruction of magnetic resonance imaging (MRI) data. These models exhibit great potential in handling unsampled data and reducing noise, highlighting their promise as generative models. However, their application in dynamic MRI remains relatively underexplored. This is primarily due to the substantial amount of fully-sampled data typically required for training, which is difficult to obtain in dynamic MRI due to its spatio-temporal complexity and high acquisition costs. To address this challenge, we propose a dynamic MRI reconstruction method based on a time-interleaved acquisition scheme, termed the Glob-al-to-local Diffusion Model. Specifically, fully encoded full-resolution reference data are constructed by merging under-sampled k-space data from adjacent time frames, generating two distinct bulk training datasets for global and local models. The global-to-local diffusion framework alternately optimizes global information and local image details, enabling zero-shot reconstruction. Extensive experiments demonstrate that the proposed method performs well in terms of noise reduction and detail preservation, achieving reconstruction quality comparable to that of supervised approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03723v1-abstract-full').style.display = 'none'; document.getElementById('2411.03723v1-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">11 pages, 9 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/2411.03487">arXiv:2411.03487</a> <span> [<a href="https://arxiv.org/pdf/2411.03487">pdf</a>, <a href="https://arxiv.org/format/2411.03487">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"> Enhancing Exploratory Capability of Visual Navigation Using Uncertainty of Implicit Scene Representation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yichen Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiming Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhe Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hesheng Wang</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="2411.03487v1-abstract-short" style="display: inline;"> In the context of visual navigation in unknown scenes, both "exploration" and "exploitation" are equally crucial. Robots must first establish environmental cognition through exploration and then utilize the cognitive information to accomplish target searches. However, most existing methods for image-goal navigation prioritize target search over the generation of exploratory behavior. To address th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03487v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03487v1-abstract-full" style="display: none;"> In the context of visual navigation in unknown scenes, both "exploration" and "exploitation" are equally crucial. Robots must first establish environmental cognition through exploration and then utilize the cognitive information to accomplish target searches. However, most existing methods for image-goal navigation prioritize target search over the generation of exploratory behavior. To address this, we propose the Navigation with Uncertainty-driven Exploration (NUE) pipeline, which uses an implicit and compact scene representation, NeRF, as a cognitive structure. We estimate the uncertainty of NeRF and augment the exploratory ability by the uncertainty to in turn facilitate the construction of implicit representation. Simultaneously, we extract memory information from NeRF to enhance the robot's reasoning ability for determining the location of the target. Ultimately, we seamlessly combine the two generated abilities to produce navigational actions. Our pipeline is end-to-end, with the environmental cognitive structure being constructed online. Extensive experimental results on image-goal navigation demonstrate the capability of our pipeline to enhance exploratory behaviors, while also enabling a natural transition from the exploration to exploitation phase. This enables our model to outperform existing memory-based cognitive navigation structures in terms of navigation performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03487v1-abstract-full').style.display = 'none'; document.getElementById('2411.03487v1-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/2411.02818">arXiv:2411.02818</a> <span> [<a href="https://arxiv.org/pdf/2411.02818">pdf</a>, <a href="https://arxiv.org/format/2411.02818">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"> LiVOS: Light Video Object Segmentation with Gated Linear Matching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qin Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jianfeng Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhengyuan Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Linjie Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+K">Kevin Lin</a>, <a href="/search/cs?searchtype=author&query=Niethammer%2C+M">Marc Niethammer</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Lijuan Wang</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="2411.02818v1-abstract-short" style="display: inline;"> Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment the current frame via softmax attention. However, STM networks face memory limitations due to the quadratic complexity of softmax matching, restricting their applicability as video length and resolution increase. To addre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02818v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02818v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02818v1-abstract-full" style="display: none;"> Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment the current frame via softmax attention. However, STM networks face memory limitations due to the quadratic complexity of softmax matching, restricting their applicability as video length and resolution increase. To address this, we propose LiVOS, a lightweight memory network that employs linear matching via linear attention, reformulating memory matching into a recurrent process that reduces the quadratic attention matrix to a constant-size, spatiotemporal-agnostic 2D state. To enhance selectivity, we introduce gated linear matching, where a data-dependent gate matrix is multiplied with the state matrix to control what information to retain or discard. Experiments on diverse benchmarks demonstrated the effectiveness of our method. It achieved 64.8 J&F on MOSE and 85.1 J&F on DAVIS, surpassing all non-STM methods and narrowing the gap with STM-based approaches. For longer and higher-resolution videos, it matched STM-based methods with 53% less GPU memory and supports 4096p inference on a 32G consumer-grade GPU--a previously cost-prohibitive capability--opening the door for long and high-resolution video foundation models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02818v1-abstract-full').style.display = 'none'; document.getElementById('2411.02818v1-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">Code&models: https://github.com/uncbiag/LiVOS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02066">arXiv:2411.02066</a> <span> [<a href="https://arxiv.org/pdf/2411.02066">pdf</a>, <a href="https://arxiv.org/format/2411.02066">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"> Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+W">Weibo Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+L">Linan Yue</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+F">Fangzhou Yao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hao Wang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yin Gu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zheng 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="2411.02066v2-abstract-short" style="display: inline;"> Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02066v2-abstract-full').style.display = 'inline'; document.getElementById('2411.02066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02066v2-abstract-full" style="display: none;"> Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i.e., knowledge proficiency) in the context of intelligent education. The primary challenges lie in identifying implicit collaborative connections and disentangling the entangled cognitive factors of learners for improved explainability and controllability in learner Cognitive Diagnosis (CD). However, there has been no work on CD capable of simultaneously modeling collaborative and disentangled cognitive states. To address this gap, we present Coral, a Collaborative cognitive diagnosis model with disentangled representation learning. Specifically, Coral first introduces a disentangled state encoder to achieve the initial disentanglement of learners' states. Subsequently, a meticulously designed collaborative representation learning procedure captures collaborative signals. It dynamically constructs a collaborative graph of learners by iteratively searching for optimal neighbors in a context-aware manner. Using the constructed graph, collaborative information is extracted through node representation learning. Finally, a decoding process aligns the initial cognitive states and collaborative states, achieving co-disentanglement with practice performance reconstructions. Extensive experiments demonstrate the superior performance of Coral, showcasing significant improvements over state-of-the-art methods across several real-world datasets. Our code is available at https://github.com/bigdata-ustc/Coral. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02066v2-abstract-full').style.display = 'none'; document.getElementById('2411.02066v2-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">v1</span> submitted 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">Accepted by NeurIPS2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01897">arXiv:2411.01897</a> <span> [<a href="https://arxiv.org/pdf/2411.01897">pdf</a>, <a href="https://arxiv.org/format/2411.01897">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"> LE-PDE++: Mamba for accelerating PDEs Simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+A">Aoming Liang</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+Z">Zhaoyang Mu</a>, <a href="/search/cs?searchtype=author&query=liu%2C+Q">Qi liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruipeng Li</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+M">Mingming Ge</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+D">Dixia Fan</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="2411.01897v2-abstract-short" style="display: inline;"> Partial Differential Equations are foundational in modeling science and natural systems such as fluid dynamics and weather forecasting. The Latent Evolution of PDEs method is designed to address the computational intensity of classical and deep learning-based PDE solvers by proposing a scalable and efficient alternative. To enhance the efficiency and accuracy of LE-PDE, we incorporate the Mamba mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01897v2-abstract-full').style.display = 'inline'; document.getElementById('2411.01897v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01897v2-abstract-full" style="display: none;"> Partial Differential Equations are foundational in modeling science and natural systems such as fluid dynamics and weather forecasting. The Latent Evolution of PDEs method is designed to address the computational intensity of classical and deep learning-based PDE solvers by proposing a scalable and efficient alternative. To enhance the efficiency and accuracy of LE-PDE, we incorporate the Mamba model, an advanced machine learning model known for its predictive efficiency and robustness in handling complex dynamic systems with a progressive learning strategy. The LE-PDE was tested on several benchmark problems. The method demonstrated a marked reduction in computational time compared to traditional solvers and standalone deep learning models while maintaining high accuracy in predicting system behavior over time. Our method doubles the inference speed compared to the LE-PDE while retaining the same level of parameter efficiency, making it well-suited for scenarios requiring long-term predictions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01897v2-abstract-full').style.display = 'none'; document.getElementById('2411.01897v2-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">v1</span> submitted 4 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/2411.01169">arXiv:2411.01169</a> <span> [<a href="https://arxiv.org/pdf/2411.01169">pdf</a>, <a href="https://arxiv.org/format/2411.01169">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="Social and Information Networks">cs.SI</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/10.1109/TKDE.2024.3397683">10.1109/TKDE.2024.3397683 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Bi-Level Graph Structure Learning for Next POI Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shu Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiang Liu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yanqiao Zhu</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+X">Xiang Tao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengdi Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</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="2411.01169v1-abstract-short" style="display: inline;"> Next point-of-interest (POI) recommendation aims to predict a user's next destination based on sequential check-in history and a set of POI candidates. Graph neural networks (GNNs) have demonstrated a remarkable capability in this endeavor by exploiting the extensive global collaborative signals present among POIs. However, most of the existing graph-based approaches construct graph structures bas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01169v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01169v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01169v1-abstract-full" style="display: none;"> Next point-of-interest (POI) recommendation aims to predict a user's next destination based on sequential check-in history and a set of POI candidates. Graph neural networks (GNNs) have demonstrated a remarkable capability in this endeavor by exploiting the extensive global collaborative signals present among POIs. However, most of the existing graph-based approaches construct graph structures based on pre-defined heuristics, failing to consider inherent hierarchical structures of POI features such as geographical locations and visiting peaks, or suffering from noisy and incomplete structures in graphs. To address the aforementioned issues, this paper presents a novel Bi-level Graph Structure Learning (BiGSL) for next POI recommendation. BiGSL first learns a hierarchical graph structure to capture the fine-to-coarse connectivity between POIs and prototypes, and then uses a pairwise learning module to dynamically infer relationships between POI pairs and prototype pairs. Based on the learned bi-level graphs, our model then employs a multi-relational graph network that considers both POI- and prototype-level neighbors, resulting in improved POI representations. Our bi-level structure learning scheme is more robust to data noise and incompleteness, and improves the exploration ability for recommendation by alleviating sparsity issues. Experimental results on three real-world datasets demonstrate the superiority of our model over existing state-of-the-art methods, with a significant improvement in recommendation accuracy and exploration performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01169v1-abstract-full').style.display = 'none'; document.getElementById('2411.01169v1-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> 2 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 IEEE Transactions on Knowledge and Data Engineering</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 11, pp. 5695-5708, Nov. 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01158">arXiv:2411.01158</a> <span> [<a href="https://arxiv.org/pdf/2411.01158">pdf</a>, <a href="https://arxiv.org/format/2411.01158">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="Molecular Networks">q-bio.MN</span> </div> </div> <p class="title is-5 mathjax"> Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiang Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shaozhen Liu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+X">Xin Sun</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shu Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</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="2411.01158v1-abstract-short" style="display: inline;"> Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01158v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01158v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01158v1-abstract-full" style="display: none;"> Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training and molecular context information. Despite these advancements, existing methods struggle with the ineffective fine-tuning of pre-trained encoders. We attribute this issue to the imbalance between the abundance of tunable parameters and the scarcity of labeled molecules, and the lack of contextual perceptiveness in the encoders. To overcome this hurdle, we propose a parameter-efficient in-context tuning method, named Pin-Tuning. Specifically, we propose a lightweight adapter for pre-trained message passing layers (MP-Adapter) and Bayesian weight consolidation for pre-trained atom/bond embedding layers (Emb-BWC), to achieve parameter-efficient tuning while preventing over-fitting and catastrophic forgetting. Additionally, we enhance the MP-Adapters with contextual perceptiveness. This innovation allows for in-context tuning of the pre-trained encoder, thereby improving its adaptability for specific FSMPP tasks. When evaluated on public datasets, our method demonstrates superior tuning with fewer trainable parameters, improving few-shot predictive performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01158v1-abstract-full').style.display = 'none'; document.getElementById('2411.01158v1-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> 2 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 NeurIPS 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/2411.00769">arXiv:2411.00769</a> <span> [<a href="https://arxiv.org/pdf/2411.00769">pdf</a>, <a href="https://arxiv.org/format/2411.00769">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> GameGen-X: Interactive Open-world Game Video Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+H">Haoxuan Che</a>, <a href="/search/cs?searchtype=author&query=He%2C+X">Xuanhua He</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quande Liu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+C">Cheng Jin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hao Chen</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="2411.00769v1-abstract-short" style="display: inline;"> We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by simulating an extensive array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interact… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00769v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00769v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00769v1-abstract-full" style="display: none;"> We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by simulating an extensive array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, predicting and altering future content based on the current clip, thus allowing for gameplay simulation. To realize this vision, we first collected and built an Open-World Video Game Dataset from scratch. It is the first and largest dataset for open-world game video generation and control, which comprises over a million diverse gameplay video clips sampling from over 150 games with informative captions from GPT-4o. GameGen-X undergoes a two-stage training process, consisting of foundation model pre-training and instruction tuning. Firstly, the model was pre-trained via text-to-video generation and video continuation, endowing it with the capability for long-sequence, high-quality open-domain game video generation. Further, to achieve interactive controllability, we designed InstructNet to incorporate game-related multi-modal control signal experts. This allows the model to adjust latent representations based on user inputs, unifying character interaction and scene content control for the first time in video generation. During instruction tuning, only the InstructNet is updated while the pre-trained foundation model is frozen, enabling the integration of interactive controllability without loss of diversity and quality of generated video content. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00769v1-abstract-full').style.display = 'none'; document.getElementById('2411.00769v1-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> 1 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://github.com/GameGen-X/GameGen-X</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00504">arXiv:2411.00504</a> <span> [<a href="https://arxiv.org/pdf/2411.00504">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Machine Learning-Accelerated Multi-Objective Design of Fractured Geothermal Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+G">Guodong Chen</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+J+J">Jiu Jimmy Jiao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiqi Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhongzheng Wang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Y">Yaochu Jin</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="2411.00504v1-abstract-short" style="display: inline;"> Multi-objective optimization has burgeoned as a potent methodology for informed decision-making in enhanced geothermal systems, aiming to concurrently maximize economic yield, ensure enduring geothermal energy provision, and curtail carbon emissions. However, addressing a multitude of design parameters inherent in computationally intensive physics-driven simulations constitutes a formidable impedi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00504v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00504v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00504v1-abstract-full" style="display: none;"> Multi-objective optimization has burgeoned as a potent methodology for informed decision-making in enhanced geothermal systems, aiming to concurrently maximize economic yield, ensure enduring geothermal energy provision, and curtail carbon emissions. However, addressing a multitude of design parameters inherent in computationally intensive physics-driven simulations constitutes a formidable impediment for geothermal design optimization, as well as across a broad range of scientific and engineering domains. Here we report an Active Learning enhanced Evolutionary Multi-objective Optimization algorithm, integrated with hydrothermal simulations in fractured media, to enable efficient optimization of fractured geothermal systems using few model evaluations. We introduce probabilistic neural network as classifier to learns to predict the Pareto dominance relationship between candidate samples and reference samples, thereby facilitating the identification of promising but uncertain offspring solutions. We then use active learning strategy to conduct hypervolume based attention subspace search with surrogate model by iteratively infilling informative samples within local promising parameter subspace. We demonstrate its effectiveness by conducting extensive experimental tests of the integrated framework, including multi-objective benchmark functions, a fractured geothermal model and a large-scale enhanced geothermal system. Results demonstrate that the ALEMO approach achieves a remarkable reduction in required simulations, with a speed-up of 1-2 orders of magnitude (10-100 times faster) than traditional evolutionary methods, thereby enabling accelerated decision-making. Our method is poised to advance the state-of-the-art of renewable geothermal energy system and enable widespread application to accelerate the discovery of optimal designs for complex systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00504v1-abstract-full').style.display = 'none'; document.getElementById('2411.00504v1-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> 1 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/2411.00078">arXiv:2411.00078</a> <span> [<a href="https://arxiv.org/pdf/2411.00078">pdf</a>, <a href="https://arxiv.org/format/2411.00078">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/cs?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/cs?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yuankai Huo</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="2411.00078v1-abstract-short" style="display: inline;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei seg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00078v1-abstract-full" style="display: none;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei segmentation within a single organ (e.g., the kidney), remains uncertain. This paper seeks to answer this key question, "How good are we?", by thoroughly evaluating the performance of recent cell foundation models on a curated multi-center, multi-disease, and multi-species external testing dataset. Additionally, we tackle a more challenging question, "How can we improve?", by developing and assessing human-in-the-loop data enrichment strategies aimed at enhancing model performance while minimizing the reliance on pixel-level human annotation. To address the first question, we curated a multicenter, multidisease, and multispecies dataset consisting of 2,542 kidney whole slide images (WSIs). Three state-of-the-art (SOTA) cell foundation models-Cellpose, StarDist, and CellViT-were selected for evaluation. To tackle the second question, we explored data enrichment algorithms by distilling predictions from the different foundation models with a human-in-the-loop framework, aiming to further enhance foundation model performance with minimal human efforts. Our experimental results showed that all three foundation models improved over their baselines with model fine-tuning with enriched data. Interestingly, the baseline model with the highest F1 score does not yield the best segmentation outcomes after fine-tuning. This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'none'; document.getElementById('2411.00078v1-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> 31 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/2410.23754">arXiv:2410.23754</a> <span> [<a href="https://arxiv.org/pdf/2410.23754">pdf</a>, <a href="https://arxiv.org/format/2410.23754">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> RealMind: Zero-Shot EEG-Based Visual Decoding and Captioning Using Multi-Modal Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+D">Dongyang Li</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+H">Haoyang Qin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+M">Mingyang Wu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuang Cao</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+C">Chen Wei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quanying Liu</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="2410.23754v1-abstract-short" style="display: inline;"> Despite significant progress in visual decoding with fMRI data, its high cost and low temporal resolution limit widespread applicability. To address these challenges, we introduce RealMind, a novel EEG-based visual decoding framework that leverages multi-modal models to efficiently interpret semantic information. By integrating semantic and geometric consistency learning, RealMind enhances feature… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23754v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23754v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23754v1-abstract-full" style="display: none;"> Despite significant progress in visual decoding with fMRI data, its high cost and low temporal resolution limit widespread applicability. To address these challenges, we introduce RealMind, a novel EEG-based visual decoding framework that leverages multi-modal models to efficiently interpret semantic information. By integrating semantic and geometric consistency learning, RealMind enhances feature alignment, leading to improved decoding performance. Our framework achieves a 56.73\% Top-5 accuracy in a 200-way retrieval task and a 26.59\% BLEU-1 score in a 200-way visual captioning task, representing the first successful attempt at zero-shot visual captioning using EEG data. RealMind provides a robust, adaptable, and cost-effective alternative to fMRI-based methods, offering scalable solutions for EEG-based visual decoding in practical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23754v1-abstract-full').style.display = 'none'; document.getElementById('2410.23754v1-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> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23506">arXiv:2410.23506</a> <span> [<a href="https://arxiv.org/pdf/2410.23506">pdf</a>, <a href="https://arxiv.org/format/2410.23506">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Learning to Achieve Goals with Belief State Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+E+S">Edward S. Hu</a>, <a href="/search/cs?searchtype=author&query=Ahn%2C+K">Kwangjun Ahn</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qinghua Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Haoran Xu</a>, <a href="/search/cs?searchtype=author&query=Tomar%2C+M">Manan Tomar</a>, <a href="/search/cs?searchtype=author&query=Langford%2C+A">Ada Langford</a>, <a href="/search/cs?searchtype=author&query=Jayaraman%2C+D">Dinesh Jayaraman</a>, <a href="/search/cs?searchtype=author&query=Lamb%2C+A">Alex Lamb</a>, <a href="/search/cs?searchtype=author&query=Langford%2C+J">John Langford</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="2410.23506v1-abstract-short" style="display: inline;"> We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the prefix and the previous token for the suffix. The Belief State Transformer effectively learns to solve challenging problems that conventional forward-only transformers struggle with, in a domain-independent fashion. Key… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23506v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23506v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23506v1-abstract-full" style="display: none;"> We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the prefix and the previous token for the suffix. The Belief State Transformer effectively learns to solve challenging problems that conventional forward-only transformers struggle with, in a domain-independent fashion. Key to this success is learning a compact belief state that captures all relevant information necessary for accurate predictions. Empirical ablations show that each component of the model is essential in difficult scenarios where standard Transformers fall short. For the task of story writing with known prefixes and suffixes, our approach outperforms the Fill-in-the-Middle method for reaching known goals and demonstrates improved performance even when the goals are unknown. Altogether, the Belief State Transformer enables more efficient goal-conditioned decoding, better test-time inference, and high-quality text representations on small scale problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23506v1-abstract-full').style.display = 'none'; document.getElementById('2410.23506v1-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> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22981">arXiv:2410.22981</a> <span> [<a href="https://arxiv.org/pdf/2410.22981">pdf</a>, <a href="https://arxiv.org/format/2410.22981">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"> DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiding Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiqian Yang</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Q">Qingyang Mao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yuze Zhao</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+M">Mingyue Cheng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhi Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+E">Enhong Chen</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="2410.22981v1-abstract-short" style="display: inline;"> Multivariate time series forecasting plays a crucial role in various real-world applications. Significant efforts have been made to integrate advanced network architectures and training strategies that enhance the capture of temporal dependencies, thereby improving forecasting accuracy. On the other hand, mainstream approaches typically utilize a single unified model with simplistic channel-mixing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22981v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22981v1-abstract-full" style="display: none;"> Multivariate time series forecasting plays a crucial role in various real-world applications. Significant efforts have been made to integrate advanced network architectures and training strategies that enhance the capture of temporal dependencies, thereby improving forecasting accuracy. On the other hand, mainstream approaches typically utilize a single unified model with simplistic channel-mixing embedding or cross-channel attention operations to account for the critical intricate inter-channel dependencies. Moreover, some methods even trade capacity for robust prediction based on the channel-independent assumption. Nonetheless, as time series data may display distinct evolving patterns due to the unique characteristics of each channel (including multiple strong seasonalities and trend changes), the unified modeling methods could yield suboptimal results. To this end, we propose DisenTS, a tailored framework for modeling disentangled channel evolving patterns in general multivariate time series forecasting. The central idea of DisenTS is to model the potential diverse patterns within the multivariate time series data in a decoupled manner. Technically, the framework employs multiple distinct forecasting models, each tasked with uncovering a unique evolving pattern. To guide the learning process without supervision of pattern partition, we introduce a novel Forecaster Aware Gate (FAG) module that generates the routing signals adaptively according to both the forecasters' states and input series' characteristics. The forecasters' states are derived from the Linear Weight Approximation (LWA) strategy, which quantizes the complex deep neural networks into compact matrices. Additionally, the Similarity Constraint (SC) is further proposed to guide each model to specialize in an underlying pattern by minimizing the mutual information between the representations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22981v1-abstract-full').style.display = 'none'; document.getElementById('2410.22981v1-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> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22732">arXiv:2410.22732</a> <span> [<a href="https://arxiv.org/pdf/2410.22732">pdf</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="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> </div> </div> <p class="title is-5 mathjax"> st-DTPM: Spatial-Temporal Guided Diffusion Transformer Probabilistic Model for Delayed Scan PET Image Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hong%2C+R">Ran Hong</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yuxia Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+L">Lei Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhonghui Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bingxuan Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xuemei Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiegen Liu</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="2410.22732v1-abstract-short" style="display: inline;"> PET imaging is widely employed for observing biological metabolic activities within the human body. However, numerous benign conditions can cause increased uptake of radiopharmaceuticals, confounding differentiation from malignant tumors. Several studies have indicated that dual-time PET imaging holds promise in distinguishing between malignant and benign tumor processes. Nevertheless, the hour-lo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22732v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22732v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22732v1-abstract-full" style="display: none;"> PET imaging is widely employed for observing biological metabolic activities within the human body. However, numerous benign conditions can cause increased uptake of radiopharmaceuticals, confounding differentiation from malignant tumors. Several studies have indicated that dual-time PET imaging holds promise in distinguishing between malignant and benign tumor processes. Nevertheless, the hour-long distribution period of radiopharmaceuticals post-injection complicates the determination of optimal timing for the second scan, presenting challenges in both practical applications and research. Notably, we have identified that delay time PET imaging can be framed as an image-to-image conversion problem. Motivated by this insight, we propose a novel spatial-temporal guided diffusion transformer probabilistic model (st-DTPM) to solve dual-time PET imaging prediction problem. Specifically, this architecture leverages the U-net framework that integrates patch-wise features of CNN and pixel-wise relevance of Transformer to obtain local and global information. And then employs a conditional DDPM model for image synthesis. Furthermore, on spatial condition, we concatenate early scan PET images and noisy PET images on every denoising step to guide the spatial distribution of denoising sampling. On temporal condition, we convert diffusion time steps and delay time to a universal time vector, then embed it to each layer of model architecture to further improve the accuracy of predictions. Experimental results demonstrated the superiority of our method over alternative approaches in preserving image quality and structural information, thereby affirming its efficacy in predictive task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22732v1-abstract-full').style.display = 'none'; document.getElementById('2410.22732v1-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> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22674">arXiv:2410.22674</a> <span> [<a href="https://arxiv.org/pdf/2410.22674">pdf</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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Dynamic PET Image Prediction Using a Network Combining Reversible and Irreversible Modules </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jie Sun</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Q">Qian Xia</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+C">Chuanfu Sun</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yumei Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Huafeng Liu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiegen Liu</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="2410.22674v1-abstract-short" style="display: inline;"> Dynamic positron emission tomography (PET) images can reveal the distribution of tracers in the organism and the dynamic processes involved in biochemical reactions, and it is widely used in clinical practice. Despite the high effectiveness of dynamic PET imaging in studying the kinetics and metabolic processes of radiotracers. Pro-longed scan times can cause discomfort for both patients and medic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22674v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22674v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22674v1-abstract-full" style="display: none;"> Dynamic positron emission tomography (PET) images can reveal the distribution of tracers in the organism and the dynamic processes involved in biochemical reactions, and it is widely used in clinical practice. Despite the high effectiveness of dynamic PET imaging in studying the kinetics and metabolic processes of radiotracers. Pro-longed scan times can cause discomfort for both patients and medical personnel. This study proposes a dynamic frame prediction method for dynamic PET imaging, reduc-ing dynamic PET scanning time by applying a multi-module deep learning framework composed of reversible and irreversible modules. The network can predict kinetic parameter images based on the early frames of dynamic PET images, and then generate complete dynamic PET images. In validation experiments with simulated data, our network demonstrated good predictive performance for kinetic parameters and was able to reconstruct high-quality dynamic PET images. Additionally, in clinical data experiments, the network exhibited good generalization performance and attached that the proposed method has promising clinical application prospects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22674v1-abstract-full').style.display = 'none'; document.getElementById('2410.22674v1-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> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22657">arXiv:2410.22657</a> <span> [<a href="https://arxiv.org/pdf/2410.22657">pdf</a>, <a href="https://arxiv.org/format/2410.22657">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Automatic programming via large language models with population self-evolution for dynamic job shop scheduling problem </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jin Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xinyu Li</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Liang Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qihao Liu</a>, <a href="/search/cs?searchtype=author&query=Teng%2C+Y">Yue Teng</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="2410.22657v1-abstract-short" style="display: inline;"> Heuristic dispatching rules (HDRs) are widely regarded as effective methods for solving dynamic job shop scheduling problems (DJSSP) in real-world production environments. However, their performance is highly scenario-dependent, often requiring expert customization. To address this, genetic programming (GP) and gene expression programming (GEP) have been extensively used for automatic algorithm de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22657v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22657v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22657v1-abstract-full" style="display: none;"> Heuristic dispatching rules (HDRs) are widely regarded as effective methods for solving dynamic job shop scheduling problems (DJSSP) in real-world production environments. However, their performance is highly scenario-dependent, often requiring expert customization. To address this, genetic programming (GP) and gene expression programming (GEP) have been extensively used for automatic algorithm design. Nevertheless, these approaches often face challenges due to high randomness in the search process and limited generalization ability, hindering the application of trained dispatching rules to new scenarios or dynamic environments. Recently, the integration of large language models (LLMs) with evolutionary algorithms has opened new avenues for prompt engineering and automatic algorithm design. To enhance the capabilities of LLMs in automatic HDRs design, this paper proposes a novel population self-evolutionary (SeEvo) method, a general search framework inspired by the self-reflective design strategies of human experts. The SeEvo method accelerates the search process and enhances exploration capabilities. Experimental results show that the proposed SeEvo method outperforms GP, GEP, end-to-end deep reinforcement learning methods, and more than 10 common HDRs from the literature, particularly in unseen and dynamic scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22657v1-abstract-full').style.display = 'none'; document.getElementById('2410.22657v1-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> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22350">arXiv:2410.22350</a> <span> [<a href="https://arxiv.org/pdf/2410.22350">pdf</a>, <a href="https://arxiv.org/format/2410.22350">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Quality-Aware End-to-End Audio-Visual Neural Speaker Diarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+M">Mao-Kui He</a>, <a href="/search/cs?searchtype=author&query=Du%2C+J">Jun Du</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+S">Shu-Tong Niu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qing-Feng Liu</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+C">Chin-Hui Lee</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="2410.22350v1-abstract-short" style="display: inline;"> In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series of binary classification output layers to simultaneously identify the activities of all speakers. This end-to-end framework is meticulously designed to effective… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22350v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22350v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22350v1-abstract-full" style="display: none;"> In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series of binary classification output layers to simultaneously identify the activities of all speakers. This end-to-end framework is meticulously designed to effectively handle situations of overlapping speech, providing accurate discrimination between speech and non-speech segments through the utilization of multi-modal information. Next, we employ a quality-aware audio-visual fusion structure to address signal quality issues for both audio degradations, such as noise, reverberation and other distortions, and video degradations, such as occlusions, off-screen speakers, or unreliable detection. Finally, a cross attention mechanism applied to multi-speaker embedding empowers the network to handle scenarios with varying numbers of speakers. Our experimental results, obtained from various data sets, demonstrate the robustness of our proposed techniques in diverse acoustic environments. Even in scenarios with severely degraded video quality, our system attains performance levels comparable to the best available audio-visual systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22350v1-abstract-full').style.display = 'none'; document.getElementById('2410.22350v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21779">arXiv:2410.21779</a> <span> [<a href="https://arxiv.org/pdf/2410.21779">pdf</a>, <a href="https://arxiv.org/format/2410.21779">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> </div> </div> <p class="title is-5 mathjax"> Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Q">Qingchuan Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiatong Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tongxuan Liu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+Y">Yuting Zeng</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+M">Mingyue Cheng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+W">Weizhe Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</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="2410.21779v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have exhibited remarkable potential across a wide array of reasoning tasks, including logical reasoning. Although massive efforts have been made to empower the logical reasoning ability of LLMs via external logical symbolic solvers, crucial challenges of the poor generalization ability to questions with different features and inevitable question information loss of sym… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21779v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21779v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21779v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have exhibited remarkable potential across a wide array of reasoning tasks, including logical reasoning. Although massive efforts have been made to empower the logical reasoning ability of LLMs via external logical symbolic solvers, crucial challenges of the poor generalization ability to questions with different features and inevitable question information loss of symbolic solver-driven approaches remain unresolved. To mitigate these issues, we introduce LINA, a LLM-driven neuro-symbolic approach for faithful logical reasoning. By enabling an LLM to autonomously perform the transition from propositional logic extraction to sophisticated logical reasoning, LINA not only bolsters the resilience of the reasoning process but also eliminates the dependency on external solvers. Additionally, through its adoption of a hypothetical-deductive reasoning paradigm, LINA effectively circumvents the expansive search space challenge that plagues traditional forward reasoning methods. Empirical evaluations demonstrate that LINA substantially outperforms both established propositional logic frameworks and conventional prompting techniques across a spectrum of five logical reasoning tasks. Specifically, LINA achieves an improvement of 24.34% over LINC on the FOLIO dataset, while also surpassing prompting strategies like CoT and CoT-SC by up to 24.02%. Our code is available at https://github.com/wufeiwuwoshihua/nshy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21779v1-abstract-full').style.display = 'none'; document.getElementById('2410.21779v1-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> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21677">arXiv:2410.21677</a> <span> [<a href="https://arxiv.org/pdf/2410.21677">pdf</a>, <a href="https://arxiv.org/format/2410.21677">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Two Criteria for Performance Analysis of Optimization Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jing%2C+Y">Yunpeng Jing</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">HaiLin Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qunfeng Liu</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="2410.21677v1-abstract-short" style="display: inline;"> Performance analysis is crucial in optimization research, especially when addressing black-box problems through nature-inspired algorithms. Current practices often rely heavily on statistical methods, which can lead to various logical paradoxes. To address this challenge, this paper introduces two criteria to ensure that performance analysis is unaffected by irrelevant factors. The first is the is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21677v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21677v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21677v1-abstract-full" style="display: none;"> Performance analysis is crucial in optimization research, especially when addressing black-box problems through nature-inspired algorithms. Current practices often rely heavily on statistical methods, which can lead to various logical paradoxes. To address this challenge, this paper introduces two criteria to ensure that performance analysis is unaffected by irrelevant factors. The first is the isomorphism criterion, which asserts that performance evaluation should remain unaffected by the modeling approach. The second is the IIA criterion,stating that comparisons between two algorithms should not be influenced by irrelevant third-party algorithms. Additionally, we conduct a comprehensive examination of the underlying causes of these paradoxes, identify conditions for checking the criteria, and propose ideas to tackle these issues. The criteria presented offer a framework for researchers to critically assess the performance metrics or ranking methods, ultimately aiming to enhance the rigor of evaluation metrics and ranking methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21677v1-abstract-full').style.display = 'none'; document.getElementById('2410.21677v1-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> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21611">arXiv:2410.21611</a> <span> [<a href="https://arxiv.org/pdf/2410.21611">pdf</a>, <a href="https://arxiv.org/format/2410.21611">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="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> <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"> CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Krause%2C+C">Claudius Krause</a>, <a href="/search/cs?searchtype=author&query=Giannelli%2C+M+F">Michele Faucci Giannelli</a>, <a href="/search/cs?searchtype=author&query=Kasieczka%2C+G">Gregor Kasieczka</a>, <a href="/search/cs?searchtype=author&query=Nachman%2C+B">Benjamin Nachman</a>, <a href="/search/cs?searchtype=author&query=Salamani%2C+D">Dalila Salamani</a>, <a href="/search/cs?searchtype=author&query=Shih%2C+D">David Shih</a>, <a href="/search/cs?searchtype=author&query=Zaborowska%2C+A">Anna Zaborowska</a>, <a href="/search/cs?searchtype=author&query=Amram%2C+O">Oz Amram</a>, <a href="/search/cs?searchtype=author&query=Borras%2C+K">Kerstin Borras</a>, <a href="/search/cs?searchtype=author&query=Buckley%2C+M+R">Matthew R. Buckley</a>, <a href="/search/cs?searchtype=author&query=Buhmann%2C+E">Erik Buhmann</a>, <a href="/search/cs?searchtype=author&query=Buss%2C+T">Thorsten Buss</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+R+P+D+C">Renato Paulo Da Costa Cardoso</a>, <a href="/search/cs?searchtype=author&query=Caterini%2C+A+L">Anthony L. Caterini</a>, <a href="/search/cs?searchtype=author&query=Chernyavskaya%2C+N">Nadezda Chernyavskaya</a>, <a href="/search/cs?searchtype=author&query=Corchia%2C+F+A+G">Federico A. G. Corchia</a>, <a href="/search/cs?searchtype=author&query=Cresswell%2C+J+C">Jesse C. Cresswell</a>, <a href="/search/cs?searchtype=author&query=Diefenbacher%2C+S">Sascha Diefenbacher</a>, <a href="/search/cs?searchtype=author&query=Dreyer%2C+E">Etienne Dreyer</a>, <a href="/search/cs?searchtype=author&query=Ekambaram%2C+V">Vijay Ekambaram</a>, <a href="/search/cs?searchtype=author&query=Eren%2C+E">Engin Eren</a>, <a href="/search/cs?searchtype=author&query=Ernst%2C+F">Florian Ernst</a>, <a href="/search/cs?searchtype=author&query=Favaro%2C+L">Luigi Favaro</a>, <a href="/search/cs?searchtype=author&query=Franchini%2C+M">Matteo Franchini</a>, <a href="/search/cs?searchtype=author&query=Gaede%2C+F">Frank Gaede</a> , et al. (44 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="2410.21611v1-abstract-short" style="display: inline;"> We present the results of the "Fast Calorimeter Simulation Challenge 2022" - the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including Variational AutoEncoder… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21611v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21611v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21611v1-abstract-full" style="display: none;"> We present the results of the "Fast Calorimeter Simulation Challenge 2022" - the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including Variational AutoEncoders (VAEs), Generative Adversarial Networks (GANs), Normalizing Flows, Diffusion models, and models based on Conditional Flow Matching. We compare all submissions in terms of quality of generated calorimeter showers, as well as shower generation time and model size. To assess the quality we use a broad range of different metrics including differences in 1-dimensional histograms of observables, KPD/FPD scores, AUCs of binary classifiers, and the log-posterior of a multiclass classifier. The results of the CaloChallenge provide the most complete and comprehensive survey of cutting-edge approaches to calorimeter fast simulation to date. In addition, our work provides a uniquely detailed perspective on the important problem of how to evaluate generative models. As such, the results presented here should be applicable for other domains that use generative AI and require fast and faithful generation of samples in a large phase space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21611v1-abstract-full').style.display = 'none'; document.getElementById('2410.21611v1-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> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">204 pages, 100+ figures, 30+ tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> HEPHY-ML-24-05, FERMILAB-PUB-24-0728-CMS, TTK-24-43 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20868">arXiv:2410.20868</a> <span> [<a href="https://arxiv.org/pdf/2410.20868">pdf</a>, <a href="https://arxiv.org/format/2410.20868">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> RecFlow: An Industrial Full Flow Recommendation Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+K">Kai Zheng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+R">Rui Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wuchao Li</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+K">Kuo Cai</a>, <a href="/search/cs?searchtype=author&query=Chai%2C+Y">Yuan Chai</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+Y">Yanan Niu</a>, <a href="/search/cs?searchtype=author&query=Hui%2C+Y">Yiqun Hui</a>, <a href="/search/cs?searchtype=author&query=Han%2C+B">Bing Han</a>, <a href="/search/cs?searchtype=author&query=Mou%2C+N">Na Mou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hongning Wang</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+W">Wentian Bao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yunen Yu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+G">Guorui Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Han Li</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Y">Yang Song</a>, <a href="/search/cs?searchtype=author&query=Lian%2C+D">Defu Lian</a>, <a href="/search/cs?searchtype=author&query=Gai%2C+K">Kun Gai</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="2410.20868v1-abstract-short" style="display: inline;"> Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where novel RS algorithms are trained and evaluated. However, when these algorithms transition to real world industrial RS, they face a critical challenge of handling… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20868v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20868v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20868v1-abstract-full" style="display: none;"> Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where novel RS algorithms are trained and evaluated. However, when these algorithms transition to real world industrial RS, they face a critical challenge of handling unexposed items which are a significantly larger space than the exposed one. This discrepancy profoundly impacts their practical performance. Additionally, these algorithms often overlook the intricate interplay between multiple RS stages, resulting in suboptimal overall system performance. To address this issue, we introduce RecFlow, an industrial full flow recommendation dataset designed to bridge the gap between offline RS benchmarks and the real online environment. Unlike existing datasets, RecFlow includes samples not only from the exposure space but also unexposed items filtered at each stage of the RS funnel. Our dataset comprises 38M interactions from 42K users across nearly 9M items with additional 1.9B stage samples collected from 9.3M online requests over 37 days and spanning 6 stages. Leveraging the RecFlow dataset, we conduct courageous exploration experiments, showcasing its potential in designing new algorithms to enhance effectiveness by incorporating stage-specific samples. Some of these algorithms have already been deployed online, consistently yielding significant gains. We propose RecFlow as the first comprehensive benchmark dataset for the RS community, supporting research on designing algorithms at any stage, study of selection bias, debiased algorithms, multi-stage consistency and optimality, multi-task recommendation, and user behavior modeling. The RecFlow dataset, along with the corresponding source code, is available at https://github.com/RecFlow-ICLR/RecFlow. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20868v1-abstract-full').style.display = 'none'; document.getElementById('2410.20868v1-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> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20730">arXiv:2410.20730</a> <span> [<a href="https://arxiv.org/pdf/2410.20730">pdf</a>, <a href="https://arxiv.org/format/2410.20730">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> GPRec: Bi-level User Modeling for Deep Recommenders </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yejing Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Dong Xu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xiangyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+Z">Zhiren Mao</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+P">Peng Xiang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+L">Ling Yan</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yao Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zijian Zhang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+X">Xuetao Wei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qidong Liu</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="2410.20730v1-abstract-short" style="display: inline;"> GPRec explicitly categorizes users into groups in a learnable manner and aligns them with corresponding group embeddings. We design the dual group embedding space to offer a diverse perspective on group preferences by contrasting positive and negative patterns. On the individual level, GPRec identifies personal preferences from ID-like features and refines the obtained individual representations t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20730v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20730v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20730v1-abstract-full" style="display: none;"> GPRec explicitly categorizes users into groups in a learnable manner and aligns them with corresponding group embeddings. We design the dual group embedding space to offer a diverse perspective on group preferences by contrasting positive and negative patterns. On the individual level, GPRec identifies personal preferences from ID-like features and refines the obtained individual representations to be independent of group ones, thereby providing a robust complement to the group-level modeling. We also present various strategies for the flexible integration of GPRec into various DRS models. Rigorous testing of GPRec on three public datasets has demonstrated significant improvements in recommendation quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20730v1-abstract-full').style.display = 'none'; document.getElementById('2410.20730v1-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> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20679">arXiv:2410.20679</a> <span> [<a href="https://arxiv.org/pdf/2410.20679">pdf</a>, <a href="https://arxiv.org/format/2410.20679">other</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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Finance">q-fin.CP</span> </div> </div> <p class="title is-5 mathjax"> MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+P">Peng Zhu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuante Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yifan Hu</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+S">Sheng Xiang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qinyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+D">Dawei Cheng</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuqi Liang</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="2410.20679v1-abstract-short" style="display: inline;"> As financial markets grow increasingly complex in the big data era, accurate stock prediction has become more critical. Traditional time series models, such as GRUs, have been widely used but often struggle to capture the intricate nonlinear dynamics of markets, particularly in the flexible selection and effective utilization of key historical information. Recently, methods like Graph Neural Netwo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20679v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20679v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20679v1-abstract-full" style="display: none;"> As financial markets grow increasingly complex in the big data era, accurate stock prediction has become more critical. Traditional time series models, such as GRUs, have been widely used but often struggle to capture the intricate nonlinear dynamics of markets, particularly in the flexible selection and effective utilization of key historical information. Recently, methods like Graph Neural Networks and Reinforcement Learning have shown promise in stock prediction but require high data quality and quantity, and they tend to exhibit instability when dealing with data sparsity and noise. Moreover, the training and inference processes for these models are typically complex and computationally expensive, limiting their broad deployment in practical applications. Existing approaches also generally struggle to capture unobservable latent market states effectively, such as market sentiment and expectations, microstructural factors, and participant behavior patterns, leading to an inadequate understanding of market dynamics and subsequently impact prediction accuracy. To address these challenges, this paper proposes a stock prediction model, MCI-GRU, based on a multi-head cross-attention mechanism and an improved GRU. First, we enhance the GRU model by replacing the reset gate with an attention mechanism, thereby increasing the model's flexibility in selecting and utilizing historical information. Second, we design a multi-head cross-attention mechanism for learning unobservable latent market state representations, which are further enriched through interactions with both temporal features and cross-sectional features. Finally, extensive experiments on four main stock markets show that the proposed method outperforms SOTA techniques across multiple metrics. Additionally, its successful application in real-world fund management operations confirms its effectiveness and practicality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20679v1-abstract-full').style.display = 'none'; document.getElementById('2410.20679v1-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> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19321">arXiv:2410.19321</a> <span> [<a href="https://arxiv.org/pdf/2410.19321">pdf</a>, <a href="https://arxiv.org/format/2410.19321">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</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"> Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+M">Mengmeng Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiaohu Wu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+X">Xiaoli Tang</a>, <a href="/search/cs?searchtype=author&query=He%2C+T">Tiantian He</a>, <a href="/search/cs?searchtype=author&query=Ong%2C+Y">Yew-Soon Ong</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qiqi Liu</a>, <a href="/search/cs?searchtype=author&query=Lao%2C+Q">Qicheng Lao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+H">Han Yu</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="2410.19321v2-abstract-short" style="display: inline;"> Federated learning (FL) is a machine learning paradigm that allows multiple FL participants (FL-PTs) to collaborate on training models without sharing private data. Due to data heterogeneity, negative transfer may occur in the FL training process. This necessitates FL-PT selection based on their data complementarity. In cross-silo FL, organizations that engage in business activities are key source… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19321v2-abstract-full').style.display = 'inline'; document.getElementById('2410.19321v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19321v2-abstract-full" style="display: none;"> Federated learning (FL) is a machine learning paradigm that allows multiple FL participants (FL-PTs) to collaborate on training models without sharing private data. Due to data heterogeneity, negative transfer may occur in the FL training process. This necessitates FL-PT selection based on their data complementarity. In cross-silo FL, organizations that engage in business activities are key sources of FL-PTs. The resulting FL ecosystem has two features: (i) self-interest, and (ii) competition among FL-PTs. This requires the desirable FL-PT selection strategy to simultaneously mitigate the problems of free riders and conflicts of interest among competitors. To this end, we propose an optimal FL collaboration formation strategy -- FedEgoists -- which ensures that: (1) a FL-PT can benefit from FL if and only if it benefits the FL ecosystem, and (2) a FL-PT will not contribute to its competitors or their supporters. It provides an efficient clustering solution to group FL-PTs into coalitions, ensuring that within each coalition, FL-PTs share the same interest. We theoretically prove that the FL-PT coalitions formed are optimal since no coalitions can collaborate together to improve the utility of any of their members. Extensive experiments on widely adopted benchmark datasets demonstrate the effectiveness of FedEgoists compared to nine state-of-the-art baseline methods, and its ability to establish efficient collaborative networks in cross-silos FL with FL-PTs that engage in business activities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19321v2-abstract-full').style.display = 'none'; document.getElementById('2410.19321v2-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">v1</span> submitted 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18514">arXiv:2410.18514</a> <span> [<a href="https://arxiv.org/pdf/2410.18514">pdf</a>, <a href="https://arxiv.org/format/2410.18514">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> <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"> Scaling up Masked Diffusion Models on Text </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nie%2C+S">Shen Nie</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+F">Fengqi Zhu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+C">Chao Du</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+T">Tianyu Pang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+G">Guangtao Zeng</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+M">Min Lin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chongxuan 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="2410.18514v1-abstract-short" style="display: inline;"> Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the first scaling law for MDMs, demonstrating a scaling rate comparable to autoregressive models (ARMs) and a relatively small compute gap. Motivated by their scalabil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18514v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18514v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18514v1-abstract-full" style="display: none;"> Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the first scaling law for MDMs, demonstrating a scaling rate comparable to autoregressive models (ARMs) and a relatively small compute gap. Motivated by their scalability, we train a family of MDMs with up to 1.1 billion (B) parameters to systematically evaluate their performance against ARMs of comparable or larger sizes. Fully leveraging the probabilistic formulation of MDMs, we propose a simple yet effective \emph{unsupervised classifier-free guidance} that effectively exploits large-scale unpaired data, boosting performance for conditional inference. In language understanding, a 1.1B MDM shows competitive results, outperforming the larger 1.5B GPT-2 model on four out of eight zero-shot benchmarks. In text generation, MDMs provide a flexible trade-off compared to ARMs utilizing KV-cache: MDMs match the performance of ARMs while being 1.4 times faster, or achieve higher quality than ARMs at a higher computational cost. Moreover, MDMs address challenging tasks for ARMs by effectively handling bidirectional reasoning and adapting to temporal shifts in data. Notably, a 1.1B MDM breaks the \emph{reverse curse} encountered by much larger ARMs with significantly more data and computation, such as Llama-2 (13B) and GPT-3 (175B). Our code is available at \url{https://github.com/ML-GSAI/SMDM}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18514v1-abstract-full').style.display = 'none'; document.getElementById('2410.18514v1-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> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18447">arXiv:2410.18447</a> <span> [<a href="https://arxiv.org/pdf/2410.18447">pdf</a>, <a href="https://arxiv.org/format/2410.18447">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> </div> </div> <p class="title is-5 mathjax"> ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zezhong Wang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+X">Xingshan Zeng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weiwen Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Liangyou Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yasheng Wang</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+L">Lifeng Shang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+X">Xin Jiang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qun Liu</a>, <a href="/search/cs?searchtype=author&query=Wong%2C+K">Kam-Fai Wong</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="2410.18447v1-abstract-short" style="display: inline;"> Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set of tools, formulating a requirement based on these tools, and generating the call statements. However, tools sampled randomly lack relevance, making them difficu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18447v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18447v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18447v1-abstract-full" style="display: none;"> Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set of tools, formulating a requirement based on these tools, and generating the call statements. However, tools sampled randomly lack relevance, making them difficult to combine and thus reducing the diversity of the data. Additionally, current work overlooks the coherence between turns of dialogues, leading to a gap between the synthesized data and real-world scenarios. To address these issues, we propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues. We integrate these two strategies and enable multiple agents to synthesize the dialogue data interactively, resulting in our tool-calling data synthesis pipeline ToolFlow. Data quality assessments demonstrate improvements in the naturalness and coherence of our synthesized dialogues. Finally, we apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow. Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18447v1-abstract-full').style.display = 'none'; document.getElementById('2410.18447v1-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> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17859">arXiv:2410.17859</a> <span> [<a href="https://arxiv.org/pdf/2410.17859">pdf</a>, <a href="https://arxiv.org/format/2410.17859">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> </div> </div> <p class="title is-5 mathjax"> DataTales: A Benchmark for Real-World Intelligent Data Narration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yajing Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Kan%2C+M">Min-Yen Kan</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="2410.17859v1-abstract-short" style="display: inline;"> We introduce DataTales, a novel benchmark designed to assess the proficiency of language models in data narration, a task crucial for transforming complex tabular data into accessible narratives. Existing benchmarks often fall short in capturing the requisite analytical complexity for practical applications. DataTales addresses this gap by offering 4.9k financial reports paired with corresponding… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17859v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17859v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17859v1-abstract-full" style="display: none;"> We introduce DataTales, a novel benchmark designed to assess the proficiency of language models in data narration, a task crucial for transforming complex tabular data into accessible narratives. Existing benchmarks often fall short in capturing the requisite analytical complexity for practical applications. DataTales addresses this gap by offering 4.9k financial reports paired with corresponding market data, showcasing the demand for models to create clear narratives and analyze large datasets while understanding specialized terminology in the field. Our findings highlights the significant challenge that language models face in achieving the necessary precision and analytical depth for proficient data narration, suggesting promising avenues for future model development and evaluation methodologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17859v1-abstract-full').style.display = 'none'; document.getElementById('2410.17859v1-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> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17518">arXiv:2410.17518</a> <span> [<a href="https://arxiv.org/pdf/2410.17518">pdf</a>, <a href="https://arxiv.org/format/2410.17518">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</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"> Univariate Conditional Variational Autoencoder for Morphogenic Patterns Design in Frontal Polymerization-Based Manufacturing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qibang Liu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+P">Pengfei Cai</a>, <a href="/search/cs?searchtype=author&query=Abueidda%2C+D">Diab Abueidda</a>, <a href="/search/cs?searchtype=author&query=Vyas%2C+S">Sagar Vyas</a>, <a href="/search/cs?searchtype=author&query=Koric%2C+S">Seid Koric</a>, <a href="/search/cs?searchtype=author&query=Gomez-Bombarelli%2C+R">Rafael Gomez-Bombarelli</a>, <a href="/search/cs?searchtype=author&query=Geubelle%2C+P">Philippe Geubelle</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="2410.17518v2-abstract-short" style="display: inline;"> Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17518v2-abstract-full').style.display = 'inline'; document.getElementById('2410.17518v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17518v2-abstract-full" style="display: none;"> Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17518v2-abstract-full').style.display = 'none'; document.getElementById('2410.17518v2-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> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.16676">arXiv:2410.16676</a> <span> [<a href="https://arxiv.org/pdf/2410.16676">pdf</a>, <a href="https://arxiv.org/format/2410.16676">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"> Improving Causal Reasoning in Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+L">Longxuan Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Delin Chen</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+S">Siheng Xiong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qingyang Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qingzhen Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+D">Dawei Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhikai Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoze Liu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+L">Liangming Pan</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="2410.16676v3-abstract-short" style="display: inline;"> Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving, decision-making, and understanding the world. While large language models (LLMs) can generate rationales for their outputs, their ability to reliably perform causal reasoning remains uncertain, often falling short in tasks requiring a deep understanding of causality. In this survey, we provide a comprehensive… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16676v3-abstract-full').style.display = 'inline'; document.getElementById('2410.16676v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16676v3-abstract-full" style="display: none;"> Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving, decision-making, and understanding the world. While large language models (LLMs) can generate rationales for their outputs, their ability to reliably perform causal reasoning remains uncertain, often falling short in tasks requiring a deep understanding of causality. In this survey, we provide a comprehensive review of research aimed at enhancing LLMs for causal reasoning. We categorize existing methods based on the role of LLMs: either as reasoning engines or as helpers providing knowledge or data to traditional CR methods, followed by a detailed discussion of the methodologies in each category. We then evaluate the performance of LLMs on various causal reasoning tasks, providing key findings and in-depth analysis. Finally, we provide insights from current studies and highlight promising directions for future research. We aim for this work to serve as a comprehensive resource, fostering further advancements in causal reasoning with LLMs. Resources are available at https://github.com/chendl02/Awesome-LLM-causal-reasoning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16676v3-abstract-full').style.display = 'none'; document.getElementById('2410.16676v3-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">v1</span> submitted 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </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=Liu%2C+Q&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Liu%2C+Q&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