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 453 results for author: <span class="mathjax">Chang, C</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Chang%2C+C">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Chang, C"> </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=Chang%2C+C&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="Chang, C"> <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=Chang%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&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/2411.15425">arXiv:2411.15425</a> <span> [<a href="https://arxiv.org/pdf/2411.15425">pdf</a>, <a href="https://arxiv.org/format/2411.15425">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sie%2C+M">Ming-Fong Sie</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+Y">Yen-Jui Chang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chien-Lung Lin</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching-Ray Chang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+S">Shih-Wei Liao</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="2411.15425v1-abstract-short" style="display: inline;"> Over 900 million Bitcoin transactions have been recorded, posing considerable challenges for machine learning in terms of computation time and maintaining prediction accuracy. We propose an innovative approach using quantum-inspired algorithms implemented with Simulated Annealing and Quantum Annealing to address the challenge of local minima in solution spaces. This method efficiently identifies k… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15425v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15425v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15425v1-abstract-full" style="display: none;"> Over 900 million Bitcoin transactions have been recorded, posing considerable challenges for machine learning in terms of computation time and maintaining prediction accuracy. We propose an innovative approach using quantum-inspired algorithms implemented with Simulated Annealing and Quantum Annealing to address the challenge of local minima in solution spaces. This method efficiently identifies key features linked to mixer addresses, significantly reducing model training time. By categorizing Bitcoin addresses into six classes: exchanges, faucets, gambling, marketplaces, mixers, and mining pools, and applying supervised learning methods, our results demonstrate that feature selection with SA reduced training time by 30.3% compared to using all features in a random forest model while maintaining a 91% F1-score for mixer addresses. This highlights the potential of quantum-inspired algorithms to swiftly and accurately identify high-risk Bitcoin addresses based on transaction features. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15425v1-abstract-full').style.display = 'none'; document.getElementById('2411.15425v1-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">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">19 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14296">arXiv:2411.14296</a> <span> [<a href="https://arxiv.org/pdf/2411.14296">pdf</a>, <a href="https://arxiv.org/format/2411.14296">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Improving Routability Prediction via NAS Using a Smooth One-shot Augmented Predictor </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sridhar%2C+A">Arjun Sridhar</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Chia Chang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Junyao Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yiran 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="2411.14296v1-abstract-short" style="display: inline;"> Routability optimization in modern EDA tools has benefited greatly from using machine learning (ML) models. Constructing and optimizing the performance of ML models continues to be a challenge. Neural Architecture Search (NAS) serves as a tool to aid in the construction and improvement of these models. Traditional NAS techniques struggle to perform well on routability prediction as a result of two… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14296v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14296v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14296v1-abstract-full" style="display: none;"> Routability optimization in modern EDA tools has benefited greatly from using machine learning (ML) models. Constructing and optimizing the performance of ML models continues to be a challenge. Neural Architecture Search (NAS) serves as a tool to aid in the construction and improvement of these models. Traditional NAS techniques struggle to perform well on routability prediction as a result of two primary factors. First, the separation between the training objective and the search objective adds noise to the NAS process. Secondly, the increased variance of the search objective further complicates performing NAS. We craft a novel NAS technique, coined SOAP-NAS, to address these challenges through novel data augmentation techniques and a novel combination of one-shot and predictor-based NAS. Results show that our technique outperforms existing solutions by 40% closer to the ideal performance measured by ROC-AUC (area under the receiver operating characteristic curve) in DRC hotspot detection. SOAPNet is able to achieve an ROC-AUC of 0.9802 and a query time of only 0.461 ms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14296v1-abstract-full').style.display = 'none'; document.getElementById('2411.14296v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14199">arXiv:2411.14199</a> <span> [<a href="https://arxiv.org/pdf/2411.14199">pdf</a>, <a href="https://arxiv.org/format/2411.14199">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="Digital Libraries">cs.DL</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"> OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Asai%2C+A">Akari Asai</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jacqueline He</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+R">Rulin Shao</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+W">Weijia Shi</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Amanpreet Singh</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+K">Kyle Lo</a>, <a href="/search/cs?searchtype=author&query=Soldaini%2C+L">Luca Soldaini</a>, <a href="/search/cs?searchtype=author&query=Feldman%2C+S">Sergey Feldman</a>, <a href="/search/cs?searchtype=author&query=D%27arcy%2C+M">Mike D'arcy</a>, <a href="/search/cs?searchtype=author&query=Wadden%2C+D">David Wadden</a>, <a href="/search/cs?searchtype=author&query=Latzke%2C+M">Matt Latzke</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+M">Minyang Tian</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+P">Pan Ji</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shengyan Liu</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+H">Hao Tong</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+B">Bohao Wu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Y">Yanyu Xiong</a>, <a href="/search/cs?searchtype=author&query=Zettlemoyer%2C+L">Luke Zettlemoyer</a>, <a href="/search/cs?searchtype=author&query=Neubig%2C+G">Graham Neubig</a>, <a href="/search/cs?searchtype=author&query=Weld%2C+D">Dan Weld</a>, <a href="/search/cs?searchtype=author&query=Downey%2C+D">Doug Downey</a>, <a href="/search/cs?searchtype=author&query=Yih%2C+W">Wen-tau Yih</a>, <a href="/search/cs?searchtype=author&query=Koh%2C+P+W">Pang Wei Koh</a>, <a href="/search/cs?searchtype=author&query=Hajishirzi%2C+H">Hannaneh Hajishirzi</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="2411.14199v1-abstract-short" style="display: inline;"> Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we dev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14199v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14199v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14199v1-abstract-full" style="display: none;"> Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscience, and biomedicine. On ScholarQABench, OpenScholar-8B outperforms GPT-4o by 5% and PaperQA2 by 7% in correctness, despite being a smaller, open model. While GPT4o hallucinates citations 78 to 90% of the time, OpenScholar achieves citation accuracy on par with human experts. OpenScholar's datastore, retriever, and self-feedback inference loop also improves off-the-shelf LMs: for instance, OpenScholar-GPT4o improves GPT-4o's correctness by 12%. In human evaluations, experts preferred OpenScholar-8B and OpenScholar-GPT4o responses over expert-written ones 51% and 70% of the time, respectively, compared to GPT4o's 32%. We open-source all of our code, models, datastore, data and a public demo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14199v1-abstract-full').style.display = 'none'; document.getElementById('2411.14199v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13560">arXiv:2411.13560</a> <span> [<a href="https://arxiv.org/pdf/2411.13560">pdf</a>, <a href="https://arxiv.org/format/2411.13560">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="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yichen Shi</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhuofu Tao</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yuhao Gao</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+T">Tianjia Zhou</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Cheng Chang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yaxing Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+B">Bingyu Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+G">Genhao Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Alvin Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiping Yu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+T">Ting-Jung Lin</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Lei He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13560v1-abstract-short" style="display: inline;"> High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13560v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13560v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13560v1-abstract-full" style="display: none;"> High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements in the automatic design process for large-scale AMS circuits. However, the absence of high-quality datasets has led to issues such as model hallucination, which undermines the robustness of automatically generated circuit designs. To address this issue, this paper introduces AMSnet-KG, a dataset encompassing various AMS circuit schematics and netlists. We construct a knowledge graph with annotations on detailed functional and performance characteristics. Facilitated by AMSnet-KG, we propose an automated AMS circuit generation framework that utilizes the comprehensive knowledge embedded in LLMs. We first formulate a design strategy (e.g., circuit architecture using a number of circuit components) based on required specifications. Next, matched circuit components are retrieved and assembled into a complete topology, and transistor sizing is obtained through Bayesian optimization. Simulation results of the netlist are fed back to the LLM for further topology refinement, ensuring the circuit design specifications are met. We perform case studies of operational amplifier and comparator design to verify the automatic design flow from specifications to netlists with minimal human effort. The dataset used in this paper will be open-sourced upon publishing of this paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13560v1-abstract-full').style.display = 'none'; document.getElementById('2411.13560v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07890">arXiv:2411.07890</a> <span> [<a href="https://arxiv.org/pdf/2411.07890">pdf</a>, <a href="https://arxiv.org/format/2411.07890">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"> Minimally Invasive Flexible Needle Manipulation Based on Finite Element Simulation and Cross Entropy Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanzhou Wang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chang Chang</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+J">Junling Mei</a>, <a href="/search/cs?searchtype=author&query=Leonard%2C+S">Simon Leonard</a>, <a href="/search/cs?searchtype=author&query=Iordachita%2C+I">Iulian Iordachita</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="2411.07890v1-abstract-short" style="display: inline;"> We present a novel approach for minimally invasive flexible needle manipulations by pairing a real-time finite element simulator with the cross-entropy method. Additionally, we demonstrate how a kinematic-driven bang-bang controller can complement the control framework for better tracking performance. We show how electromagnetic (EM) tracking can be readily incorporated into the framework to provi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07890v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07890v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07890v1-abstract-full" style="display: none;"> We present a novel approach for minimally invasive flexible needle manipulations by pairing a real-time finite element simulator with the cross-entropy method. Additionally, we demonstrate how a kinematic-driven bang-bang controller can complement the control framework for better tracking performance. We show how electromagnetic (EM) tracking can be readily incorporated into the framework to provide controller feedback. Tissue phantom experiment with EM tracking shows the average targeting error is $0.16 \pm 0.29mm$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07890v1-abstract-full').style.display = 'none'; document.getElementById('2411.07890v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE International Conference on Robotics and Automation 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07820">arXiv:2411.07820</a> <span> [<a href="https://arxiv.org/pdf/2411.07820">pdf</a>, <a href="https://arxiv.org/format/2411.07820">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cong%2C+Y">Youan Cong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Cheng Wang</a>, <a href="/search/cs?searchtype=author&query=Akash%2C+P+S">Pritom Saha Akash</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K+C">Kevin Chen-Chuan Chang</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="2411.07820v2-abstract-short" style="display: inline;"> We introduce the Extract-Refine-Retrieve-Read (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the specific knowledge requirements of Large Language Models (LLMs). Unlike conventional query optimization techniques used in RAG, the ERRR framework begins by extracting pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07820v2-abstract-full').style.display = 'inline'; document.getElementById('2411.07820v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07820v2-abstract-full" style="display: none;"> We introduce the Extract-Refine-Retrieve-Read (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the specific knowledge requirements of Large Language Models (LLMs). Unlike conventional query optimization techniques used in RAG, the ERRR framework begins by extracting parametric knowledge from LLMs, followed by using a specialized query optimizer for refining these queries. This process ensures the retrieval of only the most pertinent information essential for generating accurate responses. Moreover, to enhance flexibility and reduce computational costs, we propose a trainable scheme for our pipeline that utilizes a smaller, tunable model as the query optimizer, which is refined through knowledge distillation from a larger teacher model. Our evaluations on various question-answering (QA) datasets and with different retrieval systems show that ERRR consistently outperforms existing baselines, proving to be a versatile and cost-effective module for improving the utility and accuracy of RAG systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07820v2-abstract-full').style.display = 'none'; document.getElementById('2411.07820v2-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">v1</span> submitted 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07237">arXiv:2411.07237</a> <span> [<a href="https://arxiv.org/pdf/2411.07237">pdf</a>, <a href="https://arxiv.org/format/2411.07237">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"> Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Malaviya%2C+C">Chaitanya Malaviya</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+D">Dan Roth</a>, <a href="/search/cs?searchtype=author&query=Iyyer%2C+M">Mohit Iyyer</a>, <a href="/search/cs?searchtype=author&query=Yatskar%2C+M">Mark Yatskar</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+K">Kyle Lo</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="2411.07237v1-abstract-short" style="display: inline;"> Language model users often issue queries that lack specification, where the context under which a query was issued -- such as the user's identity, the query's intent, and the criteria for a response to be useful -- is not explicit. For instance, a good response to a subjective query like "What book should I read next?" would depend on the user's preferences, and a good response to an open-ended qu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07237v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07237v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07237v1-abstract-full" style="display: none;"> Language model users often issue queries that lack specification, where the context under which a query was issued -- such as the user's identity, the query's intent, and the criteria for a response to be useful -- is not explicit. For instance, a good response to a subjective query like "What book should I read next?" would depend on the user's preferences, and a good response to an open-ended query like "How do antibiotics work against bacteria?" would depend on the user's expertise. This makes evaluation of responses to such queries an ill-posed task, as evaluators may make arbitrary judgments about the response quality. To remedy this, we present contextualized evaluations, a protocol that synthetically constructs context surrounding an underspecified query and provides it during evaluation. We find that the presence of context can 1) alter conclusions drawn from evaluation, even flipping win rates between model pairs, 2) nudge evaluators to make fewer judgments based on surface-level criteria, like style, and 3) provide new insights about model behavior across diverse contexts. Specifically, our procedure uncovers an implicit bias towards WEIRD contexts in models' "default" responses and we find that models are not equally sensitive to following different contexts, even when they are provided in prompts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07237v1-abstract-full').style.display = 'none'; document.getElementById('2411.07237v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Code & data available at https://github.com/allenai/ContextEval</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06559">arXiv:2411.06559</a> <span> [<a href="https://arxiv.org/pdf/2411.06559">pdf</a>, <a href="https://arxiv.org/format/2411.06559">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"> Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yu Gu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+B">Boyuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Gou%2C+B">Boyu Gou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Cheng Chang</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Sanjari Srivastava</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Yanan Xie</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+P">Peng Qi</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Huan Sun</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Y">Yu Su</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="2411.06559v1-abstract-short" style="display: inline;"> Language agents have demonstrated promising capabilities in automating web-based tasks, though their current reactive approaches still underperform largely compared to humans. While incorporating advanced planning algorithms, particularly tree search methods, could enhance these agents' performance, implementing tree search directly on live websites poses significant safety risks and practical con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06559v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06559v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06559v1-abstract-full" style="display: none;"> Language agents have demonstrated promising capabilities in automating web-based tasks, though their current reactive approaches still underperform largely compared to humans. While incorporating advanced planning algorithms, particularly tree search methods, could enhance these agents' performance, implementing tree search directly on live websites poses significant safety risks and practical constraints due to irreversible actions such as confirming a purchase. In this paper, we introduce a novel paradigm that augments language agents with model-based planning, pioneering the innovative use of large language models (LLMs) as world models in complex web environments. Our method, WebDreamer, builds on the key insight that LLMs inherently encode comprehensive knowledge about website structures and functionalities. Specifically, WebDreamer uses LLMs to simulate outcomes for each candidate action (e.g., "what would happen if I click this button?") using natural language descriptions, and then evaluates these imagined outcomes to determine the optimal action at each step. Empirical results on two representative web agent benchmarks with online interaction -- VisualWebArena and Mind2Web-live -- demonstrate that WebDreamer achieves substantial improvements over reactive baselines. By establishing the viability of LLMs as world models in web environments, this work lays the groundwork for a paradigm shift in automated web interaction. More broadly, our findings open exciting new avenues for future research into 1) optimizing LLMs specifically for world modeling in complex, dynamic environments, and 2) model-based speculative planning for language agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06559v1-abstract-full').style.display = 'none'; document.getElementById('2411.06559v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 6 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06055">arXiv:2411.06055</a> <span> [<a href="https://arxiv.org/pdf/2411.06055">pdf</a>, <a href="https://arxiv.org/format/2411.06055">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Metric Geometry">math.MG</span> </div> </div> <p class="title is-5 mathjax"> Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinran Liu</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+Y">Yikun Bai</a>, <a href="/search/cs?searchtype=author&query=Mart%C3%ADn%2C+R+D">Roc铆o D铆az Mart铆n</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+K">Kaiwen Shi</a>, <a href="/search/cs?searchtype=author&query=Shahbazi%2C+A">Ashkan Shahbazi</a>, <a href="/search/cs?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/cs?searchtype=author&query=Kolouri%2C+S">Soheil Kolouri</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="2411.06055v1-abstract-short" style="display: inline;"> Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such as spherical and stereographic spherical sliced Wasserstein distances, have recently been developed to address this need. These methods reduce the computational burden of optimal transport by slicing hyperspheres into o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06055v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06055v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06055v1-abstract-full" style="display: none;"> Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such as spherical and stereographic spherical sliced Wasserstein distances, have recently been developed to address this need. These methods reduce the computational burden of optimal transport by slicing hyperspheres into one-dimensional projections, i.e., lines or circles. Concurrently, linear optimal transport has been proposed to embed distributions into $ L^2 $ spaces, where the $ L^2 $ distance approximates the optimal transport distance, thereby simplifying comparisons across multiple distributions. In this work, we introduce the Linear Spherical Sliced Optimal Transport (LSSOT) framework, which utilizes slicing to embed spherical distributions into $ L^2 $ spaces while preserving their intrinsic geometry, offering a computationally efficient metric for spherical probability measures. We establish the metricity of LSSOT and demonstrate its superior computational efficiency in applications such as cortical surface registration, 3D point cloud interpolation via gradient flow, and shape embedding. Our results demonstrate the significant computational benefits and high accuracy of LSSOT in these applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06055v1-abstract-full').style.display = 'none'; document.getElementById('2411.06055v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05025">arXiv:2411.05025</a> <span> [<a href="https://arxiv.org/pdf/2411.05025">pdf</a>, <a href="https://arxiv.org/format/2411.05025">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="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liao%2C+Z">Zhehui Liao</a>, <a href="/search/cs?searchtype=author&query=Antoniak%2C+M">Maria Antoniak</a>, <a href="/search/cs?searchtype=author&query=Cheong%2C+I">Inyoung Cheong</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+E+Y">Evie Yu-Yen Cheng</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+A">Ai-Heng Lee</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+K">Kyle Lo</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A+X">Amy X. 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="2411.05025v1-abstract-short" style="display: inline;"> The rise of large language models (LLMs) has led many researchers to consider their usage for scientific work. Some have found benefits using LLMs to augment or automate aspects of their research pipeline, while others have urged caution due to risks and ethical concerns. Yet little work has sought to quantify and characterize how researchers use LLMs and why. We present the first large-scale surv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05025v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05025v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05025v1-abstract-full" style="display: none;"> The rise of large language models (LLMs) has led many researchers to consider their usage for scientific work. Some have found benefits using LLMs to augment or automate aspects of their research pipeline, while others have urged caution due to risks and ethical concerns. Yet little work has sought to quantify and characterize how researchers use LLMs and why. We present the first large-scale survey of 816 verified research article authors to understand how the research community leverages and perceives LLMs as research tools. We examine participants' self-reported LLM usage, finding that 81% of researchers have already incorporated LLMs into different aspects of their research workflow. We also find that traditionally disadvantaged groups in academia (non-White, junior, and non-native English speaking researchers) report higher LLM usage and perceived benefits, suggesting potential for improved research equity. However, women, non-binary, and senior researchers have greater ethical concerns, potentially hindering adoption. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05025v1-abstract-full').style.display = 'none'; document.getElementById('2411.05025v1-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> 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">30 pages, 5 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/2411.02353">arXiv:2411.02353</a> <span> [<a href="https://arxiv.org/pdf/2411.02353">pdf</a>, <a href="https://arxiv.org/format/2411.02353">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Social-RAG: Retrieving from Group Interactions to Socially Ground Proactive AI Generation to Group Preferences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruotong Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xinyi Zhou</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+L">Lin Qiu</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Bragg%2C+J">Jonathan Bragg</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A+X">Amy X. 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="2411.02353v1-abstract-short" style="display: inline;"> AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, but can be unhelpful or even annoying, due to not fitting the group's preferences or behaving in socially inappropriate ways. Fortunately, group spaces have a rich history of prior social interactions and affordances for social feedback to support creating agents that align to a group's i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02353v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02353v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02353v1-abstract-full" style="display: none;"> AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, but can be unhelpful or even annoying, due to not fitting the group's preferences or behaving in socially inappropriate ways. Fortunately, group spaces have a rich history of prior social interactions and affordances for social feedback to support creating agents that align to a group's interests and norms. We present Social-RAG, a workflow for grounding agents to social information about a group, which retrieves from prior group interactions, selects relevant social signals, and then feeds the context into a large language model to generate messages to the group. We implement this into PaperPing, our system that posts academic paper recommendations in group chat, leveraging social signals determined from formative studies with 39 researchers. From a three-month deployment in 18 channels, we observed PaperPing posted relevant messages in groups without disrupting their existing social practices, fostering group common ground. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02353v1-abstract-full').style.display = 'none'; document.getElementById('2411.02353v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00929">arXiv:2411.00929</a> <span> [<a href="https://arxiv.org/pdf/2411.00929">pdf</a>, <a href="https://arxiv.org/format/2411.00929">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Text2Freq: Learning Series Patterns from Text via Frequency Domain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lo%2C+M">Ming-Chih Lo</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching Chang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+W">Wen-Chih Peng</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="2411.00929v1-abstract-short" style="display: inline;"> Traditional time series forecasting models mainly rely on historical numeric values to predict future outcomes.While these models have shown promising results, they often overlook the rich information available in other modalities, such as textual descriptions of special events, which can provide crucial insights into future dynamics.However, research that jointly incorporates text in time series… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00929v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00929v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00929v1-abstract-full" style="display: none;"> Traditional time series forecasting models mainly rely on historical numeric values to predict future outcomes.While these models have shown promising results, they often overlook the rich information available in other modalities, such as textual descriptions of special events, which can provide crucial insights into future dynamics.However, research that jointly incorporates text in time series forecasting remains relatively underexplored compared to other cross-modality work. Additionally, the modality gap between time series data and textual information poses a challenge for multimodal learning. To address this task, we propose Text2Freq, a cross-modality model that integrates text and time series data via the frequency domain. Specifically, our approach aligns textual information to the low-frequency components of time series data, establishing more effective and interpretable alignments between these two modalities. Our experiments on paired datasets of real-world stock prices and synthetic texts show that Text2Freq achieves state-of-the-art performance, with its adaptable architecture encouraging future research in this field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00929v1-abstract-full').style.display = 'none'; document.getElementById('2411.00929v1-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">7 pages, 3 figures, and be accepted by NeurIPS 2024 Workshop: Time Series in the Age of Large Models</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00078">arXiv:2411.00078</a> <span> [<a href="https://arxiv.org/pdf/2411.00078">pdf</a>, <a href="https://arxiv.org/format/2411.00078">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/cs?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/cs?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00078v1-abstract-short" style="display: inline;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei seg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00078v1-abstract-full" style="display: none;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei segmentation within a single organ (e.g., the kidney), remains uncertain. This paper seeks to answer this key question, "How good are we?", by thoroughly evaluating the performance of recent cell foundation models on a curated multi-center, multi-disease, and multi-species external testing dataset. Additionally, we tackle a more challenging question, "How can we improve?", by developing and assessing human-in-the-loop data enrichment strategies aimed at enhancing model performance while minimizing the reliance on pixel-level human annotation. To address the first question, we curated a multicenter, multidisease, and multispecies dataset consisting of 2,542 kidney whole slide images (WSIs). Three state-of-the-art (SOTA) cell foundation models-Cellpose, StarDist, and CellViT-were selected for evaluation. To tackle the second question, we explored data enrichment algorithms by distilling predictions from the different foundation models with a human-in-the-loop framework, aiming to further enhance foundation model performance with minimal human efforts. Our experimental results showed that all three foundation models improved over their baselines with model fine-tuning with enriched data. Interestingly, the baseline model with the highest F1 score does not yield the best segmentation outcomes after fine-tuning. This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'none'; document.getElementById('2411.00078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22360">arXiv:2410.22360</a> <span> [<a href="https://arxiv.org/pdf/2410.22360">pdf</a>, <a href="https://arxiv.org/format/2410.22360">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"> ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Newman%2C+B">Benjamin Newman</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+Y">Yoonjoo Lee</a>, <a href="/search/cs?searchtype=author&query=Naik%2C+A">Aakanksha Naik</a>, <a href="/search/cs?searchtype=author&query=Siangliulue%2C+P">Pao Siangliulue</a>, <a href="/search/cs?searchtype=author&query=Fok%2C+R">Raymond Fok</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Juho Kim</a>, <a href="/search/cs?searchtype=author&query=Weld%2C+D+S">Daniel S. Weld</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Lo%2C+K">Kyle Lo</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="2410.22360v1-abstract-short" style="display: inline;"> When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate these tables using language models (LMs)? In this work, we introduce a framework that leverages LMs to perform this task by decomposing it into separat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22360v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22360v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22360v1-abstract-full" style="display: none;"> When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate these tables using language models (LMs)? In this work, we introduce a framework that leverages LMs to perform this task by decomposing it into separate schema and value generation steps. To enable experimentation, we address two main challenges: First, we overcome a lack of high-quality datasets to benchmark table generation by curating and releasing arxivDIGESTables, a new dataset of 2,228 literature review tables extracted from ArXiv papers that synthesize a total of 7,542 research papers. Second, to support scalable evaluation of model generations against human-authored reference tables, we develop DecontextEval, an automatic evaluation method that aligns elements of tables with the same underlying aspects despite differing surface forms. Given these tools, we evaluate LMs' abilities to reconstruct reference tables, finding this task benefits from additional context to ground the generation (e.g. table captions, in-text references). Finally, through a human evaluation study we find that even when LMs fail to fully reconstruct a reference table, their generated novel aspects can still be useful. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22360v1-abstract-full').style.display = 'none'; document.getElementById('2410.22360v1-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 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">EMNLP 2024, 21 pages, 8 figures, 10 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21991">arXiv:2410.21991</a> <span> [<a href="https://arxiv.org/pdf/2410.21991">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> From Explicit Rules to Implicit Reasoning in an Interpretable Violence Monitoring System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wen-Dong Jiang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chih-Yung Chang</a>, <a href="/search/cs?searchtype=author&query=Kuai%2C+S">Ssu-Chi Kuai</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+D+S">Diptendu Sinha Roy</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="2410.21991v5-abstract-short" style="display: inline;"> Recently, research based on pre-trained models has demonstrated outstanding performance in violence surveillance tasks. However, most of them were black-box systems which faced challenges regarding explainability during training and inference processes. An important question is how to incorporate explicit knowledge into these implicit models, thereby designing expertdriven and interpretable violen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21991v5-abstract-full').style.display = 'inline'; document.getElementById('2410.21991v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21991v5-abstract-full" style="display: none;"> Recently, research based on pre-trained models has demonstrated outstanding performance in violence surveillance tasks. However, most of them were black-box systems which faced challenges regarding explainability during training and inference processes. An important question is how to incorporate explicit knowledge into these implicit models, thereby designing expertdriven and interpretable violence surveillance systems. This paper proposes a new paradigm for weakly supervised violence monitoring (WSVM) called Rule base Violence Monitoring (RuleVM). The proposed RuleVM uses a dual-branch structure with different designs for images and text. One of the branches is called the implicit branch, which uses only visual features for coarse-grained binary classification. In this branch, image feature extraction is divided into two channels: one responsible for extracting scene frames and the other focusing on extracting actions. The other branch is called the explicit branch, which utilizes language-image alignment to perform fine-grained classification. For the language channel design in the explicit branch, the proposed RuleVM uses the state-of-the-art YOLOWorld model to detect objects in video frames, and association rules are identified through data mining methods as descriptions of the video. Leveraging the dual-branch architecture, RuleVM achieves interpretable coarse-grained and fine-grained violence surveillance. Extensive experiments were conducted on two commonly used benchmarks, and the results show that RuleVM achieved the best performance in both coarse-grained and finegrained monitoring, significantly outperforming existing state-ofthe-art methods. Moreover, interpretability experiments uncovered some interesting rules, such as the observation that as the number of people increases, the risk level of violent behavior also rises. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21991v5-abstract-full').style.display = 'none'; document.getElementById('2410.21991v5-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 29 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">12 pages,7 figures IEEE TSMCA (Under review)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18101">arXiv:2410.18101</a> <span> [<a href="https://arxiv.org/pdf/2410.18101">pdf</a>, <a href="https://arxiv.org/format/2410.18101">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yuzhi Xu</a>, <a href="/search/cs?searchtype=author&query=Ni%2C+H">Haowei Ni</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Q">Qinhui Gao</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chia-Hua Chang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yanran Huo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+F">Fanyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Shiyu Hu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+W">Wei Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yike Zhang</a>, <a href="/search/cs?searchtype=author&query=Grovu%2C+R">Radu Grovu</a>, <a href="/search/cs?searchtype=author&query=He%2C+M">Min He</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J+Z+H">John. Z. H. Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuanqing 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="2410.18101v2-abstract-short" style="display: inline;"> Computational molecular design -- the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches, has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of k… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18101v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18101v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18101v2-abstract-full" style="display: none;"> Computational molecular design -- the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches, has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of key physiological functions, providing structural insights into the mechanism. When abundant data has been collected, a quantitative structure-activity relationship (QSAR) can be more directly constructed from experimental data, from which machine learning can distill key insights to guide the design of the next round of experiment design. Machine learning methodologies can also facilitate physical modeling, from improving the accuracy of force fields and extending them to unseen chemical spaces, to more directly enhancing the sampling on the conformational spaces. We argue that these techniques are mature enough to be applied to not just extend the longevity of life, but the beauty it manifests. In this perspective, we review the current frontiers in the research \& development of skin care products, as well as the statistical and physical toolbox applicable to addressing the challenges in this industry. Feasible interdisciplinary research projects are proposed to harness the power of machine learning tools to design innovative, effective, and inexpensive skin care products. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18101v2-abstract-full').style.display = 'none'; document.getElementById('2410.18101v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 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/2410.17249">arXiv:2410.17249</a> <span> [<a href="https://arxiv.org/pdf/2410.17249">pdf</a>, <a href="https://arxiv.org/format/2410.17249">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"> SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fan%2C+C">Cheng-De Fan</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Wei Chang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yi-Ruei Liu</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J">Jie-Ying Lee</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiun-Long Huang</a>, <a href="/search/cs?searchtype=author&query=Tseng%2C+Y">Yu-Chee Tseng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yu-Lun Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17249v1-abstract-short" style="display: inline;"> We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular scenes. Previous methods extending 3DGS to model dynamic scenes have struggled to accurately represent specular surfaces. Our method addresses this limitation by introducing a residual correction technique for accurate su… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17249v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17249v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17249v1-abstract-full" style="display: none;"> We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular scenes. Previous methods extending 3DGS to model dynamic scenes have struggled to accurately represent specular surfaces. Our method addresses this limitation by introducing a residual correction technique for accurate surface normal computation during deformation, complemented by a deformable environment map that adapts to time-varying lighting conditions. We implement a coarse-to-fine training strategy that significantly enhances both scene geometry and specular color prediction. We demonstrate that our model outperforms prior methods for view synthesis of scenes containing dynamic specular objects and that it is the only existing 3DGS method capable of synthesizing photorealistic real-world dynamic specular scenes, outperforming state-of-the-art methods in rendering complex, dynamic, and specular scenes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17249v1-abstract-full').style.display = 'none'; document.getElementById('2410.17249v1-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">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">Project page: https://cdfan0627.github.io/spectromotion/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15572">arXiv:2410.15572</a> <span> [<a href="https://arxiv.org/pdf/2410.15572">pdf</a>, <a href="https://arxiv.org/format/2410.15572">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"> Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Chi Chang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+H">Han-Pi Chang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+H">Hung-Shin Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15572v1-abstract-short" style="display: inline;"> In an era where cultural preservation is increasingly intertwined with technological innovation, this study introduces a groundbreaking approach to promoting and safeguarding the rich heritage of Taiwanese Hakka culture through the development of a Retrieval-Augmented Generation (RAG)-enhanced chatbot. Traditional large language models (LLMs), while powerful, often fall short in delivering accurat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15572v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15572v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15572v1-abstract-full" style="display: none;"> In an era where cultural preservation is increasingly intertwined with technological innovation, this study introduces a groundbreaking approach to promoting and safeguarding the rich heritage of Taiwanese Hakka culture through the development of a Retrieval-Augmented Generation (RAG)-enhanced chatbot. Traditional large language models (LLMs), while powerful, often fall short in delivering accurate and contextually rich responses, particularly in culturally specific domains. By integrating external databases with generative AI models, RAG technology bridges this gap, empowering chatbots to not only provide precise answers but also resonate deeply with the cultural nuances that are crucial for authentic interactions. This study delves into the intricate process of augmenting the chatbot's knowledge base with targeted cultural data, specifically curated to reflect the unique aspects of Hakka traditions, language, and practices. Through dynamic information retrieval, the RAG-enhanced chatbot becomes a versatile tool capable of handling complex inquiries that demand an in-depth understanding of Hakka cultural context. This is particularly significant in an age where digital platforms often dilute cultural identities, making the role of culturally aware AI systems more critical than ever. System usability studies conducted as part of our research reveal a marked improvement in both user satisfaction and engagement, highlighting the chatbot's effectiveness in fostering a deeper connection with Hakka culture. The feedback underscores the potential of RAG technology to not only enhance user experience but also to serve as a vital instrument in the broader mission of ethnic mainstreaming and cultural celebration. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15572v1-abstract-full').style.display = 'none'; document.getElementById('2410.15572v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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 to IEEE RASSE 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/2410.15511">arXiv:2410.15511</a> <span> [<a href="https://arxiv.org/pdf/2410.15511">pdf</a>, <a href="https://arxiv.org/format/2410.15511">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"> ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roy%2C+K+K">Kashob Kumar Roy</a>, <a href="/search/cs?searchtype=author&query=Akash%2C+P+S">Pritom Saha Akash</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K+C">Kevin Chen-Chuan Chang</a>, <a href="/search/cs?searchtype=author&query=Popa%2C+L">Lucian Popa</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="2410.15511v1-abstract-short" style="display: inline;"> Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowled… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15511v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15511v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15511v1-abstract-full" style="display: none;"> Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowledge from various sources effectively. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach to enhance the depth and relevance of retrieved content. ConTReGen integrates a hierarchical, top-down in-depth exploration of query facets with a systematic bottom-up synthesis, ensuring comprehensive coverage and coherent integration of multifaceted information. Extensive experiments on multiple datasets, including LFQA and ODSUM, alongside a newly introduced dataset, ODSUM-WikiHow, demonstrate that ConTReGen outperforms existing state-of-the-art RAG models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15511v1-abstract-full').style.display = 'none'; document.getElementById('2410.15511v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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 at EMNLP'24 Findings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13229">arXiv:2410.13229</a> <span> [<a href="https://arxiv.org/pdf/2410.13229">pdf</a>, <a href="https://arxiv.org/format/2410.13229">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Quamba: A Post-Training Quantization Recipe for Selective State Space Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chiang%2C+H">Hung-Yueh Chiang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chi-Chih Chang</a>, <a href="/search/cs?searchtype=author&query=Frumkin%2C+N">Natalia Frumkin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+K">Kai-Chiang Wu</a>, <a href="/search/cs?searchtype=author&query=Marculescu%2C+D">Diana Marculescu</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="2410.13229v1-abstract-short" style="display: inline;"> State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than attention-based networks. The superior computational efficiency of SSMs in long sequence modeling positions them favorably over Transformers in many scenarios. However,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13229v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13229v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13229v1-abstract-full" style="display: none;"> State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than attention-based networks. The superior computational efficiency of SSMs in long sequence modeling positions them favorably over Transformers in many scenarios. However, improving the efficiency of SSMs on request-intensive cloud-serving and resource-limited edge applications is still a formidable task. SSM quantization is a possible solution to this problem, making SSMs more suitable for wide deployment, while still maintaining their accuracy. Quantization is a common technique to reduce the model size and to utilize the low bit-width acceleration features on modern computing units, yet existing quantization techniques are poorly suited for SSMs. Most notably, SSMs have highly sensitive feature maps within the selective scan mechanism (i.e., linear recurrence) and massive outliers in the output activations which are not present in the output of token-mixing in the self-attention modules. To address this issue, we propose a static 8-bit per-tensor SSM quantization method which suppresses the maximum values of the input activations to the selective SSM for finer quantization precision and quantizes the output activations in an outlier-free space with Hadamard transform. Our 8-bit weight-activation quantized Mamba 2.8B SSM benefits from hardware acceleration and achieves a 1.72x lower generation latency on an Nvidia Orin Nano 8G, with only a 0.9% drop in average accuracy on zero-shot tasks. The experiments demonstrate the effectiveness and practical applicability of our approach for deploying SSM-based models of all sizes on both cloud and edge platforms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13229v1-abstract-full').style.display = 'none'; document.getElementById('2410.13229v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12606">arXiv:2410.12606</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching Chang</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+C">Chiao-Tung Chan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wei-Yao Wang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+W">Wen-Chih Peng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tien-Fu Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.12606v2-abstract-short" style="display: inline;"> Multivariate time-series data in fields like healthcare and industry are informative but challenging due to high dimensionality and lack of labels. Recent self-supervised learning methods excel in learning rich representations without labels but struggle with disentangled embeddings and inductive bias issues like transformation-invariance. To address these challenges, we introduce TimeDRL, a frame… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12606v2-abstract-full').style.display = 'inline'; document.getElementById('2410.12606v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12606v2-abstract-full" style="display: none;"> Multivariate time-series data in fields like healthcare and industry are informative but challenging due to high dimensionality and lack of labels. Recent self-supervised learning methods excel in learning rich representations without labels but struggle with disentangled embeddings and inductive bias issues like transformation-invariance. To address these challenges, we introduce TimeDRL, a framework for multivariate time-series representation learning with dual-level disentangled embeddings. TimeDRL features: (i) disentangled timestamp-level and instance-level embeddings using a [CLS] token strategy; (ii) timestamp-predictive and instance-contrastive tasks for representation learning; and (iii) avoidance of augmentation methods to eliminate inductive biases. Experiments on forecasting and classification datasets show TimeDRL outperforms existing methods, with further validation in semi-supervised settings with limited labeled data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12606v2-abstract-full').style.display = 'none'; document.getElementById('2410.12606v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 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">This submission has been withdrawn to avoid duplication with a full version of the paper that is already available in another arXiv entry (arXiv:2410.12606). The withdrawn version was a short format prepared for a NeurIPS workshop and is no longer necessary as a separate arXiv submission</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05341">arXiv:2410.05341</a> <span> [<a href="https://arxiv.org/pdf/2410.05341">pdf</a>, <a href="https://arxiv.org/format/2410.05341">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yamin Li</a>, <a href="/search/cs?searchtype=author&query=Lou%2C+A">Ange Lou</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyuan Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shengchao Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shiyu Wang</a>, <a href="/search/cs?searchtype=author&query=Englot%2C+D+J">Dario J. Englot</a>, <a href="/search/cs?searchtype=author&query=Kolouri%2C+S">Soheil Kolouri</a>, <a href="/search/cs?searchtype=author&query=Moyer%2C+D">Daniel Moyer</a>, <a href="/search/cs?searchtype=author&query=Bayrak%2C+R+G">Roza G. Bayrak</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</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="2410.05341v2-abstract-short" style="display: inline;"> Functional magnetic resonance imaging (fMRI) is an indispensable tool in modern neuroscience, providing a non-invasive window into whole-brain dynamics at millimeter-scale spatial resolution. However, fMRI is constrained by issues such as high operation costs and immobility. With the rapid advancements in cross-modality synthesis and brain decoding, the use of deep neural networks has emerged as a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05341v2-abstract-full').style.display = 'inline'; document.getElementById('2410.05341v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05341v2-abstract-full" style="display: none;"> Functional magnetic resonance imaging (fMRI) is an indispensable tool in modern neuroscience, providing a non-invasive window into whole-brain dynamics at millimeter-scale spatial resolution. However, fMRI is constrained by issues such as high operation costs and immobility. With the rapid advancements in cross-modality synthesis and brain decoding, the use of deep neural networks has emerged as a promising solution for inferring whole-brain, high-resolution fMRI features directly from electroencephalography (EEG), a more widely accessible and portable neuroimaging modality. Nonetheless, the complex projection from neural activity to fMRI hemodynamic responses and the spatial ambiguity of EEG pose substantial challenges both in modeling and interpretability. Relatively few studies to date have developed approaches for EEG-fMRI translation, and although they have made significant strides, the inference of fMRI signals in a given study has been limited to a small set of brain areas and to a single condition (i.e., either resting-state or a specific task). The capability to predict fMRI signals in other brain areas, as well as to generalize across conditions, remain critical gaps in the field. To tackle these challenges, we introduce a novel and generalizable framework: NeuroBOLT, i.e., Neuro-to-BOLD Transformer, which leverages multi-dimensional representation learning from temporal, spatial, and spectral domains to translate raw EEG data to the corresponding fMRI activity signals across the brain. Our experiments demonstrate that NeuroBOLT effectively reconstructs unseen resting-state fMRI signals from primary sensory, high-level cognitive areas, and deep subcortical brain regions, achieving state-of-the-art accuracy with the potential to generalize across varying conditions and sites, which significantly advances the integration of these two modalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05341v2-abstract-full').style.display = 'none'; document.getElementById('2410.05341v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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">This preprint has been accepted to NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05284">arXiv:2410.05284</a> <span> [<a href="https://arxiv.org/pdf/2410.05284">pdf</a>, <a href="https://arxiv.org/format/2410.05284">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching-Chun Chang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+K">Kai Gao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Shuying Xu</a>, <a href="/search/cs?searchtype=author&query=Kordoni%2C+A">Anastasia Kordoni</a>, <a href="/search/cs?searchtype=author&query=Leckie%2C+C">Christopher Leckie</a>, <a href="/search/cs?searchtype=author&query=Echizen%2C+I">Isao Echizen</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="2410.05284v1-abstract-short" style="display: inline;"> Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A backdoor attack involves the clandestine infiltration of a trigger during the learning process, metaphorically analogous to hypnopaedia, where ideas are implanted int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05284v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05284v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05284v1-abstract-full" style="display: none;"> Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A backdoor attack involves the clandestine infiltration of a trigger during the learning process, metaphorically analogous to hypnopaedia, where ideas are implanted into a subject's subconscious mind under the state of hypnosis or unconsciousness. When activated by a sensory stimulus, the trigger evokes conditioned reflex that directs a machine to mount a predetermined response. In this study, we propose a cybernetic framework for constant surveillance of backdoors threats, driven by the dynamic nature of untrustworthy data sources. We develop a self-aware unlearning mechanism to autonomously detach a machine's behaviour from the backdoor trigger. Through reverse engineering and statistical inference, we detect deceptive patterns and estimate the likelihood of backdoor infection. We employ model inversion to elicit artificial mental imagery, using stochastic processes to disrupt optimisation pathways and avoid convergent but potentially flawed patterns. This is followed by hypothesis analysis, which estimates the likelihood of each potentially malicious pattern being the true trigger and infers the probability of infection. The primary objective of this study is to maintain a stable state of equilibrium between knowledge fidelity and backdoor vulnerability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05284v1-abstract-full').style.display = 'none'; document.getElementById('2410.05284v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05243">arXiv:2410.05243</a> <span> [<a href="https://arxiv.org/pdf/2410.05243">pdf</a>, <a href="https://arxiv.org/format/2410.05243">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gou%2C+B">Boyu Gou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruohan Wang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+B">Boyuan Zheng</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Yanan Xie</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Cheng Chang</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+Y">Yiheng Shu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+H">Huan Sun</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Y">Yu Su</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="2410.05243v1-abstract-short" style="display: inline;"> Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05243v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05243v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05243v1-abstract-full" style="display: none;"> Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representations such as HTML or accessibility trees, which, despite their utility, often introduce noise, incompleteness, and increased computational overhead. In this paper, we advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly take pixel-level operations on the GUI. The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots, and use it to train UGround, a strong universal visual grounding model for GUI agents. Empirical results on six benchmarks spanning three categories (grounding, offline agent, and online agent) show that 1) UGround substantially outperforms existing visual grounding models for GUI agents, by up to 20% absolute, and 2) agents with UGround outperform state-of-the-art agents, despite the fact that existing agents use additional text-based input while ours only uses visual perception. These results provide strong support for the feasibility and promises of GUI agents that navigate the digital world as humans do. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05243v1-abstract-full').style.display = 'none'; document.getElementById('2410.05243v1-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/2410.04025">arXiv:2410.04025</a> <span> [<a href="https://arxiv.org/pdf/2410.04025">pdf</a>, <a href="https://arxiv.org/format/2410.04025">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pu%2C+K">Kevin Pu</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+K+J+K">K. J. Kevin Feng</a>, <a href="/search/cs?searchtype=author&query=Grossman%2C+T">Tovi Grossman</a>, <a href="/search/cs?searchtype=author&query=Hope%2C+T">Tom Hope</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+B+D">Bhavana Dalvi Mishra</a>, <a href="/search/cs?searchtype=author&query=Latzke%2C+M">Matt Latzke</a>, <a href="/search/cs?searchtype=author&query=Bragg%2C+J">Jonathan Bragg</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J+C">Joseph Chee Chang</a>, <a href="/search/cs?searchtype=author&query=Siangliulue%2C+P">Pao Siangliulue</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="2410.04025v1-abstract-short" style="display: inline;"> Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04025v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04025v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04025v1-abstract-full" style="display: none;"> Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04025v1-abstract-full').style.display = 'none'; document.getElementById('2410.04025v1-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 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/2410.03071">arXiv:2410.03071</a> <span> [<a href="https://arxiv.org/pdf/2410.03071">pdf</a>, <a href="https://arxiv.org/format/2410.03071">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Akash%2C+P+S">Pritom Saha Akash</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K+C">Kevin Chen-Chuan Chang</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="2410.03071v2-abstract-short" style="display: inline;"> Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents. However, the effectiveness of traditional topic models often relies on sufficient word co-occurrence, which is lacking in short texts. Therefore, existing approaches, whether probabilistic or neural, frequently struggle to extract meaningful patterns from such data, resulting in incoherent topics.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03071v2-abstract-full').style.display = 'inline'; document.getElementById('2410.03071v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03071v2-abstract-full" style="display: none;"> Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents. However, the effectiveness of traditional topic models often relies on sufficient word co-occurrence, which is lacking in short texts. Therefore, existing approaches, whether probabilistic or neural, frequently struggle to extract meaningful patterns from such data, resulting in incoherent topics. To address this challenge, we propose a novel approach that leverages large language models (LLMs) to extend short texts into more detailed sequences before applying topic modeling. To further improve the efficiency and solve the problem of semantic inconsistency from LLM-generated texts, we propose to use prefix tuning to train a smaller language model coupled with a variational autoencoder for short-text topic modeling. Our method significantly improves short-text topic modeling performance, as demonstrated by extensive experiments on real-world datasets with extreme data sparsity, outperforming current state-of-the-art topic models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03071v2-abstract-full').style.display = 'none'; document.getElementById('2410.03071v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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">EMNLP Findings 2024. arXiv admin note: substantial text overlap with arXiv:2310.15420</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00059">arXiv:2410.00059</a> <span> [<a href="https://arxiv.org/pdf/2410.00059">pdf</a>, <a href="https://arxiv.org/format/2410.00059">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chaohui Xu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+Q">Qi Cui</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Jinxin Dong</a>, <a href="/search/cs?searchtype=author&query=He%2C+W">Weiyang He</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chip-Hong Chang</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="2410.00059v1-abstract-short" style="display: inline;"> Illegitimate reproduction, distribution and derivation of Deep Neural Network (DNN) models can inflict economic loss, reputation damage and even privacy infringement. Passive DNN intellectual property (IP) protection methods such as watermarking and fingerprinting attempt to prove the ownership upon IP violation, but they are often too late to stop catastrophic damage of IP abuse and too feeble ag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00059v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00059v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00059v1-abstract-full" style="display: none;"> Illegitimate reproduction, distribution and derivation of Deep Neural Network (DNN) models can inflict economic loss, reputation damage and even privacy infringement. Passive DNN intellectual property (IP) protection methods such as watermarking and fingerprinting attempt to prove the ownership upon IP violation, but they are often too late to stop catastrophic damage of IP abuse and too feeble against strong adversaries. In this paper, we propose IDEA, an Inverse Domain Expert Adaptation based proactive DNN IP protection method featuring active authorization and source traceability. IDEA generalizes active authorization as an inverse problem of domain adaptation. The multi-adaptive optimization is solved by a mixture-of-experts model with one real and two fake experts. The real expert re-optimizes the source model to correctly classify test images with a unique model user key steganographically embedded. The fake experts are trained to output random prediction on test images without or with incorrect user key embedded by minimizing their mutual information (MI) with the real expert. The MoE model is knowledge distilled into a unified protected model to avoid leaking the expert model features by maximizing their MI with additional multi-layer attention and contrastive representation loss optimization. IDEA not only prevents unauthorized users without the valid key to access the functional model, but also enable the model owner to validate the deployed model and trace the source of IP infringement. We extensively evaluate IDEA on five datasets and four DNN models to demonstrate its effectiveness in authorization control, culprit tracing success rate, and robustness against various attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00059v1-abstract-full').style.display = 'none'; document.getElementById('2410.00059v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19638">arXiv:2409.19638</a> <span> [<a href="https://arxiv.org/pdf/2409.19638">pdf</a>, <a href="https://arxiv.org/format/2409.19638">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> BadHMP: Backdoor Attack against Human Motion Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chaohui Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Si Wang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chip-Hong Chang</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="2409.19638v1-abstract-short" style="display: inline;"> Precise future human motion prediction over subsecond horizons from past observations is crucial for various safety-critical applications. To date, only one study has examined the vulnerability of human motion prediction to evasion attacks. In this paper, we propose BadHMP, the first backdoor attack that targets specifically human motion prediction. Our approach involves generating poisoned traini… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19638v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19638v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19638v1-abstract-full" style="display: none;"> Precise future human motion prediction over subsecond horizons from past observations is crucial for various safety-critical applications. To date, only one study has examined the vulnerability of human motion prediction to evasion attacks. In this paper, we propose BadHMP, the first backdoor attack that targets specifically human motion prediction. Our approach involves generating poisoned training samples by embedding a localized backdoor trigger in one arm of the skeleton, causing selected joints to remain relatively still or follow predefined motion in historical time steps. Subsequently, the future sequences are globally modified to the target sequences, and the entire training dataset is traversed to select the most suitable samples for poisoning. Our carefully designed backdoor triggers and targets guarantee the smoothness and naturalness of the poisoned samples, making them stealthy enough to evade detection by the model trainer while keeping the poisoned model unobtrusive in terms of prediction fidelity to untainted sequences. The target sequences can be successfully activated by the designed input sequences even with a low poisoned sample injection ratio. Experimental results on two datasets (Human3.6M and CMU-Mocap) and two network architectures (LTD and HRI) demonstrate the high-fidelity, effectiveness, and stealthiness of BadHMP. Robustness of our attack against fine-tuning defense is also verified. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19638v1-abstract-full').style.display = 'none'; document.getElementById('2409.19638v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 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/2409.18164">arXiv:2409.18164</a> <span> [<a href="https://arxiv.org/pdf/2409.18164">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Data-Prep-Kit: getting your data ready for LLM application development </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wood%2C+D">David Wood</a>, <a href="/search/cs?searchtype=author&query=Lublinsky%2C+B">Boris Lublinsky</a>, <a href="/search/cs?searchtype=author&query=Roytman%2C+A">Alexy Roytman</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+S">Shivdeep Singh</a>, <a href="/search/cs?searchtype=author&query=Adam%2C+C">Constantin Adam</a>, <a href="/search/cs?searchtype=author&query=Adebayo%2C+A">Abdulhamid Adebayo</a>, <a href="/search/cs?searchtype=author&query=An%2C+S">Sungeun An</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+Y+C">Yuan Chi Chang</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+X">Xuan-Hong Dang</a>, <a href="/search/cs?searchtype=author&query=Desai%2C+N">Nirmit Desai</a>, <a href="/search/cs?searchtype=author&query=Dolfi%2C+M">Michele Dolfi</a>, <a href="/search/cs?searchtype=author&query=Emami-Gohari%2C+H">Hajar Emami-Gohari</a>, <a href="/search/cs?searchtype=author&query=Eres%2C+R">Revital Eres</a>, <a href="/search/cs?searchtype=author&query=Goto%2C+T">Takuya Goto</a>, <a href="/search/cs?searchtype=author&query=Joshi%2C+D">Dhiraj Joshi</a>, <a href="/search/cs?searchtype=author&query=Koyfman%2C+Y">Yan Koyfman</a>, <a href="/search/cs?searchtype=author&query=Nassar%2C+M">Mohammad Nassar</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+H">Hima Patel</a>, <a href="/search/cs?searchtype=author&query=Selvam%2C+P">Paramesvaran Selvam</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+Y">Yousaf Shah</a>, <a href="/search/cs?searchtype=author&query=Surendran%2C+S">Saptha Surendran</a>, <a href="/search/cs?searchtype=author&query=Tsuzuku%2C+D">Daiki Tsuzuku</a>, <a href="/search/cs?searchtype=author&query=Zerfos%2C+P">Petros Zerfos</a>, <a href="/search/cs?searchtype=author&query=Daijavad%2C+S">Shahrokh Daijavad</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="2409.18164v2-abstract-short" style="display: inline;"> Data preparation is the first and a very important step towards any Large Language Model (LLM) development. This paper introduces an easy-to-use, extensible, and scale-flexible open-source data preparation toolkit called Data Prep Kit (DPK). DPK is architected and designed to enable users to scale their data preparation to their needs. With DPK they can prepare data on a local machine or effortles… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18164v2-abstract-full').style.display = 'inline'; document.getElementById('2409.18164v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18164v2-abstract-full" style="display: none;"> Data preparation is the first and a very important step towards any Large Language Model (LLM) development. This paper introduces an easy-to-use, extensible, and scale-flexible open-source data preparation toolkit called Data Prep Kit (DPK). DPK is architected and designed to enable users to scale their data preparation to their needs. With DPK they can prepare data on a local machine or effortlessly scale to run on a cluster with thousands of CPU Cores. DPK comes with a highly scalable, yet extensible set of modules that transform natural language and code data. If the user needs additional transforms, they can be easily developed using extensive DPK support for transform creation. These modules can be used independently or pipelined to perform a series of operations. In this paper, we describe DPK architecture and show its performance from a small scale to a very large number of CPUs. The modules from DPK have been used for the preparation of Granite Models [1] [2]. We believe DPK is a valuable contribution to the AI community to easily prepare data to enhance the performance of their LLM models or to fine-tune models with Retrieval-Augmented Generation (RAG). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18164v2-abstract-full').style.display = 'none'; document.getElementById('2409.18164v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 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">10 pages, 7 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/2409.14115">arXiv:2409.14115</a> <span> [<a href="https://arxiv.org/pdf/2409.14115">pdf</a>, <a href="https://arxiv.org/format/2409.14115">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"> Aerial Grasping with Soft Aerial Vehicle Using Disturbance Observer-Based Model Predictive Control </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheung%2C+H+C">Hiu Ching Cheung</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+B">Bailun Jiang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yang Hu</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+H+K">Henry K. Chu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+C">Chih-Yung Wen</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching-Wei Chang</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="2409.14115v1-abstract-short" style="display: inline;"> Aerial grasping, particularly soft aerial grasping, holds significant promise for drone delivery and harvesting tasks. However, controlling UAV dynamics during aerial grasping presents considerable challenges. The increased mass during payload grasping adversely affects thrust prediction, while unpredictable environmental disturbances further complicate control efforts. In this study, our objectiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14115v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14115v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14115v1-abstract-full" style="display: none;"> Aerial grasping, particularly soft aerial grasping, holds significant promise for drone delivery and harvesting tasks. However, controlling UAV dynamics during aerial grasping presents considerable challenges. The increased mass during payload grasping adversely affects thrust prediction, while unpredictable environmental disturbances further complicate control efforts. In this study, our objective aims to enhance the control of the Soft Aerial Vehicle (SAV) during aerial grasping by incorporating a disturbance observer into a Nonlinear Model Predictive Control (NMPC) SAV controller. By integrating the disturbance observer into the NMPC SAV controller, we aim to compensate for dynamic model idealization and uncertainties arising from additional payloads and unpredictable disturbances. Our approach combines a disturbance observer-based NMPC with the SAV controller, effectively minimizing tracking errors and enabling precise aerial grasping along all three axes. The proposed SAV equipped with Disturbance Observer-based Nonlinear Model Predictive Control (DOMPC) demonstrates remarkable capabilities in handling both static and non-static payloads, leading to the successful grasping of various objects. Notably, our SAV achieves an impressive payload-to-weight ratio, surpassing previous investigations in the domain of soft grasping. Using the proposed soft aerial vehicle weighing 1.002 kg, we achieve a maximum payload of 337 g by grasping. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14115v1-abstract-full').style.display = 'none'; document.getElementById('2409.14115v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 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">8 pages, 10 figures, submitted to IEEE Robotics Automation Letters</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.11576">arXiv:2409.11576</a> <span> [<a href="https://arxiv.org/pdf/2409.11576">pdf</a>, <a href="https://arxiv.org/format/2409.11576">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Automating proton PBS treatment planning for head and neck cancers using policy gradient-based deep reinforcement learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qingqing Wang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chang Chang</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="2409.11576v1-abstract-short" style="display: inline;"> Proton pencil beam scanning (PBS) treatment planning for head and neck (H&N) cancers is a time-consuming and experience-demanding task where a large number of planning objectives are involved. Deep reinforcement learning (DRL) has recently been introduced to the planning processes of intensity-modulated radiation therapy and brachytherapy for prostate, lung, and cervical cancers. However, existing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11576v1-abstract-full').style.display = 'inline'; document.getElementById('2409.11576v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.11576v1-abstract-full" style="display: none;"> Proton pencil beam scanning (PBS) treatment planning for head and neck (H&N) cancers is a time-consuming and experience-demanding task where a large number of planning objectives are involved. Deep reinforcement learning (DRL) has recently been introduced to the planning processes of intensity-modulated radiation therapy and brachytherapy for prostate, lung, and cervical cancers. However, existing approaches are built upon the Q-learning framework and weighted linear combinations of clinical metrics, suffering from poor scalability and flexibility and only capable of adjusting a limited number of planning objectives in discrete action spaces. We propose an automatic treatment planning model using the proximal policy optimization (PPO) algorithm and a dose distribution-based reward function for proton PBS treatment planning of H&N cancers. Specifically, a set of empirical rules is used to create auxiliary planning structures from target volumes and organs-at-risk (OARs), along with their associated planning objectives. These planning objectives are fed into an in-house optimization engine to generate the spot monitor unit (MU) values. A decision-making policy network trained using PPO is developed to iteratively adjust the involved planning objective parameters in a continuous action space and refine the PBS treatment plans using a novel dose distribution-based reward function. Proton H&N treatment plans generated by the model show improved OAR sparing with equal or superior target coverage when compared with human-generated plans. Moreover, additional experiments on liver cancer demonstrate that the proposed method can be successfully generalized to other treatment sites. To the best of our knowledge, this is the first DRL-based automatic treatment planning model capable of achieving human-level performance for H&N cancers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11576v1-abstract-full').style.display = 'none'; document.getElementById('2409.11576v1-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 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/2409.09708">arXiv:2409.09708</a> <span> [<a href="https://arxiv.org/pdf/2409.09708">pdf</a>, <a href="https://arxiv.org/format/2409.09708">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+N">Ning-Chi Huang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chi-Chih Chang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+W">Wei-Cheng Lin</a>, <a href="/search/cs?searchtype=author&query=Taka%2C+E">Endri Taka</a>, <a href="/search/cs?searchtype=author&query=Marculescu%2C+D">Diana Marculescu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+K">Kai-Chiang Wu</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="2409.09708v1-abstract-short" style="display: inline;"> $N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09708v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09708v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09708v1-abstract-full" style="display: none;"> $N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M$ sparsity methods compress neural networks with a uniform setting for all layers in a network or heuristically determine the layer-wise configuration by considering the number of parameters in each layer. However, very few methods have been designed for obtaining a layer-wise customized $N{:}M$ sparse configuration for vision transformers (ViTs), which usually consist of transformer blocks involving the same number of parameters. In this work, to address the challenge of selecting suitable sparse configuration for ViTs on $N{:}M$ sparsity-supporting accelerators, we propose ELSA, Exploiting Layer-wise $N{:}M$ Sparsity for ViTs. Considering not only all $N{:}M$ sparsity levels supported by a given accelerator but also the expected throughput improvement, our methodology can reap the benefits of accelerators supporting mixed sparsity by trading off negligible accuracy loss with both memory usage and inference time reduction for ViT models. For instance, our approach achieves a noteworthy 2.9$\times$ reduction in FLOPs for both Swin-B and DeiT-B with only a marginal degradation of accuracy on ImageNet. Our code will be released upon paper acceptance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09708v1-abstract-full').style.display = 'none'; document.getElementById('2409.09708v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08825">arXiv:2409.08825</a> <span> [<a href="https://arxiv.org/pdf/2409.08825">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</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"> Flight Testing of Latch Valve with Lightweight LV-Servo Direct Drive Mechanism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+H">Hao-Che Huang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chih-Shin Chang</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+J">Jui-Cheng Hsu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+S">Shih-Sin Wei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.08825v3-abstract-short" style="display: inline;"> In the field of rocket technology, the latch valve assumes a pivotal role in regulating the flow of fuel gases and liquids to ensure the requisite energy supply. This project endeavors to innovate by replacing the conventional step motor mechanism with a servo motor for latch valve control. The selected servo motor, boasting a more compact form factor and reduced mass, aligns seamlessly with the p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08825v3-abstract-full').style.display = 'inline'; document.getElementById('2409.08825v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08825v3-abstract-full" style="display: none;"> In the field of rocket technology, the latch valve assumes a pivotal role in regulating the flow of fuel gases and liquids to ensure the requisite energy supply. This project endeavors to innovate by replacing the conventional step motor mechanism with a servo motor for latch valve control. The selected servo motor, boasting a more compact form factor and reduced mass, aligns seamlessly with the project's overarching objectives. While servo motors offer myriad advantages, it is imperative to acknowledge and address the constraints of their maximum output torque to guarantee the latch valve's reliable operation. Furthermore, as a rocket ascends, it encounters significant fluctuations in internal temperature and pressure. Consequently, rigorous environmental testing becomes paramount to validate the servo motor's performance under these dynamic conditions, thus ensuring the latch valve's unwavering functionality. The primary focus of this project is the design and testing of the mechanism's performance in simulated rocket environments, achieved through the implementation of the servo motor for latch valve control. The results reveal that the servo motor demonstrated its effectiveness and reliability in controlling the latch valve under the rigorous environmental conditions of rocket flight. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08825v3-abstract-full').style.display = 'none'; document.getElementById('2409.08825v3-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 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">21 pages, 14 figures and 1 table</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 74F10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> J.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.01556">arXiv:2409.01556</a> <span> [<a href="https://arxiv.org/pdf/2409.01556">pdf</a>, <a href="https://arxiv.org/format/2409.01556">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"> Benchmarking Cognitive Domains for LLMs: Insights from Taiwanese Hakka Culture </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Chi Chang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Ching-Yuan Chen</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+H">Hung-Shin Lee</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+C">Chih-Cheng Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.01556v2-abstract-short" style="display: inline;"> This study introduces a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in understanding and processing cultural knowledge, with a specific focus on Hakka culture as a case study. Leveraging Bloom's Taxonomy, the study develops a multi-dimensional framework that systematically assesses LLMs across six cognitive domains: Remembering, Understanding, Apply… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01556v2-abstract-full').style.display = 'inline'; document.getElementById('2409.01556v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.01556v2-abstract-full" style="display: none;"> This study introduces a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in understanding and processing cultural knowledge, with a specific focus on Hakka culture as a case study. Leveraging Bloom's Taxonomy, the study develops a multi-dimensional framework that systematically assesses LLMs across six cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. This benchmark extends beyond traditional single-dimensional evaluations by providing a deeper analysis of LLMs' abilities to handle culturally specific content, ranging from basic recall of facts to higher-order cognitive tasks such as creative synthesis. Additionally, the study integrates Retrieval-Augmented Generation (RAG) technology to address the challenges of minority cultural knowledge representation in LLMs, demonstrating how RAG enhances the models' performance by dynamically incorporating relevant external information. The results highlight the effectiveness of RAG in improving accuracy across all cognitive domains, particularly in tasks requiring precise retrieval and application of cultural knowledge. However, the findings also reveal the limitations of RAG in creative tasks, underscoring the need for further optimization. This benchmark provides a robust tool for evaluating and comparing LLMs in culturally diverse contexts, offering valuable insights for future research and development in AI-driven cultural knowledge preservation and dissemination. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01556v2-abstract-full').style.display = 'none'; document.getElementById('2409.01556v2-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 2 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">Accepted to O-COCOSDA 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/2409.01548">arXiv:2409.01548</a> <span> [<a href="https://arxiv.org/pdf/2409.01548">pdf</a>, <a href="https://arxiv.org/format/2409.01548">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+L">Li-Wei Chen</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+H">Hung-Shin Lee</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Chi Chang</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="2409.01548v3-abstract-short" style="display: inline;"> This paper introduces VoxHakka, a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. Leveraging the YourTTS framework, VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis while supporting six distinct Hakka dialects. This is achieved by training the model with dialect-specific data, allowing for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01548v3-abstract-full').style.display = 'inline'; document.getElementById('2409.01548v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.01548v3-abstract-full" style="display: none;"> This paper introduces VoxHakka, a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. Leveraging the YourTTS framework, VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis while supporting six distinct Hakka dialects. This is achieved by training the model with dialect-specific data, allowing for the generation of speaker-aware Hakka speech. To address the scarcity of publicly available Hakka speech corpora, we employed a cost-effective approach utilizing a web scraping pipeline coupled with automatic speech recognition (ASR)-based data cleaning techniques. This process ensured the acquisition of a high-quality, multi-speaker, multi-dialect dataset suitable for TTS training. Subjective listening tests conducted using comparative mean opinion scores (CMOS) demonstrate that VoxHakka significantly outperforms existing publicly available Hakka TTS systems in terms of pronunciation accuracy, tone correctness, and overall naturalness. This work represents a significant advancement in Hakka language technology and provides a valuable resource for language preservation and revitalization efforts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01548v3-abstract-full').style.display = 'none'; document.getElementById('2409.01548v3-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">v1</span> submitted 2 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">Accepted to O-COCOSDA 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/2409.01541">arXiv:2409.01541</a> <span> [<a href="https://arxiv.org/pdf/2409.01541">pdf</a>, <a href="https://arxiv.org/format/2409.01541">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Purification-Agnostic Proxy Learning for Agentic Copyright Watermarking against Adversarial Evidence Forgery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bao%2C+E">Erjin Bao</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching-Chun Chang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hanrui Wang</a>, <a href="/search/cs?searchtype=author&query=Echizen%2C+I">Isao Echizen</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="2409.01541v1-abstract-short" style="display: inline;"> With the proliferation of AI agents in various domains, protecting the ownership of AI models has become crucial due to the significant investment in their development. Unauthorized use and illegal distribution of these models pose serious threats to intellectual property, necessitating effective copyright protection measures. Model watermarking has emerged as a key technique to address this issue… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01541v1-abstract-full').style.display = 'inline'; document.getElementById('2409.01541v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.01541v1-abstract-full" style="display: none;"> With the proliferation of AI agents in various domains, protecting the ownership of AI models has become crucial due to the significant investment in their development. Unauthorized use and illegal distribution of these models pose serious threats to intellectual property, necessitating effective copyright protection measures. Model watermarking has emerged as a key technique to address this issue, embedding ownership information within models to assert rightful ownership during copyright disputes. This paper presents several contributions to model watermarking: a self-authenticating black-box watermarking protocol using hash techniques, a study on evidence forgery attacks using adversarial perturbations, a proposed defense involving a purification step to counter adversarial attacks, and a purification-agnostic proxy learning method to enhance watermark reliability and model performance. Experimental results demonstrate the effectiveness of these approaches in improving the security, reliability, and performance of watermarked models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01541v1-abstract-full').style.display = 'none'; document.getElementById('2409.01541v1-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 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/2408.15425">arXiv:2408.15425</a> <span> [<a href="https://arxiv.org/pdf/2408.15425">pdf</a>, <a href="https://arxiv.org/format/2408.15425">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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/10.55417/fr.2024001">10.55417/fr.2024001 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fast and Modular Autonomy Software for Autonomous Racing Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Saba%2C+A">Andrew Saba</a>, <a href="/search/cs?searchtype=author&query=Adetunji%2C+A">Aderotimi Adetunji</a>, <a href="/search/cs?searchtype=author&query=Johnson%2C+A">Adam Johnson</a>, <a href="/search/cs?searchtype=author&query=Kothari%2C+A">Aadi Kothari</a>, <a href="/search/cs?searchtype=author&query=Sivaprakasam%2C+M">Matthew Sivaprakasam</a>, <a href="/search/cs?searchtype=author&query=Spisak%2C+J">Joshua Spisak</a>, <a href="/search/cs?searchtype=author&query=Bharatia%2C+P">Prem Bharatia</a>, <a href="/search/cs?searchtype=author&query=Chauhan%2C+A">Arjun Chauhan</a>, <a href="/search/cs?searchtype=author&query=Duff%2C+B">Brendan Duff Jr.</a>, <a href="/search/cs?searchtype=author&query=Gasparro%2C+N">Noah Gasparro</a>, <a href="/search/cs?searchtype=author&query=King%2C+C">Charles King</a>, <a href="/search/cs?searchtype=author&query=Larkin%2C+R">Ryan Larkin</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+B">Brian Mao</a>, <a href="/search/cs?searchtype=author&query=Nye%2C+M">Micah Nye</a>, <a href="/search/cs?searchtype=author&query=Parashar%2C+A">Anjali Parashar</a>, <a href="/search/cs?searchtype=author&query=Attias%2C+J">Joseph Attias</a>, <a href="/search/cs?searchtype=author&query=Balciunas%2C+A">Aurimas Balciunas</a>, <a href="/search/cs?searchtype=author&query=Brown%2C+A">Austin Brown</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chris Chang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+M">Ming Gao</a>, <a href="/search/cs?searchtype=author&query=Heredia%2C+C">Cindy Heredia</a>, <a href="/search/cs?searchtype=author&query=Keats%2C+A">Andrew Keats</a>, <a href="/search/cs?searchtype=author&query=Lavariega%2C+J">Jose Lavariega</a>, <a href="/search/cs?searchtype=author&query=Muckelroy%2C+W">William Muckelroy III</a>, <a href="/search/cs?searchtype=author&query=Slavescu%2C+A">Andre Slavescu</a> , et al. (5 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="2408.15425v1-abstract-short" style="display: inline;"> Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their handling limits in multi-agent scenarios at extremely high ($\geq 150mph$) speeds. This Operational Design Domain (ODD) presents unique challenges across the autonomy stack. The Indy Autonomous Challenge (IAC) is an interna… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15425v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15425v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15425v1-abstract-full" style="display: none;"> Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their handling limits in multi-agent scenarios at extremely high ($\geq 150mph$) speeds. This Operational Design Domain (ODD) presents unique challenges across the autonomy stack. The Indy Autonomous Challenge (IAC) is an international competition aiming to advance autonomous vehicle development through ARV competitions. While far from challenging what a human racecar driver can do, the IAC is pushing the state of the art by facilitating full-sized ARV competitions. This paper details the MIT-Pitt-RW Team's approach to autonomous racing in the IAC. In this work, we present our modular and fast approach to agent detection, motion planning and controls to create an autonomy stack. We also provide analysis of the performance of the software stack in single and multi-agent scenarios for rapid deployment in a fast-paced competition environment. We also cover what did and did not work when deployed on a physical system the Dallara AV-21 platform and potential improvements to address these shortcomings. Finally, we convey lessons learned and discuss limitations and future directions for improvement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15425v1-abstract-full').style.display = 'none'; document.getElementById('2408.15425v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 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">Published in Journal of Field Robotics</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Field Robotics Volume 4 (2024) 1-45 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14453">arXiv:2408.14453</a> <span> [<a href="https://arxiv.org/pdf/2408.14453">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Reconstructing physiological signals from fMRI across the adult lifespan </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shiyu Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyuan Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yamin Li</a>, <a href="/search/cs?searchtype=author&query=Mather%2C+M">Mara Mather</a>, <a href="/search/cs?searchtype=author&query=Bayrak%2C+R+G">Roza G. Bayrak</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</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="2408.14453v1-abstract-short" style="display: inline;"> Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14453v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14453v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14453v1-abstract-full" style="display: none;"> Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not always possible to acquire since they require extra equipment and setup, and even when they are, the recorded physiological signals may contain substantial artifacts. To overcome this limitation, machine learning models have been proposed to directly extract features of respiratory and cardiac activity from resting-state fMRI signals. To date, such work has been carried out only in healthy young adults and in a pediatric population, leaving open questions about the efficacy of these approaches on older adults. Here, we propose a novel framework that leverages Transformer-based architectures for reconstructing two key physiological signals - low-frequency respiratory volume (RV) and heart rate (HR) fluctuations - from fMRI data, and test these models on a dataset of individuals aged 36-89 years old. Our framework outperforms previously proposed approaches (attaining median correlations between predicted and measured signals of r ~ .698 for RV and r ~ .618 for HR), indicating the potential of leveraging attention mechanisms to model fMRI-physiological signal relationships. We also evaluate several model training and fine-tuning strategies, and find that incorporating young-adult data during training improves the performance when predicting physiological signals in the aging cohort. Overall, our approach successfully infers key physiological variables directly from fMRI data from individuals across a wide range of the adult lifespan. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14453v1-abstract-full').style.display = 'none'; document.getElementById('2408.14453v1-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/2408.08422">arXiv:2408.08422</a> <span> [<a href="https://arxiv.org/pdf/2408.08422">pdf</a>, <a href="https://arxiv.org/format/2408.08422">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Assessing and Enhancing Large Language Models in Rare Disease Question-answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guanchu Wang</a>, <a href="/search/cs?searchtype=author&query=Ran%2C+J">Junhao Ran</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+R">Ruixiang Tang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chia-Yuan Chang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chia-Yuan Chang</a>, <a href="/search/cs?searchtype=author&query=Chuang%2C+Y">Yu-Neng Chuang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zirui Liu</a>, <a href="/search/cs?searchtype=author&query=Braverman%2C+V">Vladimir Braverman</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhandong Liu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xia 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="2408.08422v1-abstract-short" style="display: inline;"> Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08422v1-abstract-full').style.display = 'inline'; document.getElementById('2408.08422v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08422v1-abstract-full" style="display: none;"> Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases. Specifically, we collected 1360 high-quality question-answer pairs within the ReDis-QA dataset, covering 205 rare diseases. Additionally, we annotated meta-data for each question, facilitating the extraction of subsets specific to any given disease and its property. Based on the ReDis-QA dataset, we benchmarked several open-source LLMs, revealing that diagnosing rare diseases remains a significant challenge for these models. To facilitate retrieval augmentation generation for rare disease diagnosis, we collect the first rare diseases corpus (ReCOP), sourced from the National Organization for Rare Disorders (NORD) database. Specifically, we split the report of each rare disease into multiple chunks, each representing a different property of the disease, including their overview, symptoms, causes, effects, related disorders, diagnosis, and standard therapies. This structure ensures that the information within each chunk aligns consistently with a question. Experiment results demonstrate that ReCOP can effectively improve the accuracy of LLMs on the ReDis-QA dataset by an average of 8%. Moreover, it significantly guides LLMs to generate trustworthy answers and explanations that can be traced back to existing literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08422v1-abstract-full').style.display = 'none'; document.getElementById('2408.08422v1-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/2408.06381">arXiv:2408.06381</a> <span> [<a href="https://arxiv.org/pdf/2408.06381">pdf</a>, <a href="https://arxiv.org/format/2408.06381">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/cs?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/cs?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.06381v1-abstract-short" style="display: inline;"> Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06381v1-abstract-full').style.display = 'inline'; document.getElementById('2408.06381v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.06381v1-abstract-full" style="display: none;"> Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely used state-of-the-art (SOTA) cell nuclei foundation models (Cellpose, StarDist, and CellViT). Specifically, we created a highly diverse evaluation dataset consisting of 2,542 kidney whole slide images (WSIs) collected from both human and rodent sources, encompassing various tissue types, sizes, and staining methods. To our knowledge, this is the largest-scale evaluation of its kind to date. Our quantitative analysis of the prediction distribution reveals a persistent performance gap in kidney pathology. Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology. However, none of the foundation models are perfect; a performance gap remains in general nuclei segmentation for kidney pathology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06381v1-abstract-full').style.display = 'none'; document.getElementById('2408.06381v1-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 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/2407.21118">arXiv:2407.21118</a> <span> [<a href="https://arxiv.org/pdf/2407.21118">pdf</a>, <a href="https://arxiv.org/format/2407.21118">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Palu: Compressing KV-Cache with Low-Rank Projection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chi-Chih Chang</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+W">Wei-Cheng Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+C">Chien-Yu Lin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chong-Yan Chen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yu-Fang Hu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pei-Shuo Wang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+N">Ning-Chi Huang</a>, <a href="/search/cs?searchtype=author&query=Ceze%2C+L">Luis Ceze</a>, <a href="/search/cs?searchtype=author&query=Abdelfattah%2C+M+S">Mohamed S. Abdelfattah</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+K">Kai-Chiang Wu</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="2407.21118v2-abstract-short" style="display: inline;"> Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21118v2-abstract-full').style.display = 'inline'; document.getElementById('2407.21118v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.21118v2-abstract-full" style="display: none;"> Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, compression rate, and efficiency, Palu further encompasses (1) a medium-grained low-rank decomposition scheme, (2) an efficient rank search algorithm, (3) low-rank-aware quantization compatibility enhancements, and (4) optimized GPU kernels with operators fusion. Extensive experiments with popular LLMs show that Palu compresses KV-Cache by 50% while maintaining strong accuracy and delivering up to 1.89x on the RoPE-based attention module. When combined with quantization, Palu's inherent quantization-friendly design yields small to negligible extra accuracy degradation while saving additional memory than quantization-only methods and achieving up to 2.91x speedup for the RoPE-based attention. Moreover, it maintains comparable or even better accuracy (up to 1.19 lower perplexity) compared to quantization-only methods. These results demonstrate Palu's superior capability to effectively address the efficiency and memory challenges of LLM inference posed by KV-Cache. Our code is publicly available at: https://github.com/shadowpa0327/Palu <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21118v2-abstract-full').style.display = 'none'; document.getElementById('2407.21118v2-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> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.18269">arXiv:2407.18269</a> <span> [<a href="https://arxiv.org/pdf/2407.18269">pdf</a>, <a href="https://arxiv.org/format/2407.18269">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chen-Chia Chang</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yikang Shen</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+S">Shaoze Fan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shun Zhang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+N">Ningyuan Cao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yiran Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xin 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="2407.18269v2-abstract-short" style="display: inline;"> In the realm of electronic and electrical engineering, automation of analog circuit is increasingly vital given the complexity and customized requirements of modern applications. However, existing methods only develop search-based algorithms that require many simulation iterations to design a custom circuit topology, which is usually a time-consuming process. To this end, we introduce LaMAGIC, a p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18269v2-abstract-full').style.display = 'inline'; document.getElementById('2407.18269v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.18269v2-abstract-full" style="display: none;"> In the realm of electronic and electrical engineering, automation of analog circuit is increasingly vital given the complexity and customized requirements of modern applications. However, existing methods only develop search-based algorithms that require many simulation iterations to design a custom circuit topology, which is usually a time-consuming process. To this end, we introduce LaMAGIC, a pioneering language model-based topology generation model that leverages supervised finetuning for automated analog circuit design. LaMAGIC can efficiently generate an optimized circuit design from the custom specification in a single pass. Our approach involves a meticulous development and analysis of various input and output formulations for circuit. These formulations can ensure canonical representations of circuits and align with the autoregressive nature of LMs to effectively addressing the challenges of representing analog circuits as graphs. The experimental results show that LaMAGIC achieves a success rate of up to 96\% under a strict tolerance of 0.01. We also examine the scalability and adaptability of LaMAGIC, specifically testing its performance on more complex circuits. Our findings reveal the enhanced effectiveness of our adjacency matrix-based circuit formulation with floating-point input, suggesting its suitability for handling intricate circuit designs. This research not only demonstrates the potential of language models in graph generation, but also builds a foundational framework for future explorations in automated analog circuit design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18269v2-abstract-full').style.display = 'none'; document.getElementById('2407.18269v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6253-6262 https://proceedings.mlr.press/v235/chang24c.html</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6253-6262, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15524">arXiv:2407.15524</a> <span> [<a href="https://arxiv.org/pdf/2407.15524">pdf</a>, <a href="https://arxiv.org/format/2407.15524">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"> Fast Preemption: Forward-Backward Cascade Learning for Efficient and Transferable Proactive Adversarial Defense </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hanrui Wang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching-Chun Chang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+C">Chun-Shien Lu</a>, <a href="/search/cs?searchtype=author&query=Echizen%2C+I">Isao Echizen</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="2407.15524v4-abstract-short" style="display: inline;"> Deep learning technology has brought convenience and advanced developments but has become untrustworthy due to its sensitivity to adversarial attacks. Attackers may utilize this sensitivity to manipulate predictions. To defend against such attacks, existing anti-adversarial methods typically counteract adversarial perturbations post-attack, while we have devised a proactive strategy that preempts… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15524v4-abstract-full').style.display = 'inline'; document.getElementById('2407.15524v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15524v4-abstract-full" style="display: none;"> Deep learning technology has brought convenience and advanced developments but has become untrustworthy due to its sensitivity to adversarial attacks. Attackers may utilize this sensitivity to manipulate predictions. To defend against such attacks, existing anti-adversarial methods typically counteract adversarial perturbations post-attack, while we have devised a proactive strategy that preempts by safeguarding media upfront, effectively neutralizing potential adversarial effects before the third-party attacks occur. This strategy, dubbed Fast Preemption, provides an efficient transferable preemptive defense by using different models for labeling inputs and learning crucial features. A forward-backward cascade learning algorithm is used to compute protective perturbations, starting with forward propagation optimization to achieve rapid convergence, followed by iterative backward propagation learning to alleviate overfitting. This strategy offers state-of-the-art transferability and protection across various systems. With the running of only three steps, our Fast Preemption framework outperforms benchmark training-time, test-time, and preemptive adversarial defenses. We have also devised the first, to our knowledge, effective white-box adaptive reversion attack and demonstrate that the protection added by our defense strategy is irreversible unless the backbone model, algorithm, and settings are fully compromised. This work provides a new direction to developing proactive defenses against adversarial attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15524v4-abstract-full').style.display = 'none'; document.getElementById('2407.15524v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.12810">arXiv:2407.12810</a> <span> [<a href="https://arxiv.org/pdf/2407.12810">pdf</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"> A Study on the Situation of Connected Car Patent Portfolios </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+A+C+H">Abel C. H. Chen</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chia-Shen Chang</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="2407.12810v1-abstract-short" style="display: inline;"> In recent years, the countries of the world have drafted the specifications of connected cars; for instance, the Security Credential Management System (SCMS) has been proposed by United States Department of Transportation (USDOT), and the Cooperative Intelligent Transportation System (C-ITS) Credential Management System (CCMS) has been proposed by European Union (EU). Therefore, several companies… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12810v1-abstract-full').style.display = 'inline'; document.getElementById('2407.12810v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12810v1-abstract-full" style="display: none;"> In recent years, the countries of the world have drafted the specifications of connected cars; for instance, the Security Credential Management System (SCMS) has been proposed by United States Department of Transportation (USDOT), and the Cooperative Intelligent Transportation System (C-ITS) Credential Management System (CCMS) has been proposed by European Union (EU). Therefore, several companies have developed the technology and productions of connected cars based on specifications, and connected car patent portfolios have been proactively performed. Therefore, this study uses Patent Search System (PSS) to find and analyze the contents of patents for obtaining the innovation reports of connected cars according to patents. This study considers the single-factor and two-factors to analyze the relationships of annuals, major technology leaders, major market leaders, and major technology and applications for exploring the patent portfolios of technology leaders and market leaders in connected cars. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12810v1-abstract-full').style.display = 'none'; document.getElementById('2407.12810v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">in Chinese language</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.12254">arXiv:2407.12254</a> <span> [<a href="https://arxiv.org/pdf/2407.12254">pdf</a>, <a href="https://arxiv.org/format/2407.12254">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> COKE: Causal Discovery with Chronological Order and Expert Knowledge in High Proportion of Missing Manufacturing Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ou%2C+T">Ting-Yun Ou</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Ching Chang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+W">Wen-Chih Peng</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="2407.12254v2-abstract-short" style="display: inline;"> Understanding causal relationships between machines is crucial for fault diagnosis and optimization in manufacturing processes. Real-world datasets frequently exhibit up to 90% missing data and high dimensionality from hundreds of sensors. These datasets also include domain-specific expert knowledge and chronological order information, reflecting the recording order across different machines, whic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12254v2-abstract-full').style.display = 'inline'; document.getElementById('2407.12254v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12254v2-abstract-full" style="display: none;"> Understanding causal relationships between machines is crucial for fault diagnosis and optimization in manufacturing processes. Real-world datasets frequently exhibit up to 90% missing data and high dimensionality from hundreds of sensors. These datasets also include domain-specific expert knowledge and chronological order information, reflecting the recording order across different machines, which is pivotal for discerning causal relationships within the manufacturing data. However, previous methods for handling missing data in scenarios akin to real-world conditions have not been able to effectively utilize expert knowledge. Conversely, prior methods that can incorporate expert knowledge struggle with datasets that exhibit missing values. Therefore, we propose COKE to construct causal graphs in manufacturing datasets by leveraging expert knowledge and chronological order among sensors without imputing missing data. Utilizing the characteristics of the recipe, we maximize the use of samples with missing values, derive embeddings from intersections with an initial graph that incorporates expert knowledge and chronological order, and create a sensor ordering graph. The graph-generating process has been optimized by an actor-critic architecture to obtain a final graph that has a maximum reward. Experimental evaluations in diverse settings of sensor quantities and missing proportions demonstrate that our approach compared with the benchmark methods shows an average improvement of 39.9% in the F1-score. Moreover, the F1-score improvement can reach 62.6% when considering the configuration similar to real-world datasets, and 85.0% in real-world semiconductor datasets. The source code is available at https://github.com/OuTingYun/COKE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12254v2-abstract-full').style.display = 'none'; document.getElementById('2407.12254v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">This paper has been accepted by the ACM International Conference on Information and Knowledge Management (CIKM) 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/2407.05643">arXiv:2407.05643</a> <span> [<a href="https://arxiv.org/pdf/2407.05643">pdf</a>, <a href="https://arxiv.org/format/2407.05643">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Spatial Non-Stationary Dual-Wideband Channel Estimation for XL-MIMO Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+A">Anzheng Tang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jun-Bo Wang</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+Y">Yijin Pan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chuanwen Chang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yijian Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+H">Hongkang Yu</a>, <a href="/search/cs?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</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="2407.05643v1-abstract-short" style="display: inline;"> In this paper, we investigate the channel estimation problem for extremely large-scale multi-input and multi-output (XL-MIMO) systems, considering the spherical wavefront effect, spatially non-stationary (SnS) property, and dual-wideband effects. To accurately characterize the XL-MIMO channel, we first derive a novel spatial-and-frequency-domain channel model for XL-MIMO systems and carefully exam… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05643v1-abstract-full').style.display = 'inline'; document.getElementById('2407.05643v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05643v1-abstract-full" style="display: none;"> In this paper, we investigate the channel estimation problem for extremely large-scale multi-input and multi-output (XL-MIMO) systems, considering the spherical wavefront effect, spatially non-stationary (SnS) property, and dual-wideband effects. To accurately characterize the XL-MIMO channel, we first derive a novel spatial-and-frequency-domain channel model for XL-MIMO systems and carefully examine the channel characteristics in the angular-and-delay domain. Based on the obtained channel representation, we formulate XL-MIMO channel estimation as a Bayesian inference problem. To fully exploit the clustered sparsity of angular-and-delay channels and capture the inter-antenna and inter-subcarrier correlations, a Markov random field (MRF)-based hierarchical prior model is adopted. Meanwhile, to facilitate efficient channel reconstruction, we propose a sparse Bayesian learning (SBL) algorithm based on approximate message passing (AMP) with a unitary transformation. Tailored to the MRF-based hierarchical prior model, the message passing equations are reformulated using structured variational inference, belief propagation, and mean-field rules. Finally, simulation results validate the convergence and superiority of the proposed algorithm over existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05643v1-abstract-full').style.display = 'none'; document.getElementById('2407.05643v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">This paper has been submitted to IEEE journal for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00870">arXiv:2407.00870</a> <span> [<a href="https://arxiv.org/pdf/2407.00870">pdf</a>, <a href="https://arxiv.org/format/2407.00870">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Louie%2C+R">Ryan Louie</a>, <a href="/search/cs?searchtype=author&query=Nandi%2C+A">Ananjan Nandi</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+W">William Fang</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Cheng Chang</a>, <a href="/search/cs?searchtype=author&query=Brunskill%2C+E">Emma Brunskill</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Diyi 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="2407.00870v2-abstract-short" style="display: inline;"> Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious. To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00870v2-abstract-full').style.display = 'inline'; document.getElementById('2407.00870v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00870v2-abstract-full" style="display: none;"> Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious. To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLM-prompted roleplay. We apply this pipeline to enable senior mental health supporters to create customized AI patients for simulated practice partners for novice counselors. After uncovering issues in GPT-4 simulations not adhering to expert-defined principles, we also introduce a novel principle-adherence prompting pipeline which shows 30% improvements in response quality and principle following for the downstream task. Via a user study with 25 counseling experts, we demonstrate that the pipeline makes it easy and effective to create AI patients that more faithfully resemble real patients, as judged by creators and third-party counselors. See our project website at https://roleplay-doh.github.io/ for code and data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00870v2-abstract-full').style.display = 'none'; document.getElementById('2407.00870v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">34 pages, 24 figures, 11 Tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19568">arXiv:2406.19568</a> <span> [<a href="https://arxiv.org/pdf/2406.19568">pdf</a>, <a href="https://arxiv.org/format/2406.19568">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> What Matters in Detecting AI-Generated Videos like Sora? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chirui Chang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhengzhe Liu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+X">Xiaoyang Lyu</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+X">Xiaojuan Qi</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="2406.19568v1-abstract-short" style="display: inline;"> Recent advancements in diffusion-based video generation have showcased remarkable results, yet the gap between synthetic and real-world videos remains under-explored. In this study, we examine this gap from three fundamental perspectives: appearance, motion, and geometry, comparing real-world videos with those generated by a state-of-the-art AI model, Stable Video Diffusion. To achieve this, we tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19568v1-abstract-full').style.display = 'inline'; document.getElementById('2406.19568v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19568v1-abstract-full" style="display: none;"> Recent advancements in diffusion-based video generation have showcased remarkable results, yet the gap between synthetic and real-world videos remains under-explored. In this study, we examine this gap from three fundamental perspectives: appearance, motion, and geometry, comparing real-world videos with those generated by a state-of-the-art AI model, Stable Video Diffusion. To achieve this, we train three classifiers using 3D convolutional networks, each targeting distinct aspects: vision foundation model features for appearance, optical flow for motion, and monocular depth for geometry. Each classifier exhibits strong performance in fake video detection, both qualitatively and quantitatively. This indicates that AI-generated videos are still easily detectable, and a significant gap between real and fake videos persists. Furthermore, utilizing the Grad-CAM, we pinpoint systematic failures of AI-generated videos in appearance, motion, and geometry. Finally, we propose an Ensemble-of-Experts model that integrates appearance, optical flow, and depth information for fake video detection, resulting in enhanced robustness and generalization ability. Our model is capable of detecting videos generated by Sora with high accuracy, even without exposure to any Sora videos during training. This suggests that the gap between real and fake videos can be generalized across various video generative models. Project page: https://justin-crchang.github.io/3DCNNDetection.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19568v1-abstract-full').style.display = 'none'; document.getElementById('2406.19568v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.14045">arXiv:2406.14045</a> <span> [<a href="https://arxiv.org/pdf/2406.14045">pdf</a>, <a href="https://arxiv.org/format/2406.14045">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Understanding Different Design Choices in Training Large Time Series Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chuang%2C+Y">Yu-Neng Chuang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Songchen Li</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+J">Jiayi Yuan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guanchu Wang</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+K">Kwei-Herng Lai</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Leisheng Yu</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+S">Sirui Ding</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chia-Yuan Chang</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Q">Qiaoyu Tan</a>, <a href="/search/cs?searchtype=author&query=Zha%2C+D">Daochen Zha</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xia 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="2406.14045v1-abstract-short" style="display: inline;"> Inspired by Large Language Models (LLMs), Time Series Forecasting (TSF), a long-standing task in time series analysis, is undergoing a transition towards Large Time Series Models (LTSMs), aiming to train universal transformer-based models for TSF. However, training LTSMs on heterogeneous time series data poses unique challenges, including diverse frequencies, dimensions, and patterns across datase… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14045v1-abstract-full').style.display = 'inline'; document.getElementById('2406.14045v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.14045v1-abstract-full" style="display: none;"> Inspired by Large Language Models (LLMs), Time Series Forecasting (TSF), a long-standing task in time series analysis, is undergoing a transition towards Large Time Series Models (LTSMs), aiming to train universal transformer-based models for TSF. However, training LTSMs on heterogeneous time series data poses unique challenges, including diverse frequencies, dimensions, and patterns across datasets. Recent endeavors have studied and evaluated various design choices aimed at enhancing LTSM training and generalization capabilities, spanning pre-processing techniques, model configurations, and dataset configurations. In this work, we comprehensively analyze these design choices and aim to identify the best practices for training LTSM. Moreover, we propose \emph{time series prompt}, a novel statistical prompting strategy tailored to time series data. Furthermore, based on the observations in our analysis, we introduce \texttt{LTSM-bundle}, which bundles the best design choices we have identified. Empirical results demonstrate that \texttt{LTSM-bundle} achieves superior zero-shot and few-shot performances compared to state-of-the-art LSTMs and traditional TSF methods on benchmark datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14045v1-abstract-full').style.display = 'none'; document.getElementById('2406.14045v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11313">arXiv:2406.11313</a> <span> [<a href="https://arxiv.org/pdf/2406.11313">pdf</a>, <a href="https://arxiv.org/format/2406.11313">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"> Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+Y">Yecheol Kim</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J">Junho Lee</a>, <a href="/search/cs?searchtype=author&query=Park%2C+C">Changsoo Park</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+H+w">Hyoung won Kim</a>, <a href="/search/cs?searchtype=author&query=Lim%2C+I">Inho Lim</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Christopher Chang</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+J+W">Jun Won Choi</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="2406.11313v1-abstract-short" style="display: inline;"> 3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can adversely affect detection performance. Semi-Supervised Domain Adaptation (SSDA) aims to mitigate these challenges by transferring knowledge from a source domain, abu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11313v1-abstract-full').style.display = 'inline'; document.getElementById('2406.11313v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11313v1-abstract-full" style="display: none;"> 3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can adversely affect detection performance. Semi-Supervised Domain Adaptation (SSDA) aims to mitigate these challenges by transferring knowledge from a source domain, abundant in labeled data, to a target domain where labels are scarce. This paper presents a new SSDA method referred to as Target-Oriented Domain Augmentation (TODA) specifically tailored for LiDAR-based 3D object detection. TODA efficiently utilizes all available data, including labeled data in the source domain, and both labeled data and unlabeled data in the target domain to enhance domain adaptation performance. TODA consists of two stages: TargetMix and AdvMix. TargetMix employs mixing augmentation accounting for LiDAR sensor characteristics to facilitate feature alignment between the source-domain and target-domain. AdvMix applies point-wise adversarial augmentation with mixing augmentation, which perturbs the unlabeled data to align the features within both labeled and unlabeled data in the target domain. Our experiments conducted on the challenging domain adaptation tasks demonstrate that TODA outperforms existing domain adaptation techniques designed for 3D object detection by significant margins. The code is available at: https://github.com/rasd3/TODA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11313v1-abstract-full').style.display = 'none'; document.getElementById('2406.11313v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE Transactions on Intelligent Vehicles (T-IV). The code is available at: https://github.com/rasd3/TODA</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Chang%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Chang%2C+C&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