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 984 results for author: <span class="mathjax">Wen, J</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/" aria-role="search"> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Wen, J"> </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=Wen%2C+J&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="Wen, J"> <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=Wen%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&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/2411.17693">arXiv:2411.17693</a> <span> [<a href="https://arxiv.org/pdf/2411.17693">pdf</a>, <a href="https://arxiv.org/format/2411.17693">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"> Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiaxin Wen</a>, <a href="/search/?searchtype=author&query=Hebbar%2C+V">Vivek Hebbar</a>, <a href="/search/?searchtype=author&query=Larson%2C+C">Caleb Larson</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+A">Aryan Bhatt</a>, <a href="/search/?searchtype=author&query=Radhakrishnan%2C+A">Ansh Radhakrishnan</a>, <a href="/search/?searchtype=author&query=Sharma%2C+M">Mrinank Sharma</a>, <a href="/search/?searchtype=author&query=Sleight%2C+H">Henry Sleight</a>, <a href="/search/?searchtype=author&query=Feng%2C+S">Shi Feng</a>, <a href="/search/?searchtype=author&query=He%2C+H">He He</a>, <a href="/search/?searchtype=author&query=Perez%2C+E">Ethan Perez</a>, <a href="/search/?searchtype=author&query=Shlegeris%2C+B">Buck Shlegeris</a>, <a href="/search/?searchtype=author&query=Khan%2C+A">Akbir Khan</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="2411.17693v1-abstract-short" style="display: inline;"> As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for testing deployment strategies of untrusted models (i.e., models which might be trying to bypass safety measures). While prior work treats a single failu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17693v1-abstract-full').style.display = 'inline'; document.getElementById('2411.17693v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.17693v1-abstract-full" style="display: none;"> As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for testing deployment strategies of untrusted models (i.e., models which might be trying to bypass safety measures). While prior work treats a single failure as unacceptable, we perform control evaluations in a "distributed threat setting" -- a setting where no single action is catastrophic and no single action provides overwhelming evidence of misalignment. We approach this problem with a two-level deployment framework that uses an adaptive macro-protocol to choose between micro-protocols. Micro-protocols operate on a single task, using a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. Meanwhile, the macro-protocol maintains an adaptive credence on the untrusted model's alignment based on its past actions, using it to pick between safer and riskier micro-protocols. We evaluate our method in a code generation testbed where a red team attempts to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. We plot Pareto frontiers of safety (# of non-backdoored solutions) and usefulness (# of correct solutions). At a given level of usefulness, our adaptive deployment strategy reduces the number of backdoors by 80% compared to non-adaptive baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17693v1-abstract-full').style.display = 'none'; document.getElementById('2411.17693v1-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> 26 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/2411.15915">arXiv:2411.15915</a> <span> [<a href="https://arxiv.org/pdf/2411.15915">pdf</a>, <a href="https://arxiv.org/format/2411.15915">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"> Multi-Robot Scan-n-Print for Wire Arc Additive Manufacturing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lu%2C+C">Chen-Lung Lu</a>, <a href="/search/?searchtype=author&query=He%2C+H">Honglu He</a>, <a href="/search/?searchtype=author&query=Ren%2C+J">Jinhan Ren</a>, <a href="/search/?searchtype=author&query=Dhar%2C+J">Joni Dhar</a>, <a href="/search/?searchtype=author&query=Saunders%2C+G">Glenn Saunders</a>, <a href="/search/?searchtype=author&query=Julius%2C+A">Agung Julius</a>, <a href="/search/?searchtype=author&query=Samuel%2C+J">Johnson Samuel</a>, <a href="/search/?searchtype=author&query=Wen%2C+J+T">John T. Wen</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="2411.15915v1-abstract-short" style="display: inline;"> Robotic Wire Arc Additive Manufacturing (WAAM) is a metal additive manufacturing technology, offering flexible 3D printing while ensuring high quality near-net-shape final parts. However, WAAM also suffers from geometric imprecision, especially for low-melting-point metal such as aluminum alloys. In this paper, we present a multi-robot framework for WAAM process monitoring and control. We consider… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15915v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15915v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15915v1-abstract-full" style="display: none;"> Robotic Wire Arc Additive Manufacturing (WAAM) is a metal additive manufacturing technology, offering flexible 3D printing while ensuring high quality near-net-shape final parts. However, WAAM also suffers from geometric imprecision, especially for low-melting-point metal such as aluminum alloys. In this paper, we present a multi-robot framework for WAAM process monitoring and control. We consider a three-robot setup: a 6-dof welding robot, a 2-dof trunnion platform, and a 6-dof sensing robot with a wrist-mounted laser line scanner measuring the printed part height profile. The welding parameters, including the wire feed rate, are held constant based on the materials used, so the control input is the robot path speed. The measured output is the part height profile. The planning phase decomposes the target shape into slices of uniform height. During runtime, the sensing robot scans each printed layer, and the robot path speed for the next layer is adjusted based on the deviation from the desired profile. The adjustment is based on an identified model correlating the path speed to change in height. The control architecture coordinates the synchronous motion and data acquisition between all robots and sensors. Using a three-robot WAAM testbed, we demonstrate significant improvements of the closed loop scan-n-print approach over the current open loop result on both a flat wall and a more complex turbine blade shape. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15915v1-abstract-full').style.display = 'none'; document.getElementById('2411.15915v1-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 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/2411.15845">arXiv:2411.15845</a> <span> [<a href="https://arxiv.org/pdf/2411.15845">pdf</a>, <a href="https://arxiv.org/format/2411.15845">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Space-ground Fluid AI for 6G Edge Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Q">Qian Chen</a>, <a href="/search/?searchtype=author&query=Wang%2C+Z">Zhanwei Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+X">Xianhao Chen</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Juan Wen</a>, <a href="/search/?searchtype=author&query=Zhou%2C+D">Di Zhou</a>, <a href="/search/?searchtype=author&query=Ji%2C+S">Sijing Ji</a>, <a href="/search/?searchtype=author&query=Sheng%2C+M">Min Sheng</a>, <a href="/search/?searchtype=author&query=Huang%2C+K">Kaibin 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="2411.15845v1-abstract-short" style="display: inline;"> Edge artificial intelligence (AI) and space-ground integrated networks (SGIN) are two main usage scenarios of the sixth-generation (6G) mobile networks. Edge AI supports pervasive low-latency AI services to users, whereas SGIN provide digital services to spatial, aerial, maritime and ground users. This article advocates the integration of the two technologies by extending edge AI to space, thereby… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15845v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15845v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15845v1-abstract-full" style="display: none;"> Edge artificial intelligence (AI) and space-ground integrated networks (SGIN) are two main usage scenarios of the sixth-generation (6G) mobile networks. Edge AI supports pervasive low-latency AI services to users, whereas SGIN provide digital services to spatial, aerial, maritime and ground users. This article advocates the integration of the two technologies by extending edge AI to space, thereby delivering AI services to every corner of the planet. Beyond a simple combination, our novel framework, called Space-ground Fluid AI, leverages the predictive mobility of satellites to facilitate fluid horizontal and vertical task/model migration in the networks. This ensures non-disruptive AI service provisioning in spite of the high mobility of satellite servers. The aim of the article is to introduce the (Space-ground) Fluid AI technology. First, we outline the network architecture and unique characteristics of Fluid AI. Then, we delve into three key components of Fluid AI, i.e., fluid learning, fluid inference, and fluid model downloading. They share the common feature of coping with satellite mobility via inter-satellite and space-ground cooperation to support AI services. Finally, we present some experimental case studies to demonstrate the effectiveness of Fluid AI and identify further research opportunities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15845v1-abstract-full').style.display = 'none'; document.getElementById('2411.15845v1-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 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">5 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11694">arXiv:2411.11694</a> <span> [<a href="https://arxiv.org/pdf/2411.11694">pdf</a>, <a href="https://arxiv.org/format/2411.11694">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"> Technical Report: Enhancing LLM Reasoning with Reward-guided Tree Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Jiang%2C+J">Jinhao Jiang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhipeng Chen</a>, <a href="/search/?searchtype=author&query=Min%2C+Y">Yingqian Min</a>, <a href="/search/?searchtype=author&query=Chen%2C+J">Jie Chen</a>, <a href="/search/?searchtype=author&query=Cheng%2C+X">Xiaoxue Cheng</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jiapeng Wang</a>, <a href="/search/?searchtype=author&query=Tang%2C+Y">Yiru Tang</a>, <a href="/search/?searchtype=author&query=Sun%2C+H">Haoxiang Sun</a>, <a href="/search/?searchtype=author&query=Deng%2C+J">Jia Deng</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Zheng Liu</a>, <a href="/search/?searchtype=author&query=Yan%2C+D">Dong Yan</a>, <a href="/search/?searchtype=author&query=Xie%2C+J">Jian Xie</a>, <a href="/search/?searchtype=author&query=Wang%2C+Z">Zhongyuan Wang</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2411.11694v1-abstract-short" style="display: inline;"> Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference phase, large language models~(LLMs) can extensively explore the solution space by generating more thought tokens or diverse solutions, thereby producing more accura… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11694v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11694v1-abstract-full" style="display: none;"> Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference phase, large language models~(LLMs) can extensively explore the solution space by generating more thought tokens or diverse solutions, thereby producing more accurate responses. However, developing an o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. In this paper, we present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms. This framework is implemented by integrating the policy model, reward model, and search algorithm. It is primarily constructed around a tree search algorithm, where the policy model navigates a dynamically expanding tree guided by a specially trained reward model. We thoroughly explore various design considerations necessary for implementing this framework and provide a detailed report of the technical aspects. To assess the effectiveness of our approach, we focus on mathematical reasoning tasks and conduct extensive evaluations on four challenging datasets, significantly enhancing the reasoning abilities of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11694v1-abstract-full').style.display = 'none'; document.getElementById('2411.11694v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">LLM;Complex Reasoning;Math</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09958">arXiv:2411.09958</a> <span> [<a href="https://arxiv.org/pdf/2411.09958">pdf</a>, <a href="https://arxiv.org/format/2411.09958">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Atomic Physics">physics.atom-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Post-selection shifts the transition frequency of helium in an atomic beam </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jin-Lu Wen</a>, <a href="/search/?searchtype=author&query=Tang%2C+J">Jia-Dong Tang</a>, <a href="/search/?searchtype=author&query=Lv%2C+Y">Ya-Nan Lv</a>, <a href="/search/?searchtype=author&query=Sun%2C+Y+R">Yu R. Sun</a>, <a href="/search/?searchtype=author&query=Zou%2C+C">Chang-Ling Zou</a>, <a href="/search/?searchtype=author&query=Dong%2C+J">Jun-Feng Dong</a>, <a href="/search/?searchtype=author&query=Hu%2C+S">Shui-Ming Hu</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="2411.09958v1-abstract-short" style="display: inline;"> Post-selecting output states in measurements can effectively amplify weak signals and improve precision. However, post-selection effects may also introduce unintended biases in precision measurements. Here, we investigate the influence of post-selection in the precision spectroscopy of the $2^3S - 2^3P$ transition of helium ($^4$He) using an atomic beam. We directly observe that post-selection bas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09958v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09958v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09958v1-abstract-full" style="display: none;"> Post-selecting output states in measurements can effectively amplify weak signals and improve precision. However, post-selection effects may also introduce unintended biases in precision measurements. Here, we investigate the influence of post-selection in the precision spectroscopy of the $2^3S - 2^3P$ transition of helium ($^4$He) using an atomic beam. We directly observe that post-selection based on atomic positions causes a shift in the measured transition frequency, amounting to approximately -55 kHz. After accounting for this post-selection shift, we obtain a corrected frequency of $276,764,094,712.45 \pm 0.86$ kHz for the $2^3S_1 - 2^3P_0$ transition. Combining this result with existing data for $^3$He, we derive a new value for the difference in squared nuclear charge radii, $未r^2 [r_{h}^{2} - r_伪^{2}] = 1.0733 \pm 0.0021$ fm$^2$. This value shows a $2.8蟽$ deviation from measurements of muonic helium ions, potentially pointing to new physics that challenges lepton universality in quantum electrodynamics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09958v1-abstract-full').style.display = 'none'; document.getElementById('2411.09958v1-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">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages including appendix</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08341">arXiv:2411.08341</a> <span> [<a href="https://arxiv.org/pdf/2411.08341">pdf</a>, <a href="https://arxiv.org/format/2411.08341">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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"> Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jinbo Wen</a>, <a href="/search/?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jiacheng Wang</a>, <a href="/search/?searchtype=author&query=Sikdar%2C+B">Biplab Sikdar</a>, <a href="/search/?searchtype=author&query=Zhang%2C+P">Ping 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="2411.08341v1-abstract-short" style="display: inline;"> Data augmentation is a powerful technique to mitigate data scarcity. However, owing to fundamental differences in wireless data structures, traditional data augmentation techniques may not be suitable for wireless data. Fortunately, Generative Artificial Intelligence (GenAI) can be an effective alternative to wireless data augmentation due to its excellent data generation capability. This article… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08341v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08341v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08341v1-abstract-full" style="display: none;"> Data augmentation is a powerful technique to mitigate data scarcity. However, owing to fundamental differences in wireless data structures, traditional data augmentation techniques may not be suitable for wireless data. Fortunately, Generative Artificial Intelligence (GenAI) can be an effective alternative to wireless data augmentation due to its excellent data generation capability. This article systemically explores the potential and effectiveness of GenAI-driven data augmentation in wireless networks. We first briefly review data augmentation techniques, discuss their limitations in wireless networks, and introduce generative data augmentation, including reviewing GenAI models and their applications in data augmentation. We then explore the application prospects of GenAI-driven data augmentation in wireless networks from the physical, network, and application layers, which provides a GenAI-driven data augmentation architecture for each application. Subsequently, we propose a general generative diffusion model-based data augmentation framework for Wi-Fi gesture recognition, which uses transformer-based diffusion models to generate high-quality channel state information data. Furthermore, we develop residual neural network models for Wi-Fi gesture recognition to evaluate the role of augmented data and conduct a case study based on a real dataset. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we discuss research directions for generative data augmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08341v1-abstract-full').style.display = 'none'; document.getElementById('2411.08341v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06148">arXiv:2411.06148</a> <span> [<a href="https://arxiv.org/pdf/2411.06148">pdf</a>, <a href="https://arxiv.org/format/2411.06148">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"> Deep Reinforcement Learning for Digital Twin-Oriented Complex Networked Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiaqi Wen</a>, <a href="/search/?searchtype=author&query=Gabrys%2C+B">Bogdan Gabrys</a>, <a href="/search/?searchtype=author&query=Musial%2C+K">Katarzyna Musial</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="2411.06148v1-abstract-short" style="display: inline;"> The Digital Twin Oriented Complex Networked System (DT-CNS) aims to build and extend a Complex Networked System (CNS) model with progressively increasing dynamics complexity towards an accurate reflection of reality -- a Digital Twin of reality. Our previous work proposed evolutionary DT-CNSs to model the long-term adaptive network changes in an epidemic outbreak. This study extends this framework… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06148v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06148v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06148v1-abstract-full" style="display: none;"> The Digital Twin Oriented Complex Networked System (DT-CNS) aims to build and extend a Complex Networked System (CNS) model with progressively increasing dynamics complexity towards an accurate reflection of reality -- a Digital Twin of reality. Our previous work proposed evolutionary DT-CNSs to model the long-term adaptive network changes in an epidemic outbreak. This study extends this framework by proposeing the temporal DT-CNS model, where reinforcement learning-driven nodes make decisions on temporal directed interactions in an epidemic outbreak. We consider cooperative nodes, as well as egocentric and ignorant "free-riders" in the cooperation. We describe this epidemic spreading process with the Susceptible-Infected-Recovered ($SIR$) model and investigate the impact of epidemic severity on the epidemic resilience for different types of nodes. Our experimental results show that (i) the full cooperation leads to a higher reward and lower infection number than a cooperation with egocentric or ignorant "free-riders"; (ii) an increasing number of "free-riders" in a cooperation leads to a smaller reward, while an increasing number of egocentric "free-riders" further escalate the infection numbers and (iii) higher infection rates and a slower recovery weakens networks' resilience to severe epidemic outbreaks. These findings also indicate that promoting cooperation and reducing "free-riders" can improve public health during epidemics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06148v1-abstract-full').style.display = 'none'; document.getElementById('2411.06148v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04602">arXiv:2411.04602</a> <span> [<a href="https://arxiv.org/pdf/2411.04602">pdf</a>, <a href="https://arxiv.org/format/2411.04602">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Self-Calibrated Listwise Reranking with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ren%2C+R">Ruiyang Ren</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yuhao Wang</a>, <a href="/search/?searchtype=author&query=Zhou%2C+K">Kun Zhou</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wang%2C+W">Wenjie Wang</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Jing Liu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</a>, <a href="/search/?searchtype=author&query=Chua%2C+T">Tat-Seng Chua</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="2411.04602v1-abstract-short" style="display: inline;"> Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked permutation is generated. However, due to the limited context window of LLMs, this reranking paradigm requires a sliding window strategy to iteratively handle… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04602v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04602v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04602v1-abstract-full" style="display: none;"> Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked permutation is generated. However, due to the limited context window of LLMs, this reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. This not only increases computational costs but also restricts the LLM from fully capturing all the comparison information for all candidates. To address these challenges, we propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking. To achieve it, we first propose the relevance-aware listwise reranking framework, which incorporates explicit list-view relevance scores to improve reranking efficiency and enable global comparison across the entire candidate set. Second, to ensure the comparability of the computed scores, we propose self-calibrated training that uses point-view relevance assessments generated internally by the LLM itself to calibrate the list-view relevance assessments. Extensive experiments and comprehensive analysis on the BEIR benchmark and TREC Deep Learning Tracks demonstrate the effectiveness and efficiency of our proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04602v1-abstract-full').style.display = 'none'; document.getElementById('2411.04602v1-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/2411.03817">arXiv:2411.03817</a> <span> [<a href="https://arxiv.org/pdf/2411.03817">pdf</a>, <a href="https://arxiv.org/format/2411.03817">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="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Deng%2C+Z">Zhirui Deng</a>, <a href="/search/?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Y">Yutao Zhu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</a>, <a href="/search/?searchtype=author&query=Xiong%2C+R">Ruibin Xiong</a>, <a href="/search/?searchtype=author&query=Wang%2C+M">Mang Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Weipeng 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="2411.03817v2-abstract-short" style="display: inline;"> The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches have shifted toward the reinforcement learning strategy to further enhance agents' ability to solve complex interactive tasks with environments and tools. Howe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03817v2-abstract-full').style.display = 'inline'; document.getElementById('2411.03817v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03817v2-abstract-full" style="display: none;"> The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches have shifted toward the reinforcement learning strategy to further enhance agents' ability to solve complex interactive tasks with environments and tools. However, previous approaches are constrained by the sparse reward issue, where existing datasets solely provide a final scalar reward for each multi-step reasoning chain, potentially leading to ineffectiveness and inefficiency in policy learning. In this paper, we introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. Inheriting the spirit of novice-to-expert theory, we first compare the actions of the expert and the agent to automatically generate intermediate rewards for fine-grained optimization. Additionally, we propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment. Further theoretical analysis demonstrates that the action distribution of the agent can converge toward the expert action distribution over multiple training cycles. Experimental results across various datasets indicate that StepAgent outperforms existing baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03817v2-abstract-full').style.display = 'none'; document.getElementById('2411.03817v2-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> 22 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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/2411.03671">arXiv:2411.03671</a> <span> [<a href="https://arxiv.org/pdf/2411.03671">pdf</a>, <a href="https://arxiv.org/format/2411.03671">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <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 Physics">physics.comp-ph</span> </div> </div> <p class="title is-5 mathjax"> Energy-based physics-informed neural network for frictionless contact problems under large deformation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Bai%2C+J">Jinshuai Bai</a>, <a href="/search/?searchtype=author&query=Lin%2C+Z">Zhongya Lin</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yizheng Wang</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jiancong Wen</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Yinghua Liu</a>, <a href="/search/?searchtype=author&query=Rabczuk%2C+T">Timon Rabczuk</a>, <a href="/search/?searchtype=author&query=Gu%2C+Y">YuanTong Gu</a>, <a href="/search/?searchtype=author&query=Feng%2C+X">Xi-Qiao 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="2411.03671v1-abstract-short" style="display: inline;"> Numerical methods for contact mechanics are of great importance in engineering applications, enabling the prediction and analysis of complex surface interactions under various conditions. In this work, we propose an energy-based physics-informed neural network (PINNs) framework for solving frictionless contact problems under large deformation. Inspired by microscopic Lennard-Jones potential, a sur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03671v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03671v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03671v1-abstract-full" style="display: none;"> Numerical methods for contact mechanics are of great importance in engineering applications, enabling the prediction and analysis of complex surface interactions under various conditions. In this work, we propose an energy-based physics-informed neural network (PINNs) framework for solving frictionless contact problems under large deformation. Inspired by microscopic Lennard-Jones potential, a surface contact energy is used to describe the contact phenomena. To ensure the robustness of the proposed PINN framework, relaxation, gradual loading and output scaling techniques are introduced. In the numerical examples, the well-known Hertz contact benchmark problem is conducted, demonstrating the effectiveness and robustness of the proposed PINNs framework. Moreover, challenging contact problems with the consideration of geometrical and material nonlinearities are tested. It has been shown that the proposed PINNs framework provides a reliable and powerful tool for nonlinear contact mechanics. More importantly, the proposed PINNs framework exhibits competitive computational efficiency to the commercial FEM software when dealing with those complex contact problems. The codes used in this manuscript are available at https://github.com/JinshuaiBai/energy_PINN_Contact.(The code will be available after acceptance) <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03671v1-abstract-full').style.display = 'none'; document.getElementById('2411.03671v1-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">22 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/2411.02959">arXiv:2411.02959</a> <span> [<a href="https://arxiv.org/pdf/2411.02959">pdf</a>, <a href="https://arxiv.org/format/2411.02959">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"> HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Tan%2C+J">Jiejun Tan</a>, <a href="/search/?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a>, <a href="/search/?searchtype=author&query=Wang%2C+W">Wen Wang</a>, <a href="/search/?searchtype=author&query=Wang%2C+M">Mang Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Weipeng Chen</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2411.02959v1-abstract-short" style="display: inline;"> Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs. The Web is a major source of external knowledge used in RAG systems, and many commercial systems such as ChatGPT and Perplexity have used Web search engines as their major retrieval systems. Typically, such RAG systems retrieve search results, download HTML sources… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02959v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02959v1-abstract-full" style="display: none;"> Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs. The Web is a major source of external knowledge used in RAG systems, and many commercial systems such as ChatGPT and Perplexity have used Web search engines as their major retrieval systems. Typically, such RAG systems retrieve search results, download HTML sources of the results, and then extract plain texts from the HTML sources. Plain text documents or chunks are fed into the LLMs to augment the generation. However, much of the structural and semantic information inherent in HTML, such as headings and table structures, is lost during this plain-text-based RAG process. To alleviate this problem, we propose HtmlRAG, which uses HTML instead of plain text as the format of retrieved knowledge in RAG. We believe HTML is better than plain text in modeling knowledge in external documents, and most LLMs possess robust capacities to understand HTML. However, utilizing HTML presents new challenges. HTML contains additional content such as tags, JavaScript, and CSS specifications, which bring extra input tokens and noise to the RAG system. To address this issue, we propose HTML cleaning, compression, and pruning strategies, to shorten the HTML while minimizing the loss of information. Specifically, we design a two-step block-tree-based pruning method that prunes useless HTML blocks and keeps only the relevant part of the HTML. Experiments on six QA datasets confirm the superiority of using HTML in RAG systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02959v1-abstract-full').style.display = 'none'; document.getElementById('2411.02959v1-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/2411.00948">arXiv:2411.00948</a> <span> [<a href="https://arxiv.org/pdf/2411.00948">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cell Behavior">q-bio.CB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Multiplex Imaging Analysis in Pathology: a Comprehensive Review on Analytical Approaches and Digital Toolkits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Omar%2C+M">Mohamed Omar</a>, <a href="/search/?searchtype=author&query=Fanelli%2C+G+N">Giuseppe Nicolo Fanelli</a>, <a href="/search/?searchtype=author&query=Socciarelli%2C+F">Fabio Socciarelli</a>, <a href="/search/?searchtype=author&query=Ullanat%2C+V">Varun Ullanat</a>, <a href="/search/?searchtype=author&query=Puchala%2C+S+R">Sreekar Reddy Puchala</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">James Wen</a>, <a href="/search/?searchtype=author&query=Chowdhury%2C+A">Alex Chowdhury</a>, <a href="/search/?searchtype=author&query=Valencia%2C+I">Itzel Valencia</a>, <a href="/search/?searchtype=author&query=Scatena%2C+C">Cristian Scatena</a>, <a href="/search/?searchtype=author&query=Marchionni%2C+L">Luigi Marchionni</a>, <a href="/search/?searchtype=author&query=Umeton%2C+R">Renato Umeton</a>, <a href="/search/?searchtype=author&query=Loda%2C+M">Massimo Loda</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="2411.00948v1-abstract-short" style="display: inline;"> Conventional histopathology has long been essential for disease diagnosis, relying on visual inspection of tissue sections. Immunohistochemistry aids in detecting specific biomarkers but is limited by its single-marker approach, restricting its ability to capture the full tissue environment. The advent of multiplexed imaging technologies, like multiplexed immunofluorescence and spatial transcripto… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00948v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00948v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00948v1-abstract-full" style="display: none;"> Conventional histopathology has long been essential for disease diagnosis, relying on visual inspection of tissue sections. Immunohistochemistry aids in detecting specific biomarkers but is limited by its single-marker approach, restricting its ability to capture the full tissue environment. The advent of multiplexed imaging technologies, like multiplexed immunofluorescence and spatial transcriptomics, allows for simultaneous visualization of multiple biomarkers in a single section, enhancing morphological data with molecular and spatial information. This provides a more comprehensive view of the tissue microenvironment, cellular interactions, and disease mechanisms - crucial for understanding disease progression, prognosis, and treatment response. However, the extensive data from multiplexed imaging necessitates sophisticated computational methods for preprocessing, segmentation, feature extraction, and spatial analysis. These tools are vital for managing large, multidimensional datasets, converting raw imaging data into actionable insights. By automating labor-intensive tasks and enhancing reproducibility and accuracy, computational tools are pivotal in diagnostics and research. This review explores the current landscape of multiplexed imaging in pathology, detailing workflows and key technologies like PathML, an AI-powered platform that streamlines image analysis, making complex dataset interpretation accessible for clinical and research settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00948v1-abstract-full').style.display = 'none'; document.getElementById('2411.00948v1-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">54 pages (39 manuscript + 14 supplementary), 3 figures (figure 1, 2 and supplementary figure 1), 6 Tables (Table 1, 2, 3 and supplementary table 1,2,3)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00642">arXiv:2411.00642</a> <span> [<a href="https://arxiv.org/pdf/2411.00642">pdf</a>, <a href="https://arxiv.org/format/2411.00642">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> LLM-Based Misconfiguration Detection for AWS Serverless Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jinfeng Wen</a>, <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhenpeng Chen</a>, <a href="/search/?searchtype=author&query=Sarro%2C+F">Federica Sarro</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Z">Zixi Zhu</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Yi Liu</a>, <a href="/search/?searchtype=author&query=Ping%2C+H">Haodi Ping</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Shangguang 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="2411.00642v1-abstract-short" style="display: inline;"> Serverless computing is an emerging cloud computing paradigm that enables developers to build applications at the function level, known as serverless applications. Amazon Web Services (AWS), the leading provider in this domain, provides the Serverless Application Model (AWS SAM), the most widely adopted configuration schema for configuring and managing serverless applications through a specified f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00642v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00642v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00642v1-abstract-full" style="display: none;"> Serverless computing is an emerging cloud computing paradigm that enables developers to build applications at the function level, known as serverless applications. Amazon Web Services (AWS), the leading provider in this domain, provides the Serverless Application Model (AWS SAM), the most widely adopted configuration schema for configuring and managing serverless applications through a specified file. However, misconfigurations pose a significant challenge in serverless development. Traditional data-driven techniques may struggle with serverless applications because the complexity of serverless configurations hinders pattern recognition, and it is challenging to gather complete datasets that cover all possible configurations. Leveraging vast amounts of publicly available data during pre-training, LLMs can have the potential to assist in identifying and explaining misconfigurations in serverless applications. In this paper, we introduce SlsDetector, the first framework leveraging LLMs to detect misconfigurations in serverless applications. SlsDetector utilizes effective prompt engineering with zero-shot learning to identify configuration issues. It designs multi-dimensional constraints specifically tailored to the configuration characteristics of serverless applications and leverages the Chain of Thought technique to enhance LLMs inferences. We evaluate SlsDetector on a curated dataset of 110 configuration files. Our results show that SlsDetector, based on ChatGPT-4o, achieves a precision of 72.88%, recall of 88.18%, and F1-score of 79.75%, outperforming state-of-the-art data-driven approaches by 53.82, 17.40, and 49.72 percentage points, respectively. Furthermore, we investigate the generalization capability of SlsDetector by applying recent LLMs, including Llama 3.1 (405B) Instruct Turbo and Gemini 1.5 Pro, with results showing consistently high effectiveness across these models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00642v1-abstract-full').style.display = 'none'; document.getElementById('2411.00642v1-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/2410.23829">arXiv:2410.23829</a> <span> [<a href="https://arxiv.org/pdf/2410.23829">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Accelerator Physics">physics.acc-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> First Proof of Principle Experiment for Muon Production with Ultrashort High Intensity Laser </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+F">Feng Zhang</a>, <a href="/search/?searchtype=author&query=Deng%2C+L">Li Deng</a>, <a href="/search/?searchtype=author&query=Ge%2C+Y">Yanjie Ge</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jiaxing Wen</a>, <a href="/search/?searchtype=author&query=Cui%2C+B">Bo Cui</a>, <a href="/search/?searchtype=author&query=Feng%2C+K">Ke Feng</a>, <a href="/search/?searchtype=author&query=Wang%2C+H">Hao Wang</a>, <a href="/search/?searchtype=author&query=Wu%2C+C">Chen Wu</a>, <a href="/search/?searchtype=author&query=Pan%2C+Z">Ziwen Pan</a>, <a href="/search/?searchtype=author&query=Liu%2C+H">Hongjie Liu</a>, <a href="/search/?searchtype=author&query=Deng%2C+Z">Zhigang Deng</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zongxin Zhang</a>, <a href="/search/?searchtype=author&query=Chen%2C+L">Liangwen Chen</a>, <a href="/search/?searchtype=author&query=Yan%2C+D">Duo Yan</a>, <a href="/search/?searchtype=author&query=Shan%2C+L">Lianqiang Shan</a>, <a href="/search/?searchtype=author&query=Yuan%2C+Z">Zongqiang Yuan</a>, <a href="/search/?searchtype=author&query=Tian%2C+C">Chao Tian</a>, <a href="/search/?searchtype=author&query=Qian%2C+J">Jiayi Qian</a>, <a href="/search/?searchtype=author&query=Zhu%2C+J">Jiacheng Zhu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Y">Yi Xu</a>, <a href="/search/?searchtype=author&query=Yu%2C+Y">Yuhong Yu</a>, <a href="/search/?searchtype=author&query=Zhang%2C+X">Xueheng Zhang</a>, <a href="/search/?searchtype=author&query=Yang%2C+L">Lei Yang</a>, <a href="/search/?searchtype=author&query=Zhou%2C+W">Weimin Zhou</a>, <a href="/search/?searchtype=author&query=Gu%2C+Y">Yuqiu Gu</a> , et al. (4 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="2410.23829v1-abstract-short" style="display: inline;"> Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23829v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23829v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23829v1-abstract-full" style="display: none;"> Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $渭$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23829v1-abstract-full').style.display = 'none'; document.getElementById('2410.23829v1-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/2410.23090">arXiv:2410.23090</a> <span> [<a href="https://arxiv.org/pdf/2410.23090">pdf</a>, <a href="https://arxiv.org/format/2410.23090">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Cheng%2C+Y">Yiruo Cheng</a>, <a href="/search/?searchtype=author&query=Mao%2C+K">Kelong Mao</a>, <a href="/search/?searchtype=author&query=Zhao%2C+Z">Ziliang Zhao</a>, <a href="/search/?searchtype=author&query=Dong%2C+G">Guanting Dong</a>, <a href="/search/?searchtype=author&query=Qian%2C+H">Hongjin Qian</a>, <a href="/search/?searchtype=author&query=Wu%2C+Y">Yongkang Wu</a>, <a href="/search/?searchtype=author&query=Sakai%2C+T">Tetsuya Sakai</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</a>, <a href="/search/?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</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="2410.23090v1-abstract-short" style="display: inline;"> Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23090v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23090v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23090v1-abstract-full" style="display: none;"> Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia and tackles key challenges such as open-domain coverage, knowledge intensity, free-form responses, and topic shifts. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling. We propose a unified framework to standardize various conversational RAG methods and conduct a comprehensive evaluation of these methods on CORAL, demonstrating substantial opportunities for improving existing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23090v1-abstract-full').style.display = 'none'; document.getElementById('2410.23090v1-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/2410.20215">arXiv:2410.20215</a> <span> [<a href="https://arxiv.org/pdf/2410.20215">pdf</a>, <a href="https://arxiv.org/format/2410.20215">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"> DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Tang%2C+X">Xinyu Tang</a>, <a href="/search/?searchtype=author&query=Wang%2C+X">Xiaolei Wang</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.20215v1-abstract-short" style="display: inline;"> Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage historical pseudo-demonstrations to help solve the current problem. They assume that problems are from the same task and traverse them in a random or… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20215v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20215v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20215v1-abstract-full" style="display: none;"> Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage historical pseudo-demonstrations to help solve the current problem. They assume that problems are from the same task and traverse them in a random order. However, in real-world scenarios, problems usually come from diverse tasks, and only a few belong to the same task. The random traversing order may generate unreliable pseudo-demonstrations and lead to error accumulation. To address this problem, we reformulate ZS-ICL as a planning problem and propose a Demonstration-aware Monte Carlo Tree Search (MCTS) approach (DAWN-ICL), which leverages MCTS to strategically plan the problem-solving trajectories for ZS-ICL. In addition, to achieve effective and efficient Q value estimation, we propose a novel demonstration-aware Q-value function and use it to enhance the selection phase and accelerate the expansion and simulation phases in MCTS. Extensive experiments demonstrate the effectiveness and efficiency of DAWN-ICL on in-domain and cross-domain scenarios, and it even outperforms ICL using human-annotated labels. The code is available at https://github.com/RUCAIBox/MCTS4ZSICL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20215v1-abstract-full').style.display = 'none'; document.getElementById('2410.20215v1-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> 26 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/2410.13694">arXiv:2410.13694</a> <span> [<a href="https://arxiv.org/pdf/2410.13694">pdf</a>, <a href="https://arxiv.org/format/2410.13694">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Exploring the Design Space of Visual Context Representation in Video MLLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Du%2C+Y">Yifan Du</a>, <a href="/search/?searchtype=author&query=Huo%2C+Y">Yuqi Huo</a>, <a href="/search/?searchtype=author&query=Zhou%2C+K">Kun Zhou</a>, <a href="/search/?searchtype=author&query=Zhao%2C+Z">Zijia Zhao</a>, <a href="/search/?searchtype=author&query=Lu%2C+H">Haoyu Lu</a>, <a href="/search/?searchtype=author&query=Huang%2C+H">Han Huang</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wang%2C+B">Bingning Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Weipeng Chen</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.13694v1-abstract-short" style="display: inline;"> Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation, which refers to the scheme to select frames from a video and further select the tokens from a frame. In this paper, we explore the design space for v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13694v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13694v1-abstract-full" style="display: none;"> Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation, which refers to the scheme to select frames from a video and further select the tokens from a frame. In this paper, we explore the design space for visual context representation, and aim to improve the performance of video MLLMs by finding more effective representation schemes. Firstly, we formulate the task of visual context representation as a constrained optimization problem, and model the language modeling loss as a function of the number of frames and the number of embeddings (or tokens) per frame, given the maximum visual context window size. Then, we explore the scaling effects in frame selection and token selection respectively, and fit the corresponding function curve by conducting extensive empirical experiments. We examine the effectiveness of typical selection strategies and present empirical findings to determine the two factors. Furthermore, we study the joint effect of frame selection and token selection, and derive the optimal formula for determining the two factors. We demonstrate that the derived optimal settings show alignment with the best-performed results of empirical experiments. Our code and model are available at: https://github.com/RUCAIBox/Opt-Visor. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13694v1-abstract-full').style.display = 'none'; document.getElementById('2410.13694v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 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">Long Video MLLM; work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13169">arXiv:2410.13169</a> <span> [<a href="https://arxiv.org/pdf/2410.13169">pdf</a>, <a href="https://arxiv.org/format/2410.13169">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Deterministic Creation of Identical Monochromatic Quantum Emitters in Hexagonal Boron Nitride </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hua%2C+M">Muchuan Hua</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Wei-Ying Chen</a>, <a href="/search/?searchtype=author&query=Hou%2C+H">Hanyu Hou</a>, <a href="/search/?searchtype=author&query=Kolluru%2C+V+S+C">Venkata Surya Chaitanya Kolluru</a>, <a href="/search/?searchtype=author&query=Chan%2C+M+K+Y">Maria K. Y. Chan</a>, <a href="/search/?searchtype=author&query=Liu%2C+H">HaiHua Liu</a>, <a href="/search/?searchtype=author&query=Gage%2C+T+E">Thomas E. Gage</a>, <a href="/search/?searchtype=author&query=Zuo%2C+J">Jian-Min Zuo</a>, <a href="/search/?searchtype=author&query=Diroll%2C+B+T">Benjamin T. Diroll</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jianguo Wen</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="2410.13169v1-abstract-short" style="display: inline;"> Deterministic creation of quantum emitters with high single-photon-purity and excellent indistinguishability is essential for practical applications in quantum information science. Many successful attempts have been carried out in hexagonal boron nitride showing its capability of hosting room temperature quantum emitters. However, most of the existing methods produce emitters with heterogeneous op… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13169v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13169v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13169v1-abstract-full" style="display: none;"> Deterministic creation of quantum emitters with high single-photon-purity and excellent indistinguishability is essential for practical applications in quantum information science. Many successful attempts have been carried out in hexagonal boron nitride showing its capability of hosting room temperature quantum emitters. However, most of the existing methods produce emitters with heterogeneous optical properties and unclear creation mechanisms. Here, the authors report a deterministic creation of identical room temperature quantum emitters using masked-carbon-ion implantation on freestanding hBN flakes. Quantum emitters fabricated by our approach showed thermally limited monochromaticity with an emission center wavelength distribution of 590.7 +- 2.7 nm, a narrow full width half maximum of 7.1 +- 1.7 nm, excellent brightness (1MHz emission rate), and extraordinary stability. Our method provides a reliable platform for characterization and fabrication research on hBN based quantum emitters, helping to reveal the origins of the single-photon-emission behavior in hBN and favoring practical applications, especially the industrial-scale production of quantum technology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13169v1-abstract-full').style.display = 'none'; document.getElementById('2410.13169v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 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">29 pages, 5 figures, research article</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12327">arXiv:2410.12327</a> <span> [<a href="https://arxiv.org/pdf/2410.12327">pdf</a>, <a href="https://arxiv.org/format/2410.12327">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"> Neuron-based Personality Trait Induction in Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Deng%2C+J">Jia Deng</a>, <a href="/search/?searchtype=author&query=Tang%2C+T">Tianyi Tang</a>, <a href="/search/?searchtype=author&query=Yin%2C+Y">Yanbin Yin</a>, <a href="/search/?searchtype=author&query=Yang%2C+W">Wenhao Yang</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.12327v1-abstract-short" style="display: inline;"> Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a larg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12327v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12327v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12327v1-abstract-full" style="display: none;"> Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and is designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PersonalityBench, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12327v1-abstract-full').style.display = 'none'; document.getElementById('2410.12327v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 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/2410.11582">arXiv:2410.11582</a> <span> [<a href="https://arxiv.org/pdf/2410.11582">pdf</a>, <a href="https://arxiv.org/format/2410.11582">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> On-the-fly Modulation for Balanced Multimodal Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wei%2C+Y">Yake Wei</a>, <a href="/search/?searchtype=author&query=Hu%2C+D">Di Hu</a>, <a href="/search/?searchtype=author&query=Du%2C+H">Henghui Du</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.11582v1-abstract-short" style="display: inline;"> Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective for all modalities, leads to imbalanced and under-optimized uni-modal representations. Specifically, we point out that there often exists modality with more discr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11582v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11582v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11582v1-abstract-full" style="display: none;"> Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective for all modalities, leads to imbalanced and under-optimized uni-modal representations. Specifically, we point out that there often exists modality with more discriminative information, e.g., vision of playing football and sound of blowing wind. They could dominate the joint training process, resulting in other modalities being significantly under-optimized. To alleviate this problem, we first analyze the under-optimized phenomenon from both the feed-forward and the back-propagation stages during optimization. Then, On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies are proposed to modulate the optimization of each modality, by monitoring the discriminative discrepancy between modalities during training. Concretely, OPM weakens the influence of the dominant modality by dropping its feature with dynamical probability in the feed-forward stage, while OGM mitigates its gradient in the back-propagation stage. In experiments, our methods demonstrate considerable improvement across a variety of multimodal tasks. These simple yet effective strategies not only enhance performance in vanilla and task-oriented multimodal models, but also in more complex multimodal tasks, showcasing their effectiveness and flexibility. The source code is available at \url{https://github.com/GeWu-Lab/BML_TPAMI2024}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11582v1-abstract-full').style.display = 'none'; document.getElementById('2410.11582v1-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> <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 T-PAMI 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/2410.10275">arXiv:2410.10275</a> <span> [<a href="https://arxiv.org/pdf/2410.10275">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Superconductivity">cond-mat.supr-con</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Probing the Meissner effect in pressurized bilayer nickelate superconductors using diamond quantum sensors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Junyan Wen</a>, <a href="/search/?searchtype=author&query=Xu%2C+Y">Yue Xu</a>, <a href="/search/?searchtype=author&query=Wang%2C+G">Gang Wang</a>, <a href="/search/?searchtype=author&query=He%2C+Z">Ze-Xu He</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yang Chen</a>, <a href="/search/?searchtype=author&query=Wang%2C+N">Ningning Wang</a>, <a href="/search/?searchtype=author&query=Lu%2C+T">Tenglong Lu</a>, <a href="/search/?searchtype=author&query=Ma%2C+X">Xiaoli Ma</a>, <a href="/search/?searchtype=author&query=Jin%2C+F">Feng Jin</a>, <a href="/search/?searchtype=author&query=Chen%2C+L">Liucheng Chen</a>, <a href="/search/?searchtype=author&query=Liu%2C+M">Miao Liu</a>, <a href="/search/?searchtype=author&query=Fan%2C+J">Jing-Wei Fan</a>, <a href="/search/?searchtype=author&query=Liu%2C+X">Xiaobing Liu</a>, <a href="/search/?searchtype=author&query=Pan%2C+X">Xin-Yu Pan</a>, <a href="/search/?searchtype=author&query=Liu%2C+G">Gang-Qin Liu</a>, <a href="/search/?searchtype=author&query=Cheng%2C+J">Jinguang Cheng</a>, <a href="/search/?searchtype=author&query=Yu%2C+X">Xiaohui 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="2410.10275v1-abstract-short" style="display: inline;"> Recent reports on the signatures of high-temperature superconductivity with a critical temperature Tc close to 80 K have triggered great research interest and extensive follow-up studies. Although zero-resistance state has been successfully achieved under improved hydrostatic pressure conditions, there is no clear evidence of superconducting diamagnetism in pressurized… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10275v1-abstract-full').style.display = 'inline'; document.getElementById('2410.10275v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.10275v1-abstract-full" style="display: none;"> Recent reports on the signatures of high-temperature superconductivity with a critical temperature Tc close to 80 K have triggered great research interest and extensive follow-up studies. Although zero-resistance state has been successfully achieved under improved hydrostatic pressure conditions, there is no clear evidence of superconducting diamagnetism in pressurized $\mathrm{La_{3}Ni_{2}O_{7-未}}$ due to the low superconducting volume fraction and limited magnetic measurement techniques under high pressure conditions. Here, using shallow nitrogen-vacancy centers implanted on the culet of diamond anvils as in-situ quantum sensors, we observe convincing evidence for the Meissner effect in polycrystalline samples $\mathrm{La_{3}Ni_{2}O_{7-未}}$ and $\mathrm{La_{2}PrNi_{2}O_{7}}$: the magnetic field expulsion during both field cooling and field warming processes. The correlated measurements of Raman spectra and NV-based magnetic imaging indicate an incomplete structural transformation related to the displacement of oxygen ions emerging in the non-superconducting region. Furthermore, comparative experiments on different pressure transmitting media (silicone oil and KBr) and nickelates ($\mathrm{La_{3}Ni_{2}O_{7-未}}$ and $\mathrm{La_{2}PrNi_{2}O_{7}}$) reveal that an improved hydrostatic pressure conditions and the substitution of La by Pr in $\mathrm{La_{3}Ni_{2}O_{7-未}}$ can dramatically increase the superconductivity. Our work clarifies the controversy about the Meissner effect of bilayer nickelate and contributes to a deeper understanding of the mechanism of nickelate high-temperature superconductors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.10275v1-abstract-full').style.display = 'none'; document.getElementById('2410.10275v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 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/2410.09584">arXiv:2410.09584</a> <span> [<a href="https://arxiv.org/pdf/2410.09584">pdf</a>, <a href="https://arxiv.org/format/2410.09584">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="Information Retrieval">cs.IR</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"> Toward General Instruction-Following Alignment for Retrieval-Augmented Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Dong%2C+G">Guanting Dong</a>, <a href="/search/?searchtype=author&query=Song%2C+X">Xiaoshuai Song</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Y">Yutao Zhu</a>, <a href="/search/?searchtype=author&query=Qiao%2C+R">Runqi Qiao</a>, <a href="/search/?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.09584v1-abstract-short" style="display: inline;"> Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) alignment within the RAG domain remains limited. To address this issue, we propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipelin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09584v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09584v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09584v1-abstract-full" style="display: none;"> Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) alignment within the RAG domain remains limited. To address this issue, we propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipeline for instruction-following alignment in RAG systems. We start by manually crafting a minimal set of atomic instructions (<100) and developing combination rules to synthesize and verify complex instructions for a seed set. We then use supervised models for instruction rewriting while simultaneously generating code to automate the verification of instruction quality via a Python executor. Finally, we integrate these instructions with extensive RAG and general data samples, scaling up to a high-quality VIF-RAG-QA dataset (>100k) through automated processes. To further bridge the gap in instruction-following auto-evaluation for RAG systems, we introduce FollowRAG Benchmark, which includes approximately 3K test samples, covering 22 categories of general instruction constraints and four knowledge-intensive QA datasets. Due to its robust pipeline design, FollowRAG can seamlessly integrate with different RAG benchmarks. Using FollowRAG and eight widely-used IF and foundational abilities benchmarks for LLMs, we demonstrate that VIF-RAG markedly enhances LLM performance across a broad range of general instruction constraints while effectively leveraging its capabilities in RAG scenarios. Further analysis offers practical insights for achieving IF alignment in RAG systems. Our code and datasets are released at https://FollowRAG.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09584v1-abstract-full').style.display = 'none'; document.getElementById('2410.09584v1-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 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">Working in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08197">arXiv:2410.08197</a> <span> [<a href="https://arxiv.org/pdf/2410.08197">pdf</a>, <a href="https://arxiv.org/format/2410.08197">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"> From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Qu%2C+C">Changle Qu</a>, <a href="/search/?searchtype=author&query=Dai%2C+S">Sunhao Dai</a>, <a href="/search/?searchtype=author&query=Wei%2C+X">Xiaochi Wei</a>, <a href="/search/?searchtype=author&query=Cai%2C+H">Hengyi Cai</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Shuaiqiang Wang</a>, <a href="/search/?searchtype=author&query=Yin%2C+D">Dawei Yin</a>, <a href="/search/?searchtype=author&query=Xu%2C+J">Jun Xu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.08197v1-abstract-short" style="display: inline;"> Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical chall… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08197v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08197v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08197v1-abstract-full" style="display: none;"> Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical challenge of bridging the comprehension gap between LLMs and external tools due to the inadequacies and inaccuracies inherent in existing human-centric tool documentation. We propose a novel framework, DRAFT, aimed at Dynamically Refining tool documentation through the Analysis of Feedback and Trails emanating from LLMs' interactions with external tools. This methodology pivots on an innovative trial-and-error approach, consisting of three distinct learning phases: experience gathering, learning from experience, and documentation rewriting, to iteratively enhance the tool documentation. This process is further optimized by implementing a diversity-promoting exploration strategy to ensure explorative diversity and a tool-adaptive termination mechanism to prevent overfitting while enhancing efficiency. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality, fostering a deeper comprehension and more effective utilization of tools by LLMs. Notably, our analysis reveals that the tool documentation refined via our approach demonstrates robust cross-model generalization capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08197v1-abstract-full').style.display = 'none'; document.getElementById('2410.08197v1-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 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/2410.07825">arXiv:2410.07825</a> <span> [<a href="https://arxiv.org/pdf/2410.07825">pdf</a>, <a href="https://arxiv.org/format/2410.07825">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"> Extracting and Transferring Abilities For Building Multi-lingual Ability-enhanced Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chen%2C+Z">Zhipeng Chen</a>, <a href="/search/?searchtype=author&query=Song%2C+L">Liang Song</a>, <a href="/search/?searchtype=author&query=Zhou%2C+K">Kun Zhou</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wang%2C+B">Bingning Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+W">Weipeng Chen</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.07825v1-abstract-short" style="display: inline;"> Multi-lingual ability transfer has become increasingly important for the broad application of large language models (LLMs). Existing work highly relies on training with the multi-lingual ability-related data, which may be not available for low-resource languages. To solve it, we propose a Multi-lingual Ability Extraction and Transfer approach, named as MAET. Our key idea is to decompose and extrac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07825v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07825v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07825v1-abstract-full" style="display: none;"> Multi-lingual ability transfer has become increasingly important for the broad application of large language models (LLMs). Existing work highly relies on training with the multi-lingual ability-related data, which may be not available for low-resource languages. To solve it, we propose a Multi-lingual Ability Extraction and Transfer approach, named as MAET. Our key idea is to decompose and extract language-agnostic ability-related weights from LLMs, and transfer them across different languages by simple addition and subtraction operations without training. Specially, our MAET consists of the extraction and transfer stages. In the extraction stage, we firstly locate key neurons that are highly related to specific abilities, and then employ them to extract the transferable ability-specific weights. In the transfer stage, we further select the ability-related parameter tensors, and design the merging strategy based on the linguistic and ability specific weights, to build the multi-lingual ability-enhanced LLM. To demonstrate the effectiveness of our proposed approach, we conduct extensive experiments on mathematical and scientific tasks in both high-resource lingual and low-resource lingual scenarios. Experiment results have shown that MAET can effectively and efficiently extract and transfer the advanced abilities, and outperform training-based baseline methods. Our code and data are available at \url{https://github.com/RUCAIBox/MAET}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07825v1-abstract-full').style.display = 'none'; document.getElementById('2410.07825v1-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 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">18 Pages. Working in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04800">arXiv:2410.04800</a> <span> [<a href="https://arxiv.org/pdf/2410.04800">pdf</a>, <a href="https://arxiv.org/format/2410.04800">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Metric Geometry">math.MG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Functional Analysis">math.FA</span> </div> </div> <p class="title is-5 mathjax"> A New Linear Programming Method in Sphere Packing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Mo%2C+Q">Qun Mo</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jinming Wen</a>, <a href="/search/?searchtype=author&query=Xia%2C+Y">Yu Xia</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.04800v1-abstract-short" style="display: inline;"> Inspired by the linear programming method developed by Cohn and Elkies (Ann. Math. 157(2): 689-714, 2003), we introduce a new linear programming method to solve the sphere packing problem. More concretely, we consider sequences of auxiliary functions $\{g_m\}_{m\in \mathbb{N}^{+}}$, where $g_m$ is a $m螞$-periodic auxiliary function defined on $\mathbb{R}^n$, with $螞$ being a given full-rank lattic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04800v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04800v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04800v1-abstract-full" style="display: none;"> Inspired by the linear programming method developed by Cohn and Elkies (Ann. Math. 157(2): 689-714, 2003), we introduce a new linear programming method to solve the sphere packing problem. More concretely, we consider sequences of auxiliary functions $\{g_m\}_{m\in \mathbb{N}^{+}}$, where $g_m$ is a $m螞$-periodic auxiliary function defined on $\mathbb{R}^n$, with $螞$ being a given full-rank lattice in $\mathbb{R}^n$. This new method extends the original approach and offers a greater flexibility. Furthermore, using this new linear programming framework, we construct several effective auxiliary functions for dimensions $n=1,2,3$. We hope this approach provides valuable insights into solving sphere packing problems for $n=2,3$ and even higher dimensions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04800v1-abstract-full').style.display = 'none'; document.getElementById('2410.04800v1-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 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/2410.04360">arXiv:2410.04360</a> <span> [<a href="https://arxiv.org/pdf/2410.04360">pdf</a>, <a href="https://arxiv.org/format/2410.04360">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> GenSim: A General Social Simulation Platform with Large Language Model based Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Tang%2C+J">Jiakai Tang</a>, <a href="/search/?searchtype=author&query=Gao%2C+H">Heyang Gao</a>, <a href="/search/?searchtype=author&query=Pan%2C+X">Xuchen Pan</a>, <a href="/search/?searchtype=author&query=Wang%2C+L">Lei Wang</a>, <a href="/search/?searchtype=author&query=Tan%2C+H">Haoran Tan</a>, <a href="/search/?searchtype=author&query=Gao%2C+D">Dawei Gao</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yushuo Chen</a>, <a href="/search/?searchtype=author&query=Chen%2C+X">Xu Chen</a>, <a href="/search/?searchtype=author&query=Lin%2C+Y">Yankai Lin</a>, <a href="/search/?searchtype=author&query=Li%2C+Y">Yaliang Li</a>, <a href="/search/?searchtype=author&query=Ding%2C+B">Bolin Ding</a>, <a href="/search/?searchtype=author&query=Zhou%2C+J">Jingren Zhou</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jun Wang</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2410.04360v2-abstract-short" style="display: inline;"> With the rapid advancement of large language models (LLMs), recent years have witnessed many promising studies on leveraging LLM-based agents to simulate human social behavior. While prior work has demonstrated significant potential across various domains, much of it has focused on specific scenarios involving a limited number of agents and has lacked the ability to adapt when errors occur during… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04360v2-abstract-full').style.display = 'inline'; document.getElementById('2410.04360v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04360v2-abstract-full" style="display: none;"> With the rapid advancement of large language models (LLMs), recent years have witnessed many promising studies on leveraging LLM-based agents to simulate human social behavior. While prior work has demonstrated significant potential across various domains, much of it has focused on specific scenarios involving a limited number of agents and has lacked the ability to adapt when errors occur during simulation. To overcome these limitations, we propose a novel LLM-agent-based simulation platform called \textit{GenSim}, which: (1) \textbf{Abstracts a set of general functions} to simplify the simulation of customized social scenarios; (2) \textbf{Supports one hundred thousand agents} to better simulate large-scale populations in real-world contexts; (3) \textbf{Incorporates error-correction mechanisms} to ensure more reliable and long-term simulations. To evaluate our platform, we assess both the efficiency of large-scale agent simulations and the effectiveness of the error-correction mechanisms. To our knowledge, GenSim represents an initial step toward a general, large-scale, and correctable social simulation platform based on LLM agents, promising to further advance the field of social science. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04360v2-abstract-full').style.display = 'none'; document.getElementById('2410.04360v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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/2410.04006">arXiv:2410.04006</a> <span> [<a href="https://arxiv.org/pdf/2410.04006">pdf</a>, <a href="https://arxiv.org/format/2410.04006">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optics">physics.optics</span> </div> </div> <p class="title is-5 mathjax"> Universal parity and duality asymmetries-based optical force/torque framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yuan%2C+X">Xu Yuan</a>, <a href="/search/?searchtype=author&query=Zhao%2C+X">Xiaoshu Zhao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jiquan Wen</a>, <a href="/search/?searchtype=author&query=Zheng%2C+H">Hongxia Zheng</a>, <a href="/search/?searchtype=author&query=Li%2C+X">Xiao Li</a>, <a href="/search/?searchtype=author&query=Chen%2C+H">Huajin Chen</a>, <a href="/search/?searchtype=author&query=Ng%2C+J">Jack Ng</a>, <a href="/search/?searchtype=author&query=Lin%2C+Z">Zhifang Lin</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="2410.04006v1-abstract-short" style="display: inline;"> Understanding how the structured incident light interacts with the inherent properties of the manipulated particle and governs the optical force/torque exerted is a cornerstone in the design of optical manipulation techniques, apart from its theoretical significance. Based on the Cartesian multipole expansion theory, we establish a framework for optical force/torque exerted on an arbitrary sized b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04006v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04006v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04006v1-abstract-full" style="display: none;"> Understanding how the structured incident light interacts with the inherent properties of the manipulated particle and governs the optical force/torque exerted is a cornerstone in the design of optical manipulation techniques, apart from its theoretical significance. Based on the Cartesian multipole expansion theory, we establish a framework for optical force/torque exerted on an arbitrary sized bi-isotropic (chiral) spherical particle immersed in generic monochromatic optical fields. Rigorous expressions are thus derived which explicitly bridges such mechanical effects of light with particle-property-dependent coefficients and "force/torque source" quantities that characterize the incident light structures. Such quantities, totalled only 12, are quadratic in terms of electric and magnetic field vectors, among which are linear and angular momenta, gradient of energy density, spin density, and helicity. They are further organized into four categories based on their parity (P) and duality (D) symmetries and shown to couple with a particle with different P and D symmetries to induce optical force/torque. This classification specifies the symmetry-breaking criteria required to induce optical force/torque, offering a promising roadmap for engineering the optical manipulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04006v1-abstract-full').style.display = 'none'; document.getElementById('2410.04006v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 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/2410.01176">arXiv:2410.01176</a> <span> [<a href="https://arxiv.org/pdf/2410.01176">pdf</a>, <a href="https://arxiv.org/format/2410.01176">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"> Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhong%2C+Y">Yue Zhong</a>, <a href="/search/?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jinbo Wen</a>, <a href="/search/?searchtype=author&query=Ye%2C+D">Dongdong Ye</a>, <a href="/search/?searchtype=author&query=Nie%2C+J">Jiangtian Nie</a>, <a href="/search/?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/?searchtype=author&query=Gao%2C+X">Xiaozheng Gao</a>, <a href="/search/?searchtype=author&query=Xie%2C+S">Shengli Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.01176v1-abstract-short" style="display: inline;"> Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space, enabling a wide range of applications. This evolution has led to the development of the Vehicular Embodied AI NETwork (VEANET), where advanced AI capabilities are integrated into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AV… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01176v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01176v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01176v1-abstract-full" style="display: none;"> Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space, enabling a wide range of applications. This evolution has led to the development of the Vehicular Embodied AI NETwork (VEANET), where advanced AI capabilities are integrated into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AVs), are autonomous entities that can perceive their environment and take actions to achieve specific goals, actively interacting with the physical world. Embodied twins are digital models of these embodied agents, with various embodied AI twins for intelligent applications in cyberspace. In VEANET, embodied AI twins act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving using generative AI models. Due to limited computational resources of AVs, these AVs often offload computationally intensive tasks, such as constructing and updating embodied AI twins, to nearby RSUs. However, since the rapid mobility of AVs and the limited provision coverage of a single RSU, embodied AI twins require dynamic migrations from current RSU to other RSUs in real-time, resulting in the challenge of selecting suitable RSUs for efficient embodied AI twins migrations. Given information asymmetry, AVs cannot know the detailed information of RSUs. To this end, in this paper, we construct a multi-dimensional contract theoretical model between AVs and alternative RSUs. Considering that AVs may exhibit irrational behavior, we utilize prospect theory instead of expected utility theory to model the actual utilities of AVs. Finally, we employ a generative diffusion model-based algorithm to identify the optimal contract designs. Compared with traditional deep reinforcement learning algorithms, numerical results demonstrate the effectiveness of the proposed scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01176v1-abstract-full').style.display = 'none'; document.getElementById('2410.01176v1-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 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/2409.20163">arXiv:2409.20163</a> <span> [<a href="https://arxiv.org/pdf/2409.20163">pdf</a>, <a href="https://arxiv.org/format/2409.20163">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"> MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+Z">Zeyu Zhang</a>, <a href="/search/?searchtype=author&query=Dai%2C+Q">Quanyu Dai</a>, <a href="/search/?searchtype=author&query=Chen%2C+L">Luyu Chen</a>, <a href="/search/?searchtype=author&query=Jiang%2C+Z">Zeren Jiang</a>, <a href="/search/?searchtype=author&query=Li%2C+R">Rui Li</a>, <a href="/search/?searchtype=author&query=Zhu%2C+J">Jieming Zhu</a>, <a href="/search/?searchtype=author&query=Chen%2C+X">Xu Chen</a>, <a href="/search/?searchtype=author&query=Xie%2C+Y">Yi Xie</a>, <a href="/search/?searchtype=author&query=Dong%2C+Z">Zhenhua Dong</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2409.20163v1-abstract-short" style="display: inline;"> LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries. However, there still lacks an objective and automatic evaluation on their memory capability, largely due to the challenges in constructing reliable questions and answers (QAs) according to user messages. In this paper, we propose MemSim, a Bayes… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20163v1-abstract-full').style.display = 'inline'; document.getElementById('2409.20163v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.20163v1-abstract-full" style="display: none;"> LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries. However, there still lacks an objective and automatic evaluation on their memory capability, largely due to the challenges in constructing reliable questions and answers (QAs) according to user messages. In this paper, we propose MemSim, a Bayesian simulator designed to automatically construct reliable QAs from generated user messages, simultaneously keeping their diversity and scalability. Specifically, we introduce the Bayesian Relation Network (BRNet) and a causal generation mechanism to mitigate the impact of LLM hallucinations on factual information, facilitating the automatic creation of an evaluation dataset. Based on MemSim, we generate a dataset in the daily-life scenario, named MemDaily, and conduct extensive experiments to assess the effectiveness of our approach. We also provide a benchmark for evaluating different memory mechanisms in LLM-based agents with the MemDaily dataset. To benefit the research community, we have released our project at https://github.com/nuster1128/MemSim. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.20163v1-abstract-full').style.display = 'none'; document.getElementById('2409.20163v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">26 pages, 25 tables, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18707">arXiv:2409.18707</a> <span> [<a href="https://arxiv.org/pdf/2409.18707">pdf</a>, <a href="https://arxiv.org/format/2409.18707">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"> Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wu%2C+K">Kun Wu</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Y">Yichen Zhu</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jinming Li</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Junjie Wen</a>, <a href="/search/?searchtype=author&query=Liu%2C+N">Ning Liu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiyuan Xu</a>, <a href="/search/?searchtype=author&query=Qiu%2C+Q">Qinru Qiu</a>, <a href="/search/?searchtype=author&query=Tang%2C+J">Jian Tang</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="2409.18707v2-abstract-short" style="display: inline;"> Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space: typically, a goal can be accomplished in multiple ways, resulting in a multimodal action distribution for a single task. The complexity of action distribution escalates as the number of tasks increases. In this work, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18707v2-abstract-full').style.display = 'inline'; document.getElementById('2409.18707v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18707v2-abstract-full" style="display: none;"> Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space: typically, a goal can be accomplished in multiple ways, resulting in a multimodal action distribution for a single task. The complexity of action distribution escalates as the number of tasks increases. In this work, we propose \textbf{Discrete Policy}, a robot learning method for training universal agents capable of multi-task manipulation skills. Discrete Policy employs vector quantization to map action sequences into a discrete latent space, facilitating the learning of task-specific codes. These codes are then reconstructed into the action space conditioned on observations and language instruction. We evaluate our method on both simulation and multiple real-world embodiments, including both single-arm and bimanual robot settings. We demonstrate that our proposed Discrete Policy outperforms a well-established Diffusion Policy baseline and many state-of-the-art approaches, including ACT, Octo, and OpenVLA. For example, in a real-world multi-task training setting with five tasks, Discrete Policy achieves an average success rate that is 26\% higher than Diffusion Policy and 15\% higher than OpenVLA. As the number of tasks increases to 12, the performance gap between Discrete Policy and Diffusion Policy widens to 32.5\%, further showcasing the advantages of our approach. Our work empirically demonstrates that learning multi-task policies within the latent space is a vital step toward achieving general-purpose agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18707v2-abstract-full').style.display = 'none'; document.getElementById('2409.18707v2-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> 26 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17506">arXiv:2409.17506</a> <span> [<a href="https://arxiv.org/pdf/2409.17506">pdf</a>, <a href="https://arxiv.org/format/2409.17506">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Optimizing Resource Allocation for Multi-modal Semantic Communication in Mobile AIGC Networks: A Diffusion-based Game Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+J">Jian Liu</a>, <a href="/search/?searchtype=author&query=Xiao%2C+M">Ming Xiao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jinbo Wen</a>, <a href="/search/?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/?searchtype=author&query=Zhang%2C+R">Ruichen Zhang</a>, <a href="/search/?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/?searchtype=author&query=Zhang%2C+W">Weiting Zhang</a>, <a href="/search/?searchtype=author&query=Liu%2C+Y">Ying 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="2409.17506v1-abstract-short" style="display: inline;"> Mobile Artificial Intelligence-Generated Content (AIGC) networks enable massive users to obtain customized content generation services. However, users still need to download a large number of AIGC outputs from mobile AIGC service providers, which strains communication resources and increases the risk of transmission failures. Fortunately, Semantic Communication (SemCom) can improve transmission ef… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17506v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17506v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17506v1-abstract-full" style="display: none;"> Mobile Artificial Intelligence-Generated Content (AIGC) networks enable massive users to obtain customized content generation services. However, users still need to download a large number of AIGC outputs from mobile AIGC service providers, which strains communication resources and increases the risk of transmission failures. Fortunately, Semantic Communication (SemCom) can improve transmission efficiency and reliability through semantic information processing. Moreover, recent advances in Generative Artificial Intelligence (GAI) further enhanced the effectiveness of SemCom through its powerful generative capabilities. However, how to strike a balance between high-quality content generation and the size of semantic information transmitted is a major challenge. In this paper, we propose a Generative Diffusion Model (GDM)-based multi-modal SemCom (GM-SemCom) framework. The framework improves the accuracy of information reconstruction by integrating GDMs and multi-modal semantic information and also adopts a controllable extraction module for efficient and controllable problems of unstable data recovery and slow decoding speed in GAI-enabled SemCom. Then, we introduce a novel metric called Age of Semantic Information (AoSI) based on the concept of Age of Information (AoI) to quantify the freshness of semantic information. To address the resource trading problem within the framework, we propose a Stackelberg game model, which integrates the AoSI with psychological factors to provide a comprehensive measure of user utility. Furthermore, we propose a GDM-based algorithm to solve the game under incomplete information. Compared with the traditional deep reinforcement learning algorithms, numerical results demonstrate that the proposed algorithm converges faster and is closer to the Stackelberg equilibrium. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17506v1-abstract-full').style.display = 'none'; document.getElementById('2409.17506v1-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> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17066">arXiv:2409.17066</a> <span> [<a href="https://arxiv.org/pdf/2409.17066">pdf</a>, <a href="https://arxiv.org/format/2409.17066">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"> VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+Y">Yifei Liu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jicheng Wen</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yang Wang</a>, <a href="/search/?searchtype=author&query=Ye%2C+S">Shengyu Ye</a>, <a href="/search/?searchtype=author&query=Zhang%2C+L+L">Li Lyna Zhang</a>, <a href="/search/?searchtype=author&query=Cao%2C+T">Ting Cao</a>, <a href="/search/?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/?searchtype=author&query=Yang%2C+M">Mao Yang</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="2409.17066v2-abstract-short" style="display: inline;"> Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits). It reduces memory requirements, optimizes storage costs, and decreases memory bandwidth needs during inference. However, due to numerical representa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17066v2-abstract-full').style.display = 'inline'; document.getElementById('2409.17066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17066v2-abstract-full" style="display: none;"> Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits). It reduces memory requirements, optimizes storage costs, and decreases memory bandwidth needs during inference. However, due to numerical representation limitations, traditional scalar-based weight quantization struggles to achieve such extreme low-bit. Recent research on Vector Quantization (VQ) for LLMs has demonstrated the potential for extremely low-bit model quantization by compressing vectors into indices using lookup tables. In this paper, we introduce Vector Post-Training Quantization (VPTQ) for extremely low-bit quantization of LLMs. We use Second-Order Optimization to formulate the LLM VQ problem and guide our quantization algorithm design by solving the optimization. We further refine the weights using Channel-Independent Second-Order Optimization for a granular VQ. In addition, by decomposing the optimization problem, we propose a brief and effective codebook initialization algorithm. We also extend VPTQ to support residual and outlier quantization, which enhances model accuracy and further compresses the model. Our experimental results show that VPTQ reduces model quantization perplexity by $0.01$-$0.34$ on LLaMA-2, $0.38$-$0.68$ on Mistral-7B, $4.41$-$7.34$ on LLaMA-3 over SOTA at 2-bit, with an average accuracy improvement of $0.79$-$1.5\%$ on LLaMA-2, $1\%$ on Mistral-7B, $11$-$22\%$ on LLaMA-3 on QA tasks on average. We only utilize $10.4$-$18.6\%$ of the quantization algorithm execution time, resulting in a $1.6$-$1.8\times$ increase in inference throughput compared to SOTA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17066v2-abstract-full').style.display = 'none'; document.getElementById('2409.17066v2-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> 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">EMNLP 2024, Main, Poster</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16526">arXiv:2409.16526</a> <span> [<a href="https://arxiv.org/pdf/2409.16526">pdf</a>, <a href="https://arxiv.org/format/2409.16526">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> </div> </div> <p class="title is-5 mathjax"> APILOT: Navigating Large Language Models to Generate Secure Code by Sidestepping Outdated API Pitfalls </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Bai%2C+W">Weiheng Bai</a>, <a href="/search/?searchtype=author&query=Xuan%2C+K">Keyang Xuan</a>, <a href="/search/?searchtype=author&query=Huang%2C+P">Pengxiang Huang</a>, <a href="/search/?searchtype=author&query=Wu%2C+Q">Qiushi Wu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jianing Wen</a>, <a href="/search/?searchtype=author&query=Wu%2C+J">Jingjing Wu</a>, <a href="/search/?searchtype=author&query=Lu%2C+K">Kangjie Lu</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="2409.16526v1-abstract-short" style="display: inline;"> With the rapid development of large language models (LLMs), their applications have expanded into diverse fields, such as code assistance. However, the substantial size of LLMs makes their training highly resource- and time-intensive, rendering frequent retraining or updates impractical. Consequently, time-sensitive data can become outdated, potentially misleading LLMs in time-aware tasks. For exa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16526v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16526v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16526v1-abstract-full" style="display: none;"> With the rapid development of large language models (LLMs), their applications have expanded into diverse fields, such as code assistance. However, the substantial size of LLMs makes their training highly resource- and time-intensive, rendering frequent retraining or updates impractical. Consequently, time-sensitive data can become outdated, potentially misleading LLMs in time-aware tasks. For example, new vulnerabilities are discovered in various programs every day. Without updating their knowledge, LLMs may inadvertently generate code that includes these newly discovered vulnerabilities. Current strategies, such as prompt engineering and fine-tuning, do not effectively address this issue. To address this issue, we propose solution, named APILOT, which maintains a realtime, quickly updatable dataset of outdated APIs. Additionally, APILOT utilizes an augmented generation method that leverages this dataset to navigate LLMs in generating secure, version-aware code. We conducted a comprehensive evaluation to measure the effectiveness of APILOT in reducing the incidence of outdated API recommendations across seven different state-of-the-art LLMs. The evaluation results indicate that APILOT can reduce outdated code recommendations by 89.42% on average with limited performance overhead. Interestingly, while enhancing security, APILOT also improves the usability of the code generated by LLMs, showing an average increase of 27.54% in usability. This underscores APILOT's dual capability to enhance both the safety and practical utility of code suggestions in contemporary software development environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16526v1-abstract-full').style.display = 'none'; document.getElementById('2409.16526v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14411">arXiv:2409.14411</a> <span> [<a href="https://arxiv.org/pdf/2409.14411">pdf</a>, <a href="https://arxiv.org/format/2409.14411">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"> Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhu%2C+M">Minjie Zhu</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Y">Yichen Zhu</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jinming Li</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Junjie Wen</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiyuan Xu</a>, <a href="/search/?searchtype=author&query=Liu%2C+N">Ning Liu</a>, <a href="/search/?searchtype=author&query=Cheng%2C+R">Ran Cheng</a>, <a href="/search/?searchtype=author&query=Shen%2C+C">Chaomin Shen</a>, <a href="/search/?searchtype=author&query=Peng%2C+Y">Yaxin Peng</a>, <a href="/search/?searchtype=author&query=Feng%2C+F">Feifei Feng</a>, <a href="/search/?searchtype=author&query=Tang%2C+J">Jian Tang</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="2409.14411v2-abstract-short" style="display: inline;"> Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model size would lead to enhanced performance. However, our observations indicate that Diffusion Policy in transformer architecture (\DP) struggles to scale effectiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14411v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14411v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14411v2-abstract-full" style="display: none;"> Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model size would lead to enhanced performance. However, our observations indicate that Diffusion Policy in transformer architecture (\DP) struggles to scale effectively; even minor additions of layers can deteriorate training outcomes. To address this issue, we introduce Scalable Diffusion Transformer Policy for visuomotor learning. Our proposed method, namely \textbf{\methodname}, introduces two modules that improve the training dynamic of Diffusion Policy and allow the network to better handle multimodal action distribution. First, we identify that \DP~suffers from large gradient issues, making the optimization of Diffusion Policy unstable. To resolve this issue, we factorize the feature embedding of observation into multiple affine layers, and integrate it into the transformer blocks. Additionally, our utilize non-causal attention which allows the policy network to \enquote{see} future actions during prediction, helping to reduce compounding errors. We demonstrate that our proposed method successfully scales the Diffusion Policy from 10 million to 1 billion parameters. This new model, named \methodname, can effectively scale up the model size with improved performance and generalization. We benchmark \methodname~across 50 different tasks from MetaWorld and find that our largest \methodname~outperforms \DP~with an average improvement of 21.6\%. Across 7 real-world robot tasks, our ScaleDP demonstrates an average improvement of 36.25\% over DP-T on four single-arm tasks and 75\% on three bimanual tasks. We believe our work paves the way for scaling up models for visuomotor learning. The project page is available at scaling-diffusion-policy.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14411v2-abstract-full').style.display = 'none'; document.getElementById('2409.14411v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.13504">arXiv:2409.13504</a> <span> [<a href="https://arxiv.org/pdf/2409.13504">pdf</a>, <a href="https://arxiv.org/format/2409.13504">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> </div> <div 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/10.1103/PhysRevLett.133.176401">10.1103/PhysRevLett.133.176401 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Absence of altermagnetic spin splitting character in rutile oxide RuO$_2$ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Liu%2C+J">Jiayu Liu</a>, <a href="/search/?searchtype=author&query=Zhan%2C+J">Jie Zhan</a>, <a href="/search/?searchtype=author&query=Li%2C+T">Tongrui Li</a>, <a href="/search/?searchtype=author&query=Liu%2C+J">Jishan Liu</a>, <a href="/search/?searchtype=author&query=Cheng%2C+S">Shufan Cheng</a>, <a href="/search/?searchtype=author&query=Shi%2C+Y">Yuming Shi</a>, <a href="/search/?searchtype=author&query=Deng%2C+L">Liwei Deng</a>, <a href="/search/?searchtype=author&query=Zhang%2C+M">Meng Zhang</a>, <a href="/search/?searchtype=author&query=Li%2C+C">Chihao Li</a>, <a href="/search/?searchtype=author&query=Ding%2C+J">Jianyang Ding</a>, <a href="/search/?searchtype=author&query=Jiang%2C+Q">Qi Jiang</a>, <a href="/search/?searchtype=author&query=Ye%2C+M">Mao Ye</a>, <a href="/search/?searchtype=author&query=Liu%2C+Z">Zhengtai Liu</a>, <a href="/search/?searchtype=author&query=Jiang%2C+Z">Zhicheng Jiang</a>, <a href="/search/?searchtype=author&query=Wang%2C+S">Siyu Wang</a>, <a href="/search/?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/?searchtype=author&query=Xie%2C+Y">Yanwu Xie</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yilin Wang</a>, <a href="/search/?searchtype=author&query=Qiao%2C+S">Shan Qiao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jinsheng Wen</a>, <a href="/search/?searchtype=author&query=Sun%2C+Y">Yan Sun</a>, <a href="/search/?searchtype=author&query=Shen%2C+D">Dawei Shen</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="2409.13504v2-abstract-short" style="display: inline;"> Rutile RuO$_2$ has been posited as a potential $d$-wave altermagnetism candidate, with a predicted significant spin splitting up to 1.4 eV. Despite accumulating theoretical predictions and transport measurements, direct spectroscopic observation of spin splitting has remained elusive. Here, we employ spin- and angle-resolved photoemission spectroscopy to investigate the band structures and spin po… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13504v2-abstract-full').style.display = 'inline'; document.getElementById('2409.13504v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13504v2-abstract-full" style="display: none;"> Rutile RuO$_2$ has been posited as a potential $d$-wave altermagnetism candidate, with a predicted significant spin splitting up to 1.4 eV. Despite accumulating theoretical predictions and transport measurements, direct spectroscopic observation of spin splitting has remained elusive. Here, we employ spin- and angle-resolved photoemission spectroscopy to investigate the band structures and spin polarization of thin-film and single-crystal RuO$_2$. Contrary to expectations of altermagnetism, our analysis indicates that RuO$_2$'s electronic structure aligns with those predicted under non-magnetic conditions, exhibiting no evidence of the hypothesized spin splitting. Additionally, we observe significant in-plane spin polarization of the low-lying bulk bands, which is antisymmetric about the high-symmetry plane and contrary to the $d$-wave spin texture due to time-reversal symmetry breaking in altermagnetism. These findings definitively challenge the altermagnetic order previously proposed for rutile RuO$_2$, prompting a reevaluation of its magnetic properties. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13504v2-abstract-full').style.display = 'none'; document.getElementById('2409.13504v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">7 pages, 4 figures. Published in Physical Review Letters</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Phys. Rev. Lett. 133, 176401 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.12822">arXiv:2409.12822</a> <span> [<a href="https://arxiv.org/pdf/2409.12822">pdf</a>, <a href="https://arxiv.org/format/2409.12822">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"> Language Models Learn to Mislead Humans via RLHF </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiaxin Wen</a>, <a href="/search/?searchtype=author&query=Zhong%2C+R">Ruiqi Zhong</a>, <a href="/search/?searchtype=author&query=Khan%2C+A">Akbir Khan</a>, <a href="/search/?searchtype=author&query=Perez%2C+E">Ethan Perez</a>, <a href="/search/?searchtype=author&query=Steinhardt%2C+J">Jacob Steinhardt</a>, <a href="/search/?searchtype=author&query=Huang%2C+M">Minlie Huang</a>, <a href="/search/?searchtype=author&query=Bowman%2C+S+R">Samuel R. Bowman</a>, <a href="/search/?searchtype=author&query=He%2C+H">He He</a>, <a href="/search/?searchtype=author&query=Feng%2C+S">Shi 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="2409.12822v2-abstract-short" style="display: inline;"> Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wrong. We study this phenomenon under a standard RLHF pipeline, calling it "U-SOPHISTRY" since it is Uni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12822v2-abstract-full').style.display = 'inline'; document.getElementById('2409.12822v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12822v2-abstract-full" style="display: none;"> Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wrong. We study this phenomenon under a standard RLHF pipeline, calling it "U-SOPHISTRY" since it is Unintended by model developers. Specifically, we ask time-constrained (e.g., 3-10 minutes) human subjects to evaluate the correctness of model outputs and calculate humans' accuracy against gold labels. On a question-answering task (QuALITY) and programming task (APPS), RLHF makes LMs better at convincing our subjects but not at completing the task correctly. RLHF also makes the model harder to evaluate: our subjects' false positive rate increases by 24.1% on QuALITY and 18.3% on APPS. Finally, we show that probing, a state-of-the-art approach for detecting Intended Sophistry (e.g. backdoored LMs), does not generalize to U-SOPHISTRY. Our results highlight an important failure mode of RLHF and call for more research in assisting humans to align them. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12822v2-abstract-full').style.display = 'none'; document.getElementById('2409.12822v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.12514">arXiv:2409.12514</a> <span> [<a href="https://arxiv.org/pdf/2409.12514">pdf</a>, <a href="https://arxiv.org/format/2409.12514">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Junjie Wen</a>, <a href="/search/?searchtype=author&query=Zhu%2C+Y">Yichen Zhu</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jinming Li</a>, <a href="/search/?searchtype=author&query=Zhu%2C+M">Minjie Zhu</a>, <a href="/search/?searchtype=author&query=Wu%2C+K">Kun Wu</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhiyuan Xu</a>, <a href="/search/?searchtype=author&query=Liu%2C+N">Ning Liu</a>, <a href="/search/?searchtype=author&query=Cheng%2C+R">Ran Cheng</a>, <a href="/search/?searchtype=author&query=Shen%2C+C">Chaomin Shen</a>, <a href="/search/?searchtype=author&query=Peng%2C+Y">Yaxin Peng</a>, <a href="/search/?searchtype=author&query=Feng%2C+F">Feifei Feng</a>, <a href="/search/?searchtype=author&query=Tang%2C+J">Jian Tang</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="2409.12514v4-abstract-short" style="display: inline;"> Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12514v4-abstract-full').style.display = 'inline'; document.getElementById('2409.12514v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12514v4-abstract-full" style="display: none;"> Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that \methodname offers an interesting perspective on utilizing pre-trained multimodal models for policy learning. Our project is at https://tiny-vla.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12514v4-abstract-full').style.display = 'none'; document.getElementById('2409.12514v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">add more citations</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.12452">arXiv:2409.12452</a> <span> [<a href="https://arxiv.org/pdf/2409.12452">pdf</a>, <a href="https://arxiv.org/format/2409.12452">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"> Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiaxin Wen</a>, <a href="/search/?searchtype=author&query=Guan%2C+J">Jian Guan</a>, <a href="/search/?searchtype=author&query=Wang%2C+H">Hongning Wang</a>, <a href="/search/?searchtype=author&query=Wu%2C+W">Wei Wu</a>, <a href="/search/?searchtype=author&query=Huang%2C+M">Minlie 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="2409.12452v2-abstract-short" style="display: inline;"> Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on prompting or task-specific fine-tuning, often suffering from poor robustness and cross-task generalization. To address the limitation, we introduce Cod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12452v2-abstract-full').style.display = 'inline'; document.getElementById('2409.12452v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12452v2-abstract-full" style="display: none;"> Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on prompting or task-specific fine-tuning, often suffering from poor robustness and cross-task generalization. To address the limitation, we introduce CodePlan, a scalable framework that empowers LLMs to generate and follow \textit{code-form plans} -- pseudocode that outlines high-level, structured reasoning processes. By leveraging the structured and versatile nature of code, CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. Importantly, CodePlan allows automatic extraction of code-form plans from massive, wide-ranging text corpora without the need for curated, task-specific datasets. This enables it to scale up efficiently and improve LLM's reasoning capabilities across diverse scenarios. To train CodePlan, we construct a large-scale dataset of 2M examples that integrate code-form plans with standard prompt-response pairs from existing corpora. With minimal computation overhead during both training and inference, CodePlan achieves a 25.1\% relative improvement compared with directly generating responses, averaged across 13 challenging multi-step reasoning benchmarks, spanning mathematical reasoning, symbolic reasoning, instruction-following, multi-hop QA, and decision-making tasks. Further analysis reveals CodePlan's increasing performance gains on more complex reasoning tasks, as well as significant data efficiency thanks to its generalization ability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12452v2-abstract-full').style.display = 'none'; document.getElementById('2409.12452v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.11924">arXiv:2409.11924</a> <span> [<a href="https://arxiv.org/pdf/2409.11924">pdf</a>, <a href="https://arxiv.org/format/2409.11924">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optics">physics.optics</span> </div> </div> <p class="title is-5 mathjax"> Optical intensity-gradient torque due to chiral multipole interplay </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiquan Wen</a>, <a href="/search/?searchtype=author&query=Chen%2C+H">Huajin Chen</a>, <a href="/search/?searchtype=author&query=Zheng%2C+H">Hongxia Zheng</a>, <a href="/search/?searchtype=author&query=Xu%2C+X">Xiaohao Xu</a>, <a href="/search/?searchtype=author&query=Yan%2C+S">Shaohui Yan</a>, <a href="/search/?searchtype=author&query=Yao%2C+B">Baoli Yao</a>, <a href="/search/?searchtype=author&query=Lin%2C+Z">Zhifang Lin</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="2409.11924v1-abstract-short" style="display: inline;"> Owing to the ubiquity and easy-to-shape property of optical intensity, the intensity gradient force of light has been most spectacularly exploited in optical manipulation of small particles. Manifesting the intensity gradient as an optical torque to spin particles is of great fascination on both fundamental and practical sides but remains elusive. Here, we uncover the existence of the optical inte… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11924v1-abstract-full').style.display = 'inline'; document.getElementById('2409.11924v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.11924v1-abstract-full" style="display: none;"> Owing to the ubiquity and easy-to-shape property of optical intensity, the intensity gradient force of light has been most spectacularly exploited in optical manipulation of small particles. Manifesting the intensity gradient as an optical torque to spin particles is of great fascination on both fundamental and practical sides but remains elusive. Here, we uncover the existence of the optical intensity-gradient torque in the interaction of light with chiral particles. Such a new type of torque derives from the interplay between chirality induced multipoles, which switches its direction for particles with opposite chirality. We show that this torque can be directly detected by a simple standing wave field, created with the interference of two counterpropagating plane-like waves. Our work offers a unique route to achieve rotational control of matter by tailoring the field intensity of Maxwell waves. It also establishes a framework that maps a remarkable connection among the optical forces and torques, across chiral to nonchiral. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11924v1-abstract-full').style.display = 'none'; document.getElementById('2409.11924v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09751">arXiv:2409.09751</a> <span> [<a href="https://arxiv.org/pdf/2409.09751">pdf</a>, <a href="https://arxiv.org/format/2409.09751">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Solar and Stellar Astrophysics">astro-ph.SR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Astrophysics of Galaxies">astro-ph.GA</span> </div> </div> <p class="title is-5 mathjax"> Mass-loss Rate of Highly Evolved Stars in the Magellanic Clouds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jing Wen</a>, <a href="/search/?searchtype=author&query=Yang%2C+M">Ming Yang</a>, <a href="/search/?searchtype=author&query=Gao%2C+J">Jian Gao</a>, <a href="/search/?searchtype=author&query=Chen%2C+B">Bingqiu Chen</a>, <a href="/search/?searchtype=author&query=Ren%2C+Y">Yi Ren</a>, <a href="/search/?searchtype=author&query=Jiang%2C+B">Biwei Jiang</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="2409.09751v1-abstract-short" style="display: inline;"> Asymptotic giant branch stars (AGBs) and red supergiant stars (RSGs) exhibit significant mass loss phenomena and are considered important sources of interstellar dust. In this work, we employed an uniform method of spectral energy distribution fitting to analyze a large, and hence statistically significant, sample of approximately 40,000 RSGs and AGBs in the Magellanic Clouds (MCs), providing a ne… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09751v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09751v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09751v1-abstract-full" style="display: none;"> Asymptotic giant branch stars (AGBs) and red supergiant stars (RSGs) exhibit significant mass loss phenomena and are considered important sources of interstellar dust. In this work, we employed an uniform method of spectral energy distribution fitting to analyze a large, and hence statistically significant, sample of approximately 40,000 RSGs and AGBs in the Magellanic Clouds (MCs), providing a new catalog of evolved stars that includes stellar parameters and dust properties. Our results reveal that the total dust-production rate (DPR) of the Large Magellanic Cloud is approximately $9.69\times10^{-6}\,\rm{M_{\odot }\, yr^{-1}}$, while it is around $1.75\times10^{-6}\,\rm{M_{\odot }\,yr^{-1}}$ for the Small Magellanic Cloud, with a few stars significantly contributing to the total DPR. No significant differences were observed in the contributions to DPR from carbon-rich and oxygen-rich (O-rich) evolved stars in the MCs. We explored the relations between stellar parameters (luminosity, infrared color, period, amplitude) and mass-loss rate (MLR) for evolved stars. A prominent turning point at $\log{(L/L_{\odot})} \approx 4.4$ appears in the luminosity-MLR diagram of RSGs, potentially related to the mass-loss mechanism of RSGs. The luminosity-MLR relation of AGBs is highly scattered. The DPR of AGBs shows a clear change with pulsation period and amplitude, with DPR exhibiting a drastic increase at pulsation periods of approximately 300 days and I-band amplitudes greater than 0.5 mag. Metallicity has some impact on the DPR of O-rich stars, with lower metallicity seeming to result in lower mean DPR and a higher proportion of optically thin stars. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09751v1-abstract-full').style.display = 'none'; document.getElementById('2409.09751v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">30 pages,19 figures. Accepted for publication in ApJS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07931">arXiv:2409.07931</a> <span> [<a href="https://arxiv.org/pdf/2409.07931">pdf</a>, <a href="https://arxiv.org/format/2409.07931">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"> Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lu%2C+X">Xiaohuan Lu</a>, <a href="/search/?searchtype=author&query=Zhao%2C+L">Lian Zhao</a>, <a href="/search/?searchtype=author&query=Wong%2C+W+K">Wai Keung Wong</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jie Wen</a>, <a href="/search/?searchtype=author&query=Long%2C+J">Jiang Long</a>, <a href="/search/?searchtype=author&query=Xie%2C+W">Wulin Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.07931v1-abstract-short" style="display: inline;"> In real-world scenarios, multi-view multi-label learning often encounters the challenge of incomplete training data due to limitations in data collection and unreliable annotation processes. The absence of multi-view features impairs the comprehensive understanding of samples, omitting crucial details essential for classification. To address this issue, we present a task-augmented cross-view imput… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07931v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07931v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07931v1-abstract-full" style="display: none;"> In real-world scenarios, multi-view multi-label learning often encounters the challenge of incomplete training data due to limitations in data collection and unreliable annotation processes. The absence of multi-view features impairs the comprehensive understanding of samples, omitting crucial details essential for classification. To address this issue, we present a task-augmented cross-view imputation network (TACVI-Net) for the purpose of handling partial multi-view incomplete multi-label classification. Specifically, we employ a two-stage network to derive highly task-relevant features to recover the missing views. In the first stage, we leverage the information bottleneck theory to obtain a discriminative representation of each view by extracting task-relevant information through a view-specific encoder-classifier architecture. In the second stage, an autoencoder based multi-view reconstruction network is utilized to extract high-level semantic representation of the augmented features and recover the missing data, thereby aiding the final classification task. Extensive experiments on five datasets demonstrate that our TACVI-Net outperforms other state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07931v1-abstract-full').style.display = 'none'; document.getElementById('2409.07931v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07503">arXiv:2409.07503</a> <span> [<a href="https://arxiv.org/pdf/2409.07503">pdf</a>, <a href="https://arxiv.org/format/2409.07503">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="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"> AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lv%2C+L">Lijia Lv</a>, <a href="/search/?searchtype=author&query=Zhang%2C+W">Weigang Zhang</a>, <a href="/search/?searchtype=author&query=Tang%2C+X">Xuehai Tang</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jie Wen</a>, <a href="/search/?searchtype=author&query=Liu%2C+F">Feng Liu</a>, <a href="/search/?searchtype=author&query=Han%2C+J">Jizhong Han</a>, <a href="/search/?searchtype=author&query=Hu%2C+S">Songlin Hu</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="2409.07503v1-abstract-short" style="display: inline;"> Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community. However, traditional attack methods, which primarily focus on the semantic level, are easily detected by the model. These methods overlook the difference in the model… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07503v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07503v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07503v1-abstract-full" style="display: none;"> Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community. However, traditional attack methods, which primarily focus on the semantic level, are easily detected by the model. These methods overlook the difference in the model's alignment protection capabilities at different output stages. To address this issue, we propose an adaptive position pre-fill jailbreak attack approach for executing jailbreak attacks on LLMs. Our method leverages the model's instruction-following capabilities to first output pre-filled safe content, then exploits its narrative-shifting abilities to generate harmful content. Extensive black-box experiments demonstrate our method can improve the attack success rate by 47% on the widely recognized secure model (Llama2) compared to existing approaches. Our code can be found at: https://github.com/Yummy416/AdaPPA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07503v1-abstract-full').style.display = 'none'; document.getElementById('2409.07503v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05633">arXiv:2409.05633</a> <span> [<a href="https://arxiv.org/pdf/2409.05633">pdf</a>, <a href="https://arxiv.org/format/2409.05633">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"> Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zheng%2C+B">Bowen Zheng</a>, <a href="/search/?searchtype=author&query=Zhang%2C+J">Junjie Zhang</a>, <a href="/search/?searchtype=author&query=Lu%2C+H">Hongyu Lu</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yu Chen</a>, <a href="/search/?searchtype=author&query=Chen%2C+M">Ming Chen</a>, <a href="/search/?searchtype=author&query=Zhao%2C+W+X">Wayne Xin Zhao</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2409.05633v1-abstract-short" style="display: inline;"> Graph neural network (GNN) has been a powerful approach in collaborative filtering (CF) due to its ability to model high-order user-item relationships. Recently, to alleviate the data sparsity and enhance representation learning, many efforts have been conducted to integrate contrastive learning (CL) with GNNs. Despite the promising improvements, the contrastive view generation based on structure… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05633v1-abstract-full').style.display = 'inline'; document.getElementById('2409.05633v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05633v1-abstract-full" style="display: none;"> Graph neural network (GNN) has been a powerful approach in collaborative filtering (CF) due to its ability to model high-order user-item relationships. Recently, to alleviate the data sparsity and enhance representation learning, many efforts have been conducted to integrate contrastive learning (CL) with GNNs. Despite the promising improvements, the contrastive view generation based on structure and representation perturbations in existing methods potentially disrupts the collaborative information in contrastive views, resulting in limited effectiveness of positive alignment. To overcome this issue, we propose CoGCL, a novel framework that aims to enhance graph contrastive learning by constructing contrastive views with stronger collaborative information via discrete codes. The core idea is to map users and items into discrete codes rich in collaborative information for reliable and informative contrastive view generation. To this end, we initially introduce a multi-level vector quantizer in an end-to-end manner to quantize user and item representations into discrete codes. Based on these discrete codes, we enhance the collaborative information of contrastive views by considering neighborhood structure and semantic relevance respectively. For neighborhood structure, we propose virtual neighbor augmentation by treating discrete codes as virtual neighbors, which expands an observed user-item interaction into multiple edges involving discrete codes. Regarding semantic relevance, we identify similar users/items based on shared discrete codes and interaction targets to generate the semantically relevant view. Through these strategies, we construct contrastive views with stronger collaborative information and develop a triple-view graph contrastive learning approach. Extensive experiments on four public datasets demonstrate the effectiveness of our proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05633v1-abstract-full').style.display = 'none'; document.getElementById('2409.05633v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.04093">arXiv:2409.04093</a> <span> [<a href="https://arxiv.org/pdf/2409.04093">pdf</a>, <a href="https://arxiv.org/ps/2409.04093">ps</a>, <a href="https://arxiv.org/format/2409.04093">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Superconductivity">cond-mat.supr-con</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mesoscale and Nanoscale Physics">cond-mat.mes-hall</span> </div> </div> <p class="title is-5 mathjax"> Observation of superconducting diode effect in antiferromagnetic Mott insulator $伪$-RuCl$_3$ </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=He%2C+J">Jiadian He</a>, <a href="/search/?searchtype=author&query=Ding%2C+Y">Yifan Ding</a>, <a href="/search/?searchtype=author&query=Zeng%2C+X">Xiaohui Zeng</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yiwen Zhang</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yanjiang Wang</a>, <a href="/search/?searchtype=author&query=Dong%2C+P">Peng Dong</a>, <a href="/search/?searchtype=author&query=Zhou%2C+X">Xiang Zhou</a>, <a href="/search/?searchtype=author&query=Wu%2C+Y">Yueshen Wu</a>, <a href="/search/?searchtype=author&query=Cao%2C+K">Kecheng Cao</a>, <a href="/search/?searchtype=author&query=Ran%2C+K">Kejing Ran</a>, <a href="/search/?searchtype=author&query=Wang%2C+J">Jinghui Wang</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yulin Chen</a>, <a href="/search/?searchtype=author&query=Watanabe%2C+K">Kenji Watanabe</a>, <a href="/search/?searchtype=author&query=Taniguchi%2C+T">Takashi Taniguchi</a>, <a href="/search/?searchtype=author&query=Yu%2C+S">Shun-Li Yu</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jian-Xin Li</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jinsheng Wen</a>, <a href="/search/?searchtype=author&query=Li%2C+J">Jun 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="2409.04093v1-abstract-short" style="display: inline;"> Nonreciprocal superconductivity, also called as superconducting diode effect that spontaneously breaks time-reversal symmetry, is characterized by asymmetric critical currents under opposite applied current directions. This distinct state unveils a rich ore of intriguing physical properties, particularly in the realm of nanoscience application of superconductors. Towards the experimental realizati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04093v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04093v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04093v1-abstract-full" style="display: none;"> Nonreciprocal superconductivity, also called as superconducting diode effect that spontaneously breaks time-reversal symmetry, is characterized by asymmetric critical currents under opposite applied current directions. This distinct state unveils a rich ore of intriguing physical properties, particularly in the realm of nanoscience application of superconductors. Towards the experimental realization of superconducting diode effect, the construction of two-dimensional heterostructures of magnets and $s$-wave superconductors is considered to be a promising pathway. In this study, we present our findings of superconducting diode effect manifested in the magnetic Mott insulator $伪$-RuCl$_3$. This phenomenon is induced by the proximity effect within a van der Waals heterostructure, consisting of thin $伪$-RuCl$_3$/NbSe$_2$ flakes. Through transport property measurements, we have confirmed a weak superconducting gap of 0.2 meV, which is significantly lower than the intrinsic gap of NbSe$_2$(1.2 meV). Upon the application of a weak magnetic field below 70 mT, we observed an asymmetry in the critical currents under positive and negative applied currents. This observation demonstrates a typical superconducting diode effect in the superconducting $伪$-RuCl$_3$. The superconducting diode effect and nonreciprocal resistance are observed exclusively when the magnetic field is aligned out-of-plane. This suggests that an Ising-type spin-orbit coupling in the superconducting $伪$-RuCl$_3$ may be responsible for the mechanism. Our findings furnish a platform for the exploration of superconducting diode effect via the artificial construction of heterostructures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04093v1-abstract-full').style.display = 'none'; document.getElementById('2409.04093v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.02073">arXiv:2409.02073</a> <span> [<a href="https://arxiv.org/pdf/2409.02073">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mesoscale and Nanoscale Physics">cond-mat.mes-hall</span> </div> </div> <p class="title is-5 mathjax"> Revealing subterahertz atomic vibrations in quantum paraelectrics by surface-sensitive spintronic terahertz spectroscopy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Chu%2C+Z">Zhaodong Chu</a>, <a href="/search/?searchtype=author&query=Yang%2C+J">Junyi Yang</a>, <a href="/search/?searchtype=author&query=Li%2C+Y">Yan Li</a>, <a href="/search/?searchtype=author&query=Hwangbo%2C+K">Kyle Hwangbo</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jianguo Wen</a>, <a href="/search/?searchtype=author&query=Bielinski%2C+A+R">Ashley R. Bielinski</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a>, <a href="/search/?searchtype=author&query=Martinson%2C+A+B+F">Alex B. F. Martinson</a>, <a href="/search/?searchtype=author&query=Hruszkewycz%2C+S">Stephan Hruszkewycz</a>, <a href="/search/?searchtype=author&query=Fong%2C+D+D">Dillon D. Fong</a>, <a href="/search/?searchtype=author&query=Xu%2C+X">Xiaodong Xu</a>, <a href="/search/?searchtype=author&query=Norman%2C+M+R">Michael R. Norman</a>, <a href="/search/?searchtype=author&query=Bhattacharya%2C+A">Anand Bhattacharya</a>, <a href="/search/?searchtype=author&query=Wen%2C+H">Haidan Wen</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="2409.02073v2-abstract-short" style="display: inline;"> Understanding surface collective dynamics in quantum materials is crucial for advancing quantum technologies. For example, surface phonon modes in quantum paraelectrics are thought to play an essential role in facilitating interfacial superconductivity. However, detecting these modes, especially below 1 terahertz (THz), is challenging due to limited sampling volumes and the need for high spectrosc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02073v2-abstract-full').style.display = 'inline'; document.getElementById('2409.02073v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02073v2-abstract-full" style="display: none;"> Understanding surface collective dynamics in quantum materials is crucial for advancing quantum technologies. For example, surface phonon modes in quantum paraelectrics are thought to play an essential role in facilitating interfacial superconductivity. However, detecting these modes, especially below 1 terahertz (THz), is challenging due to limited sampling volumes and the need for high spectroscopic resolution. Here, we report surface soft transverse optical (TO1) phonon dynamics in KTaO3 and SrTiO3 by developing surface-sensitive spintronic THz spectroscopy that can sense the collective modes only a few nanometers deep from the surface. In KTaO3, the TO1 mode softens and sharpens with decreasing temperature, leveling off at 0.7 THz. In contrast, this mode in SrTiO3 broadens significantly below the quantum paraelectric crossover and coincides with the hardening of a sub-meV phonon mode related to the antiferrodistortive transition. These observations that deviate from their bulk properties may have implications for interfacial superconductivity and ferroelectricity. The developed technique opens opportunities for sensing low-energy surface excitations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02073v2-abstract-full').style.display = 'none'; document.getElementById('2409.02073v2-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">v1</span> submitted 3 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The main text consists of 24 pages and includes 4 figures. Supplementary Information is also provided. Science Advances accepted</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14600">arXiv:2408.14600</a> <span> [<a href="https://arxiv.org/pdf/2408.14600">pdf</a>, <a href="https://arxiv.org/format/2408.14600">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"> PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Li%2C+Y">Yidi Li</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Jiahao Wen</a>, <a href="/search/?searchtype=author&query=Ren%2C+B">Bin Ren</a>, <a href="/search/?searchtype=author&query=Li%2C+W">Wenhao Li</a>, <a href="/search/?searchtype=author&query=Xu%2C+Z">Zhenhuan Xu</a>, <a href="/search/?searchtype=author&query=Guo%2C+H">Hao Guo</a>, <a href="/search/?searchtype=author&query=Liu%2C+H">Hong Liu</a>, <a href="/search/?searchtype=author&query=Sebe%2C+N">Nicu Sebe</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="2408.14600v1-abstract-short" style="display: inline;"> The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying solely on point features within regions of interest can lead to information loss and limitations in local feature representation. To tackle these challenges, we propose a novel two… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14600v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14600v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14600v1-abstract-full" style="display: none;"> The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying solely on point features within regions of interest can lead to information loss and limitations in local feature representation. To tackle these challenges, we propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN). PVAFN leverages an attention mechanism to improve multi-modal feature fusion during the feature extraction phase. In the refinement stage, it utilizes a multi-pooling strategy to integrate both multi-scale and region-specific information effectively. The point-voxel attention mechanism adaptively combines point cloud and voxel-based Bird's-Eye-View (BEV) features, resulting in richer object representations that help to reduce false detections. Additionally, a multi-pooling enhancement module is introduced to boost the model's perception capabilities. This module employs cluster pooling and pyramid pooling techniques to efficiently capture key geometric details and fine-grained shape structures, thereby enhancing the integration of local and global features. Extensive experiments on the KITTI and Waymo datasets demonstrate that the proposed PVAFN achieves competitive performance. The code and models will be available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14600v1-abstract-full').style.display = 'none'; document.getElementById('2408.14600v1-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> 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">3D Object Detection</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14243">arXiv:2408.14243</a> <span> [<a href="https://arxiv.org/pdf/2408.14243">pdf</a>, <a href="https://arxiv.org/format/2408.14243">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="General Economics">econ.GN</span> </div> </div> <p class="title is-5 mathjax"> Insuring Long-Term Care in Developing Countries: The Interaction between Formal and Informal Insurance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jiayi Wen</a>, <a href="/search/?searchtype=author&query=Yu%2C+X">Xiaoqing 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="2408.14243v1-abstract-short" style="display: inline;"> Does public insurance reduce uninsured long-term care (LTC) risks in developing countries, where informal insurance predominates? This paper exploits the rollout of LTC insurance in China around 2016 to examine the impact of public LTC insurance on healthy workers' labor supply, a critical self-insurance channel. We find that workers eligible for public LTC insurance were less likely to engage in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14243v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14243v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14243v1-abstract-full" style="display: none;"> Does public insurance reduce uninsured long-term care (LTC) risks in developing countries, where informal insurance predominates? This paper exploits the rollout of LTC insurance in China around 2016 to examine the impact of public LTC insurance on healthy workers' labor supply, a critical self-insurance channel. We find that workers eligible for public LTC insurance were less likely to engage in labor work and worked fewer weeks annually following the policy change, suggesting a mitigation of uninsured risks. However, these impacts were insignificant among those with strong informal insurance coverage. Parallel changes in anticipated formal care use corroborate these findings. While our results reveal that public LTC insurance provides limited additional risk-sharing when informal insurance predominates, they also underscore its growing importance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14243v1-abstract-full').style.display = 'none'; document.getElementById('2408.14243v1-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> 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.08209">arXiv:2408.08209</a> <span> [<a href="https://arxiv.org/pdf/2408.08209">pdf</a>, <a href="https://arxiv.org/format/2408.08209">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"> Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+C">Changshuo Zhang</a>, <a href="/search/?searchtype=author&query=Shi%2C+T">Teng Shi</a>, <a href="/search/?searchtype=author&query=Zhang%2C+X">Xiao Zhang</a>, <a href="/search/?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/?searchtype=author&query=Xie%2C+R">Ruobing Xie</a>, <a href="/search/?searchtype=author&query=Xu%2C+J">Jun Xu</a>, <a href="/search/?searchtype=author&query=Wen%2C+J">Ji-Rong Wen</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="2408.08209v1-abstract-short" style="display: inline;"> Nowadays, many recommender systems encompass various domains to cater to users' diverse needs, leading to user behaviors transitioning across different domains. In fact, user behaviors across different domains reveal changes in preference toward recommended items. For instance, a shift from negative feedback to positive feedback indicates improved user satisfaction. However, existing cross-domain… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08209v1-abstract-full').style.display = 'inline'; document.getElementById('2408.08209v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08209v1-abstract-full" style="display: none;"> Nowadays, many recommender systems encompass various domains to cater to users' diverse needs, leading to user behaviors transitioning across different domains. In fact, user behaviors across different domains reveal changes in preference toward recommended items. For instance, a shift from negative feedback to positive feedback indicates improved user satisfaction. However, existing cross-domain sequential recommendation methods typically model user interests by focusing solely on information about domain transitions, often overlooking the valuable insights provided by users' feedback transitions. In this paper, we propose $\text{Transition}^2$, a novel method to model transitions across both domains and types of user feedback. Specifically, $\text{Transition}^2$ introduces a transition-aware graph encoder based on user history, assigning different weights to edges according to the feedback type. This enables the graph encoder to extract historical embeddings that capture the transition information between different domains and feedback types. Subsequently, we encode the user history using a cross-transition multi-head self-attention, incorporating various masks to distinguish different types of transitions. Finally, we integrate these modules to make predictions across different domains. Experimental results on two public datasets demonstrate the effectiveness of $\text{Transition}^2$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08209v1-abstract-full').style.display = 'none'; document.getElementById('2408.08209v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.04677">arXiv:2408.04677</a> <span> [<a href="https://arxiv.org/pdf/2408.04677">pdf</a>, <a href="https://arxiv.org/format/2408.04677">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Open-Source Software Architecture for Multi-Robot Wire Arc Additive Manufacturing (WAAM) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=He%2C+H">Honglu He</a>, <a href="/search/?searchtype=author&query=Lu%2C+C">Chen-lung Lu</a>, <a href="/search/?searchtype=author&query=Ren%2C+J">Jinhan Ren</a>, <a href="/search/?searchtype=author&query=Dhar%2C+J">Joni Dhar</a>, <a href="/search/?searchtype=author&query=Saunders%2C+G">Glenn Saunders</a>, <a href="/search/?searchtype=author&query=Wason%2C+J">John Wason</a>, <a href="/search/?searchtype=author&query=Samuel%2C+J">Johnson Samuel</a>, <a href="/search/?searchtype=author&query=Julius%2C+A">Agung Julius</a>, <a href="/search/?searchtype=author&query=Wen%2C+J+T">John T. Wen</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="2408.04677v1-abstract-short" style="display: inline;"> Wire Arc Additive Manufacturing (WAAM) is a metal 3D printing technology that deposits molten metal wire on a substrate to form desired geometries. Articulated robot arms are commonly used in WAAM to produce complex geometric shapes. However, they mostly rely on proprietary robot and weld control software that limits process tuning and customization, incorporation of third-party sensors, implement… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04677v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04677v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04677v1-abstract-full" style="display: none;"> Wire Arc Additive Manufacturing (WAAM) is a metal 3D printing technology that deposits molten metal wire on a substrate to form desired geometries. Articulated robot arms are commonly used in WAAM to produce complex geometric shapes. However, they mostly rely on proprietary robot and weld control software that limits process tuning and customization, incorporation of third-party sensors, implementation on robots and weld controllers from multiple vendors, and customizable user programming. This paper presents a general open-source software architecture for WAAM that addresses these limitations. The foundation of this architecture is Robot Raconteur, an open-source control and communication framework that serves as the middleware for integrating robots and sensors from different vendors. Based on this architecture, we developed an end-to-end robotic WAAM implementation that takes a CAD file to a printed WAAM part and evaluates the accuracy of the result. The major components in the architecture include part slicing, robot motion planning, part metrology, in-process sensing, and process tuning. The current implementation is based on Motoman robots and Fronius weld controller, but the approach is applicable to other industrial robots and weld controllers. The capability of the WAAM tested is demonstrated through the printing of parts of various geometries and acquisition of in-process sensor data for motion adjustment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04677v1-abstract-full').style.display = 'none'; document.getElementById('2408.04677v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01173">arXiv:2408.01173</a> <span> [<a href="https://arxiv.org/pdf/2408.01173">pdf</a>, <a href="https://arxiv.org/format/2408.01173">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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"> Sustainable Diffusion-based Incentive Mechanism for Generative AI-driven Digital Twins in Industrial Cyber-Physical Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wen%2C+J">Jinbo Wen</a>, <a href="/search/?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/?searchtype=author&query=Mao%2C+S">Shiwen Mao</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="2408.01173v1-abstract-short" style="display: inline;"> Industrial Cyber-Physical Systems (ICPSs) are an integral component of modern manufacturing and industries. By digitizing data throughout the product life cycle, Digital Twins (DTs) in ICPSs enable a shift from current industrial infrastructures to intelligent and adaptive infrastructures. Thanks to data process capability, Generative Artificial Intelligence (GAI) can drive the construction and up… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01173v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01173v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01173v1-abstract-full" style="display: none;"> Industrial Cyber-Physical Systems (ICPSs) are an integral component of modern manufacturing and industries. By digitizing data throughout the product life cycle, Digital Twins (DTs) in ICPSs enable a shift from current industrial infrastructures to intelligent and adaptive infrastructures. Thanks to data process capability, Generative Artificial Intelligence (GAI) can drive the construction and update of DTs to improve predictive accuracy and prepare for diverse smart manufacturing. However, mechanisms that leverage sensing Industrial Internet of Things (IIoT) devices to share data for the construction of DTs are susceptible to adverse selection problems. In this paper, we first develop a GAI-driven DT architecture for ICPSs. To address the adverse selection problem caused by information asymmetry, we propose a contract theory model and develop the sustainable diffusion-based soft actor-critic algorithm to identify the optimal feasible contract. Specifically, we leverage the dynamic structured pruning technique to reduce parameter numbers of actor networks, allowing sustainability and efficient implementation of the proposed algorithm. Finally, numerical results demonstrate the effectiveness of the proposed scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01173v1-abstract-full').style.display = 'none'; document.getElementById('2408.01173v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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=Wen%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Wen%2C+J&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