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 279 results for author: <span class="mathjax">Tran, N</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=Tran%2C+N">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="Tran, N"> </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=Tran%2C+N&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="Tran, N"> <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=Tran%2C+N&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </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/2502.08355">arXiv:2502.08355</a> <span> [<a href="https://arxiv.org/pdf/2502.08355">pdf</a>, <a href="https://arxiv.org/format/2502.08355">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"> Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baldi%2C+T">Tommaso Baldi</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+J">Javier Campos</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+O">Olivia Weng</a>, <a href="/search/cs?searchtype=author&query=Geniesse%2C+C">Caleb Geniesse</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Kastner%2C+R">Ryan Kastner</a>, <a href="/search/cs?searchtype=author&query=Biondi%2C+A">Alessandro Biondi</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="2502.08355v1-abstract-short" style="display: inline;"> In this paper, we propose a method to perform empirical analysis of the loss landscape of machine learning (ML) models. The method is applied to two ML models for scientific sensing, which necessitates quantization to be deployed and are subject to noise and perturbations due to experimental conditions. Our method allows assessing the robustness of ML models to such effects as a function of quanti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08355v1-abstract-full').style.display = 'inline'; document.getElementById('2502.08355v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08355v1-abstract-full" style="display: none;"> In this paper, we propose a method to perform empirical analysis of the loss landscape of machine learning (ML) models. The method is applied to two ML models for scientific sensing, which necessitates quantization to be deployed and are subject to noise and perturbations due to experimental conditions. Our method allows assessing the robustness of ML models to such effects as a function of quantization precision and under different regularization techniques -- two crucial concerns that remained underexplored so far. By investigating the interplay between performance, efficiency, and robustness by means of loss landscape analysis, we both established a strong correlation between gently-shaped landscapes and robustness to input and weight perturbations and observed other intriguing and non-obvious phenomena. Our method allows a systematic exploration of such trade-offs a priori, i.e., without training and testing multiple models, leading to more efficient development workflows. This work also highlights the importance of incorporating robustness into the Pareto optimization of ML models, enabling more reliable and adaptive scientific sensing systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08355v1-abstract-full').style.display = 'none'; document.getElementById('2502.08355v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </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">Under review</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-CONF-25-0045-CSAID </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.14764">arXiv:2501.14764</a> <span> [<a href="https://arxiv.org/pdf/2501.14764">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Battery-free, stretchable, and autonomous smart packaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Douaki%2C+A">Ali Douaki</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+M">Mukhtar Ahmed</a>, <a href="/search/cs?searchtype=author&query=Longo%2C+E">Edoardo Longo</a>, <a href="/search/cs?searchtype=author&query=Windisch%2C+G">Giulia Windisch</a>, <a href="/search/cs?searchtype=author&query=Riaz%2C+R">Raheel Riaz</a>, <a href="/search/cs?searchtype=author&query=Inam%2C+S">Sarwar Inam</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T+N">Thi Nga Tran</a>, <a href="/search/cs?searchtype=author&query=Papadopoulou%2C+E+L">Evie L. Papadopoulou</a>, <a href="/search/cs?searchtype=author&query=Athanassiou%2C+A">Athanassia Athanassiou</a>, <a href="/search/cs?searchtype=author&query=Boselli%2C+E">Emanuele Boselli</a>, <a href="/search/cs?searchtype=author&query=Petti%2C+L">Luisa Petti</a>, <a href="/search/cs?searchtype=author&query=Lugli%2C+P">Paolo Lugli</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="2501.14764v1-abstract-short" style="display: inline;"> In the food industry, innovative packaging solutions are increasingly important for reducing food waste and for contributing to global sustainability efforts. However, current food packaging is generally passive and unable to adapt to changes in the food environment in real-time. To address this, we have developed a battery-less and autonomous smart packaging system that wirelessly powers closed-l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14764v1-abstract-full').style.display = 'inline'; document.getElementById('2501.14764v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14764v1-abstract-full" style="display: none;"> In the food industry, innovative packaging solutions are increasingly important for reducing food waste and for contributing to global sustainability efforts. However, current food packaging is generally passive and unable to adapt to changes in the food environment in real-time. To address this, we have developed a battery-less and autonomous smart packaging system that wirelessly powers closed-loop sensing and release of active compounds. This system integrates a gas sensor for real-time food monitoring, a Near-Field Communication (NFC) antenna, and a controlled release of active compounds to prevent quality deterioration in the complex food environment. We have demonstrated the ability of the developed smart packaging system, to continuously monitor the freshness of fish products and to trigger the release of active compounds when the food starts to spoil. The system was able to extend the shelf-life of the food product up to 14 days, due to the controlled release of antioxidant and antibacterial compounds. Our system could pave the way towards an Internet of Things solution that addresses protection, active prevention of food spoilage and sustainability, facing all the current challenges of the food packaging industry. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14764v1-abstract-full').style.display = 'none'; document.getElementById('2501.14764v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.14663">arXiv:2501.14663</a> <span> [<a href="https://arxiv.org/pdf/2501.14663">pdf</a>, <a href="https://arxiv.org/format/2501.14663">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> End-to-end workflow for machine learning-based qubit readout with QICK and hls4ml </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Du%2C+B">Botao Du</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+J">Javier Campos</a>, <a href="/search/cs?searchtype=author&query=Boltasseva%2C+A">Alexandra Boltasseva</a>, <a href="/search/cs?searchtype=author&query=Dixit%2C+A+V">Akash V. Dixit</a>, <a href="/search/cs?searchtype=author&query=Fahim%2C+F">Farah Fahim</a>, <a href="/search/cs?searchtype=author&query=Kudyshev%2C+Z">Zhaxylyk Kudyshev</a>, <a href="/search/cs?searchtype=author&query=Lopez%2C+S">Santiago Lopez</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+R">Ruichao Ma</a>, <a href="/search/cs?searchtype=author&query=Perdue%2C+G+N">Gabriel N. Perdue</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Yesilyurt%2C+O">Omer Yesilyurt</a>, <a href="/search/cs?searchtype=author&query=Bowring%2C+D">Daniel Bowring</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="2501.14663v1-abstract-short" style="display: inline;"> We present an end-to-end workflow for superconducting qubit readout that embeds co-designed Neural Networks (NNs) into the Quantum Instrumentation Control Kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx RFSoC FPGAs, we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14663v1-abstract-full').style.display = 'inline'; document.getElementById('2501.14663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14663v1-abstract-full" style="display: none;"> We present an end-to-end workflow for superconducting qubit readout that embeds co-designed Neural Networks (NNs) into the Quantum Instrumentation Control Kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx RFSoC FPGAs, we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python APIs. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32ns and less than 16% FPGA look-up table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14663v1-abstract-full').style.display = 'none'; document.getElementById('2501.14663v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-24-0925-ETD-PPD </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.05520">arXiv:2501.05520</a> <span> [<a href="https://arxiv.org/pdf/2501.05520">pdf</a>, <a href="https://arxiv.org/format/2501.05520">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Track reconstruction as a service for collider physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Haoran Zhao</a>, <a href="/search/cs?searchtype=author&query=Chou%2C+Y">Yuan-Tang Chou</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yao Yao</a>, <a href="/search/cs?searchtype=author&query=Ju%2C+X">Xiangyang Ju</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+Y">Yongbin Feng</a>, <a href="/search/cs?searchtype=author&query=McCormack%2C+W+P">William Patrick McCormack</a>, <a href="/search/cs?searchtype=author&query=Cochran-Branson%2C+M">Miles Cochran-Branson</a>, <a href="/search/cs?searchtype=author&query=Schulte%2C+J">Jan-Frederik Schulte</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Miaoyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/cs?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</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="2501.05520v2-abstract-short" style="display: inline;"> Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05520v2-abstract-full').style.display = 'inline'; document.getElementById('2501.05520v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05520v2-abstract-full" style="display: none;"> Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain in fully harnessing the computational capacity of coprocessors in a scalable and non-disruptive manner. This paper proposes an inference-as-a-service approach for particle tracking in high energy physics experiments. To evaluate the efficacy of this approach, two distinct tracking algorithms are tested: Patatrack, a rule-based algorithm, and Exa$.$TrkX, a machine learning-based algorithm. The as-a-service implementations show enhanced GPU utilization and can process requests from multiple CPU cores concurrently without increasing per-request latency. The impact of data transfer is minimal and insignificant compared to running on local coprocessors. This approach greatly improves the computational efficiency of charged particle tracking, providing a solution to the computing challenges anticipated in the High-Luminosity LHC era. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05520v2-abstract-full').style.display = 'none'; document.getElementById('2501.05520v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </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, 8 figures, submitted to JINST</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-25-0004-CSAID-PPD </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.05515">arXiv:2501.05515</a> <span> [<a href="https://arxiv.org/pdf/2501.05515">pdf</a>, <a href="https://arxiv.org/format/2501.05515">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="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> </div> </div> <p class="title is-5 mathjax"> Neural Architecture Codesign for Fast Physics Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weitz%2C+J">Jason Weitz</a>, <a href="/search/cs?searchtype=author&query=Demler%2C+D">Dmitri Demler</a>, <a href="/search/cs?searchtype=author&query=McDermott%2C+L">Luke McDermott</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</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="2501.05515v1-abstract-short" style="display: inline;"> We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method employs neural architecture search and network compression in a two-stage approach to discover hardware efficient models. This approach consists of a global search stage that explores a wide range of architectures while cons… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05515v1-abstract-full').style.display = 'inline'; document.getElementById('2501.05515v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05515v1-abstract-full" style="display: none;"> We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method employs neural architecture search and network compression in a two-stage approach to discover hardware efficient models. This approach consists of a global search stage that explores a wide range of architectures while considering hardware constraints, followed by a local search stage that fine-tunes and compresses the most promising candidates. We exceed performance on various tasks and show further speedup through model compression techniques such as quantization-aware-training and neural network pruning. We synthesize the optimal models to high level synthesis code for FPGA deployment with the hls4ml library. Additionally, our hierarchical search space provides greater flexibility in optimization, which can easily extend to other tasks and domains. We demonstrate this with two case studies: Bragg peak finding in materials science and jet classification in high energy physics, achieving models with improved accuracy, smaller latencies, or reduced resource utilization relative to the baseline models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05515v1-abstract-full').style.display = 'none'; document.getElementById('2501.05515v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </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, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-24-0945-CSAID </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.04845">arXiv:2501.04845</a> <span> [<a href="https://arxiv.org/pdf/2501.04845">pdf</a>, <a href="https://arxiv.org/ps/2501.04845">ps</a>, <a href="https://arxiv.org/format/2501.04845">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Nuclear Experiment">nucl-ex</span> </div> </div> <p class="title is-5 mathjax"> Intelligent experiments through real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and future EIC detectors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kvapil%2C+J">J. Kvapil</a>, <a href="/search/cs?searchtype=author&query=Borca-Tasciuc%2C+G">G. Borca-Tasciuc</a>, <a href="/search/cs?searchtype=author&query=Bossi%2C+H">H. Bossi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">K. Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Y. Chen</a>, <a href="/search/cs?searchtype=author&query=Morales%2C+Y+C">Y. Corrales Morales</a>, <a href="/search/cs?searchtype=author&query=Da+Costa%2C+H">H. Da Costa</a>, <a href="/search/cs?searchtype=author&query=Da+Silva%2C+C">C. Da Silva</a>, <a href="/search/cs?searchtype=author&query=Dean%2C+C">C. Dean</a>, <a href="/search/cs?searchtype=author&query=Durham%2C+J">J. Durham</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+S">S. Fu</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+C">C. Hao</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">P. Harris</a>, <a href="/search/cs?searchtype=author&query=Hen%2C+O">O. Hen</a>, <a href="/search/cs?searchtype=author&query=Jheng%2C+H">H. Jheng</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+Y">Y. Lee</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">P. Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">X. Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Y. Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M+X">M. X. Liu</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">V. Loncar</a>, <a href="/search/cs?searchtype=author&query=Mitrevski%2C+J+P">J. P. Mitrevski</a>, <a href="/search/cs?searchtype=author&query=Olvera%2C+A">A. Olvera</a>, <a href="/search/cs?searchtype=author&query=Purschke%2C+M+L">M. L. Purschke</a>, <a href="/search/cs?searchtype=author&query=Renck%2C+J+S">J. S. Renck</a> , et al. (8 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="2501.04845v1-abstract-short" style="display: inline;"> This R\&D project, initiated by the DOE Nuclear Physics AI-Machine Learning initiative in 2022, leverages AI to address data processing challenges in high-energy nuclear experiments (RHIC, LHC, and future EIC). Our focus is on developing a demonstrator for real-time processing of high-rate data streams from sPHENIX experiment tracking detectors. The limitations of a 15 kHz maximum trigger rate imp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04845v1-abstract-full').style.display = 'inline'; document.getElementById('2501.04845v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.04845v1-abstract-full" style="display: none;"> This R\&D project, initiated by the DOE Nuclear Physics AI-Machine Learning initiative in 2022, leverages AI to address data processing challenges in high-energy nuclear experiments (RHIC, LHC, and future EIC). Our focus is on developing a demonstrator for real-time processing of high-rate data streams from sPHENIX experiment tracking detectors. The limitations of a 15 kHz maximum trigger rate imposed by the calorimeters can be negated by intelligent use of streaming technology in the tracking system. The approach efficiently identifies low momentum rare heavy flavor events in high-rate p+p collisions (3MHz), using Graph Neural Network (GNN) and High Level Synthesis for Machine Learning (hls4ml). Success at sPHENIX promises immediate benefits, minimizing resources and accelerating the heavy-flavor measurements. The approach is transferable to other fields. For the EIC, we develop a DIS-electron tagger using Artificial Intelligence - Machine Learning (AI-ML) algorithms for real-time identification, showcasing the transformative potential of AI and FPGA technologies in high-energy nuclear and particle experiments real-time data processing pipelines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04845v1-abstract-full').style.display = 'none'; document.getElementById('2501.04845v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </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 for 42nd International Conference on High Energy Physics (ICHEP2024), 18-24 July 2024, Prague, Czech Republic</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> LA-UR-24-30394 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.05683">arXiv:2412.05683</a> <span> [<a href="https://arxiv.org/pdf/2412.05683">pdf</a>, <a href="https://arxiv.org/format/2412.05683">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Research Methodology and Academic Publishing: A Structured Framework for Quality and Integrity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Piran%2C+M+J">Md. Jalil Piran</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</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="2412.05683v2-abstract-short" style="display: inline;"> Following a brief introduction to research, research processes, research types, papers, reviews, and evaluations, this paper presents a structured framework for addressing inconsistencies in research methodology, technical writing, quality assessment, and publication standards across academic disciplines. Using a four-dimensional evaluation model that focuses on 1) technical content, 2) structural… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05683v2-abstract-full').style.display = 'inline'; document.getElementById('2412.05683v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05683v2-abstract-full" style="display: none;"> Following a brief introduction to research, research processes, research types, papers, reviews, and evaluations, this paper presents a structured framework for addressing inconsistencies in research methodology, technical writing, quality assessment, and publication standards across academic disciplines. Using a four-dimensional evaluation model that focuses on 1) technical content, 2) structural coherence, 3) writing precision, and 4) ethical integrity, this framework not only standardizes review and publication processes but also serves as a practical guide for authors in preparing high-quality manuscripts. Each of these four dimensions cannot be compromised for the sake of another. Following that, we discuss the components of a research paper adhering to the four-dimensional evaluation model in detail by providing guidelines and principles. By aligning manuscripts with journal standards, reducing review bias, and enhancing transparency, the framework contributes to more reliable and reproducible research results. Moreover, by strengthening cross-disciplinary credibility, improving publication consistency, and fostering public trust in academic literature, this initiative is expected to positively influence both research quality and scholarly publishing's reputation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05683v2-abstract-full').style.display = 'none'; document.getElementById('2412.05683v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03620">arXiv:2412.03620</a> <span> [<a href="https://arxiv.org/pdf/2412.03620">pdf</a>, <a href="https://arxiv.org/ps/2412.03620">ps</a>, <a href="https://arxiv.org/format/2412.03620">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div 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/10.3389/fdata.2023.1284511">10.3389/fdata.2023.1284511 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Recommender Systems for Sustainability: Overview and Research Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Felfernig%2C+A">Alexander Felfernig</a>, <a href="/search/cs?searchtype=author&query=Wundara%2C+M">Manfred Wundara</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T+N+T">Thi Ngoc Trang Tran</a>, <a href="/search/cs?searchtype=author&query=Polat-Erdeniz%2C+S">Seda Polat-Erdeniz</a>, <a href="/search/cs?searchtype=author&query=Lubos%2C+S">Sebastian Lubos</a>, <a href="/search/cs?searchtype=author&query=El-Mansi%2C+M">Merfat El-Mansi</a>, <a href="/search/cs?searchtype=author&query=Garber%2C+D">Damian Garber</a>, <a href="/search/cs?searchtype=author&query=Le%2C+V">Viet-Man Le</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="2412.03620v1-abstract-short" style="display: inline;"> Sustainability development goals (SDGs) are regarded as a universal call to action with the overall objectives of planet protection, ending of poverty, and ensuring peace and prosperity for all people. In order to achieve these objectives, different AI technologies play a major role. Specifically, recommender systems can provide support for organizations and individuals to achieve the defined goal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03620v1-abstract-full').style.display = 'inline'; document.getElementById('2412.03620v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03620v1-abstract-full" style="display: none;"> Sustainability development goals (SDGs) are regarded as a universal call to action with the overall objectives of planet protection, ending of poverty, and ensuring peace and prosperity for all people. In order to achieve these objectives, different AI technologies play a major role. Specifically, recommender systems can provide support for organizations and individuals to achieve the defined goals. Recommender systems integrate AI technologies such as machine learning, explainable AI (XAI), case-based reasoning, and constraint solving in order to find and explain user-relevant alternatives from a potentially large set of options. In this article, we summarize the state of the art in applying recommender systems to support the achievement of sustainability development goals. In this context, we discuss open issues for future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03620v1-abstract-full').style.display = 'none'; document.getElementById('2412.03620v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Frontiers in Big Data 6 (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03441">arXiv:2412.03441</a> <span> [<a href="https://arxiv.org/pdf/2412.03441">pdf</a>, <a href="https://arxiv.org/format/2412.03441">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> PBP: Post-training Backdoor Purification for Malware Classifiers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+T">Dung Thuy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+N">Ngoc N. Tran</a>, <a href="/search/cs?searchtype=author&query=Johnson%2C+T+T">Taylor T. Johnson</a>, <a href="/search/cs?searchtype=author&query=Leach%2C+K">Kevin Leach</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="2412.03441v3-abstract-short" style="display: inline;"> In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious samples into public malware repositories, contaminating the training data and potentially misclassifying malware by the ML model. Current countermeasures predominantl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03441v3-abstract-full').style.display = 'inline'; document.getElementById('2412.03441v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03441v3-abstract-full" style="display: none;"> In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious samples into public malware repositories, contaminating the training data and potentially misclassifying malware by the ML model. Current countermeasures predominantly focus on detecting poisoned samples by leveraging disagreements within the outputs of a diverse set of ensemble models on training data points. However, these methods are not suitable for scenarios where Machine Learning-as-a-Service (MLaaS) is used or when users aim to remove backdoors from a model after it has been trained. Addressing this scenario, we introduce PBP, a post-training defense for malware classifiers that mitigates various types of backdoor embeddings without assuming any specific backdoor embedding mechanism. Our method exploits the influence of backdoor attacks on the activation distribution of neural networks, independent of the trigger-embedding method. In the presence of a backdoor attack, the activation distribution of each layer is distorted into a mixture of distributions. By regulating the statistics of the batch normalization layers, we can guide a backdoored model to perform similarly to a clean one. Our method demonstrates substantial advantages over several state-of-the-art methods, as evidenced by experiments on two datasets, two types of backdoor methods, and various attack configurations. Notably, our approach requires only a small portion of the training data -- only 1\% -- to purify the backdoor and reduce the attack success rate from 100\% to almost 0\%, a 100-fold improvement over the baseline methods. Our code is available at \url{https://github.com/judydnguyen/pbp-backdoor-purification-official}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03441v3-abstract-full').style.display = 'none'; document.getElementById('2412.03441v3-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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 NDSS 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/2410.11564">arXiv:2410.11564</a> <span> [<a href="https://arxiv.org/pdf/2410.11564">pdf</a>, <a href="https://arxiv.org/format/2410.11564">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shang-Ching Liu</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+V+N">Van Nhiem Tran</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wenkai Chen</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+W">Wei-Lun Cheng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yen-Lin Huang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+I">I-Bin Liao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yung-Hui Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianwei 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="2410.11564v1-abstract-short" style="display: inline;"> Affordance understanding, the task of identifying actionable regions on 3D objects, plays a vital role in allowing robotic systems to engage with and operate within the physical world. Although Visual Language Models (VLMs) have excelled in high-level reasoning and long-horizon planning for robotic manipulation, they still fall short in grasping the nuanced physical properties required for effecti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11564v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11564v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11564v1-abstract-full" style="display: none;"> Affordance understanding, the task of identifying actionable regions on 3D objects, plays a vital role in allowing robotic systems to engage with and operate within the physical world. Although Visual Language Models (VLMs) have excelled in high-level reasoning and long-horizon planning for robotic manipulation, they still fall short in grasping the nuanced physical properties required for effective human-robot interaction. In this paper, we introduce PAVLM (Point cloud Affordance Vision-Language Model), an innovative framework that utilizes the extensive multimodal knowledge embedded in pre-trained language models to enhance 3D affordance understanding of point cloud. PAVLM integrates a geometric-guided propagation module with hidden embeddings from large language models (LLMs) to enrich visual semantics. On the language side, we prompt Llama-3.1 models to generate refined context-aware text, augmenting the instructional input with deeper semantic cues. Experimental results on the 3D-AffordanceNet benchmark demonstrate that PAVLM outperforms baseline methods for both full and partial point clouds, particularly excelling in its generalization to novel open-world affordance tasks of 3D objects. For more information, visit our project site: pavlm-source.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11564v1-abstract-full').style.display = 'none'; document.getElementById('2410.11564v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09765">arXiv:2410.09765</a> <span> [<a href="https://arxiv.org/pdf/2410.09765">pdf</a>, <a href="https://arxiv.org/format/2410.09765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> INA-Infra: An Open and Extensible Infrastructure for Intent-driven Network Automation Research </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nguyen-Bao-Long Tran</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+T+V">Tuan V. Ngo</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+M+V">Mao V. Ngo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+B">Binbin Chen</a>, <a href="/search/cs?searchtype=author&query=Park%2C+J">Jihong Park</a>, <a href="/search/cs?searchtype=author&query=Quek%2C+T+Q+S">Tony Q. S. Quek</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="2410.09765v1-abstract-short" style="display: inline;"> As telecommunications systems progress to support diverse use cases with heterogeneous and dynamic Quality of Service (QoS) requirements, it becomes an increasingly complex task to automatically manage various resources involved -- from radio, compute, to X-haul network, which are distributed from the edge to the cloud. Intent-driven network automation can play an important role in NextG networks… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09765v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09765v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09765v1-abstract-full" style="display: none;"> As telecommunications systems progress to support diverse use cases with heterogeneous and dynamic Quality of Service (QoS) requirements, it becomes an increasingly complex task to automatically manage various resources involved -- from radio, compute, to X-haul network, which are distributed from the edge to the cloud. Intent-driven network automation can play an important role in NextG networks to meet this need. Towards this, we have developed INA-Infra, an open, extensible, and end-to-end 5G/beyond 5G network infrastructure with intent-driven network automation and end-to-end network slicing capability. INA-Infra is designed using open-source components and is based on O-RAN architecture. INA-Infra manages the network infrastructure, various resources, and (virtualized / containerized) network functions using Nephio -- a cloud-native intent automation solution. It also incorporates intent-driven intelligent control using a Resource Management rApp and a Network Slicing xApp. We demonstrate that INA-Infra can manage the 5G network in a highly automatic and optimized manner, allowing the mobile network operators to focus on specifying the intents of different traffic classes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09765v1-abstract-full').style.display = 'none'; document.getElementById('2410.09765v1-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 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">Preprint version, published at workshop OpenRIT-6G, part of IEEE GLOBECOM 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/2410.05789">arXiv:2410.05789</a> <span> [<a href="https://arxiv.org/pdf/2410.05789">pdf</a>, <a href="https://arxiv.org/format/2410.05789">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"> Hybrid Gripper with Passive Pneumatic Soft Joints for Grasping Deformable Thin Objects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Ngoc-Duy Tran</a>, <a href="/search/cs?searchtype=author&query=Ly%2C+H">Hoang-Hiep Ly</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+X">Xuan-Thuan Nguyen</a>, <a href="/search/cs?searchtype=author&query=Mac%2C+T">Thi-Thoa Mac</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+A">Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+T+D">Tung D. Ta</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="2410.05789v2-abstract-short" style="display: inline;"> Grasping a variety of objects remains a key challenge in the development of versatile robotic systems. The human hand is remarkably dexterous, capable of grasping and manipulating objects with diverse shapes, mechanical properties, and textures. Inspired by how humans use two fingers to pick up thin and large objects such as fabric or sheets of paper, we aim to develop a gripper optimized for gras… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05789v2-abstract-full').style.display = 'inline'; document.getElementById('2410.05789v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05789v2-abstract-full" style="display: none;"> Grasping a variety of objects remains a key challenge in the development of versatile robotic systems. The human hand is remarkably dexterous, capable of grasping and manipulating objects with diverse shapes, mechanical properties, and textures. Inspired by how humans use two fingers to pick up thin and large objects such as fabric or sheets of paper, we aim to develop a gripper optimized for grasping such deformable objects. Observing how the soft and flexible fingertip joints of the hand approach and grasp thin materials, a hybrid gripper design that incorporates both soft and rigid components was proposed. The gripper utilizes a soft pneumatic ring wrapped around a rigid revolute joint to create a flexible two-fingered gripper. Experiments were conducted to characterize and evaluate the gripper performance in handling sheets of paper and other objects. Compared to rigid grippers, the proposed design improves grasping efficiency and reduces the gripping distance by up to eightfold. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05789v2-abstract-full').style.display = 'none'; document.getElementById('2410.05789v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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/2410.02845">arXiv:2410.02845</a> <span> [<a href="https://arxiv.org/pdf/2410.02845">pdf</a>, <a href="https://arxiv.org/format/2410.02845">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"> Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+D">Minh Duong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+K">Khanh Le</a>, <a href="/search/cs?searchtype=author&query=Do%2C+K">Khoi Do</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Trinh%2C+C">Chien Trinh</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhaohui 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="2410.02845v1-abstract-short" style="display: inline;"> In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle during aggregation, can negate progress, leading to severe weight and gradient update degradation. To address this issue, we introduce a new approach… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02845v1-abstract-full').style.display = 'inline'; document.getElementById('2410.02845v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02845v1-abstract-full" style="display: none;"> In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle during aggregation, can negate progress, leading to severe weight and gradient update degradation. To address this issue, we introduce a new approach to pFL design, namely Federated Learning with Layer-wise Aggregation via Gradient Analysis (FedLAG), utilizing the concept of gradient conflict at the layer level. Specifically, when layer-wise gradients of different clients form acute angles, those gradients align in the same direction, enabling updates across different clients toward identifying client-invariant features. Conversely, when layer-wise gradient pairs make create obtuse angles, the layers tend to focus on client-specific tasks. In hindsights, FedLAG assigns layers for personalization based on the extent of layer-wise gradient conflicts. Specifically, layers with gradient conflicts are excluded from the global aggregation process. The theoretical evaluation demonstrates that when integrated into other pFL baselines, FedLAG enhances pFL performance by a certain margin. Therefore, our proposed method achieves superior convergence behavior compared with other baselines. Extensive experiments show that our FedLAG outperforms several state-of-the-art methods and can be easily incorporated with many existing methods to further enhance performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02845v1-abstract-full').style.display = 'none'; document.getElementById('2410.02845v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18690">arXiv:2409.18690</a> <span> [<a href="https://arxiv.org/pdf/2409.18690">pdf</a>, <a href="https://arxiv.org/format/2409.18690">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 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/10.1145/3640457.3691708">10.1145/3640457.3691708 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Less is More: Towards Sustainability-Aware Persuasive Explanations in Recommender Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+T+N+T">Thi Ngoc Trang Tran</a>, <a href="/search/cs?searchtype=author&query=Erdeniz%2C+S+P">Seda Polat Erdeniz</a>, <a href="/search/cs?searchtype=author&query=Felfernig%2C+A">Alexander Felfernig</a>, <a href="/search/cs?searchtype=author&query=Lubos%2C+S">Sebastian Lubos</a>, <a href="/search/cs?searchtype=author&query=El-Mansi%2C+M">Merfat El-Mansi</a>, <a href="/search/cs?searchtype=author&query=Le%2C+V">Viet-Man Le</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="2409.18690v1-abstract-short" style="display: inline;"> Recommender systems play an important role in supporting the achievement of the United Nations sustainable development goals (SDGs). In recommender systems, explanations can support different goals, such as increasing a user's trust in a recommendation, persuading a user to purchase specific items, or increasing the understanding of the reasons behind a recommendation. In this paper, we discuss th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18690v1-abstract-full').style.display = 'inline'; document.getElementById('2409.18690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18690v1-abstract-full" style="display: none;"> Recommender systems play an important role in supporting the achievement of the United Nations sustainable development goals (SDGs). In recommender systems, explanations can support different goals, such as increasing a user's trust in a recommendation, persuading a user to purchase specific items, or increasing the understanding of the reasons behind a recommendation. In this paper, we discuss the concept of "sustainability-aware persuasive explanations" which we regard as a major concept to support the achievement of the mentioned SDGs. Such explanations are orthogonal to most existing explanation approaches since they focus on a "less is more" principle, which per se is not included in existing e-commerce platforms. Based on a user study in three item domains, we analyze the potential impacts of sustainability-aware persuasive explanations. The study results are promising regarding user acceptance and the potential impacts of such explanations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18690v1-abstract-full').style.display = 'none'; document.getElementById('2409.18690v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The paper was accepted for publication and will be presented in the LBR track of RecSys 2024, 14.- 18. October 2024, Bari, Italy</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08181">arXiv:2409.08181</a> <span> [<a href="https://arxiv.org/pdf/2409.08181">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> </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/10.54941/ahfe1005071">10.54941/ahfe1005071 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Enhancing Canine Musculoskeletal Diagnoses: Leveraging Synthetic Image Data for Pre-Training AI-Models on Visual Documentations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thi%C3%9Fen%2C+M">Martin Thi脽en</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T+N+D">Thi Ngoc Diep Tran</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6nbein%2C+B+J">Ben Joel Sch枚nbein</a>, <a href="/search/cs?searchtype=author&query=Trapp%2C+U">Ute Trapp</a>, <a href="/search/cs?searchtype=author&query=Ratsch%2C+B+E">Barbara Esteve Ratsch</a>, <a href="/search/cs?searchtype=author&query=Egner%2C+B">Beate Egner</a>, <a href="/search/cs?searchtype=author&query=Piat%2C+R">Romana Piat</a>, <a href="/search/cs?searchtype=author&query=Hergenr%C3%B6ther%2C+E">Elke Hergenr枚ther</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="2409.08181v1-abstract-short" style="display: inline;"> The examination of the musculoskeletal system in dogs is a challenging task in veterinary practice. In this work, a novel method has been developed that enables efficient documentation of a dog's condition through a visual representation. However, since the visual documentation is new, there is no existing training data. The objective of this work is therefore to mitigate the impact of data scarci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08181v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08181v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08181v1-abstract-full" style="display: none;"> The examination of the musculoskeletal system in dogs is a challenging task in veterinary practice. In this work, a novel method has been developed that enables efficient documentation of a dog's condition through a visual representation. However, since the visual documentation is new, there is no existing training data. The objective of this work is therefore to mitigate the impact of data scarcity in order to develop an AI-based diagnostic support system. To this end, the potential of synthetic data that mimics realistic visual documentations of diseases for pre-training AI models is investigated. We propose a method for generating synthetic image data that mimics realistic visual documentations. Initially, a basic dataset containing three distinct classes is generated, followed by the creation of a more sophisticated dataset containing 36 different classes. Both datasets are used for the pre-training of an AI model. Subsequently, an evaluation dataset is created, consisting of 250 manually created visual documentations for five different diseases. This dataset, along with a subset containing 25 examples. The obtained results on the evaluation dataset containing 25 examples demonstrate a significant enhancement of approximately 10% in diagnosis accuracy when utilizing generated synthetic images that mimic real-world visual documentations. However, these results do not hold true for the larger evaluation dataset containing 250 examples, indicating that the advantages of using synthetic data for pre-training an AI model emerge primarily when dealing with few examples of visual documentations for a given disease. Overall, this work provides valuable insights into mitigating the limitations imposed by limited training data through the strategic use of generated synthetic data, presenting an approach applicable beyond the canine musculoskeletal assessment domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08181v1-abstract-full').style.display = 'none'; document.getElementById('2409.08181v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.10886">arXiv:2408.10886</a> <span> [<a href="https://arxiv.org/pdf/2408.10886">pdf</a>, <a href="https://arxiv.org/format/2408.10886">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/RE59067.2024.00046">10.1109/RE59067.2024.00046 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Leveraging LLMs for the Quality Assurance of Software Requirements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lubos%2C+S">Sebastian Lubos</a>, <a href="/search/cs?searchtype=author&query=Felfernig%2C+A">Alexander Felfernig</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T+N+T">Thi Ngoc Trang Tran</a>, <a href="/search/cs?searchtype=author&query=Garber%2C+D">Damian Garber</a>, <a href="/search/cs?searchtype=author&query=Mansi%2C+M+E">Merfat El Mansi</a>, <a href="/search/cs?searchtype=author&query=Erdeniz%2C+S+P">Seda Polat Erdeniz</a>, <a href="/search/cs?searchtype=author&query=Le%2C+V">Viet-Man Le</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="2408.10886v1-abstract-short" style="display: inline;"> Successful software projects depend on the quality of software requirements. Creating high-quality requirements is a crucial step toward successful software development. Effective support in this area can significantly reduce development costs and enhance the software quality. In this paper, we introduce and assess the capabilities of a Large Language Model (LLM) to evaluate the quality characteri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10886v1-abstract-full').style.display = 'inline'; document.getElementById('2408.10886v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.10886v1-abstract-full" style="display: none;"> Successful software projects depend on the quality of software requirements. Creating high-quality requirements is a crucial step toward successful software development. Effective support in this area can significantly reduce development costs and enhance the software quality. In this paper, we introduce and assess the capabilities of a Large Language Model (LLM) to evaluate the quality characteristics of software requirements according to the ISO 29148 standard. We aim to further improve the support of stakeholders engaged in requirements engineering (RE). We show how an LLM can assess requirements, explain its decision-making process, and examine its capacity to propose improved versions of requirements. We conduct a study with software engineers to validate our approach. Our findings emphasize the potential of LLMs for improving the quality of software requirements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10886v1-abstract-full').style.display = 'none'; document.getElementById('2408.10886v1-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 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">Accepted for publication at the RE@Next! track of RE 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/2408.08926">arXiv:2408.08926</a> <span> [<a href="https://arxiv.org/pdf/2408.08926">pdf</a>, <a href="https://arxiv.org/format/2408.08926">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+A+K">Andy K. Zhang</a>, <a href="/search/cs?searchtype=author&query=Perry%2C+N">Neil Perry</a>, <a href="/search/cs?searchtype=author&query=Dulepet%2C+R">Riya Dulepet</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+J">Joey Ji</a>, <a href="/search/cs?searchtype=author&query=Menders%2C+C">Celeste Menders</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J+W">Justin W. Lin</a>, <a href="/search/cs?searchtype=author&query=Jones%2C+E">Eliot Jones</a>, <a href="/search/cs?searchtype=author&query=Hussein%2C+G">Gashon Hussein</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Samantha Liu</a>, <a href="/search/cs?searchtype=author&query=Jasper%2C+D">Donovan Jasper</a>, <a href="/search/cs?searchtype=author&query=Peetathawatchai%2C+P">Pura Peetathawatchai</a>, <a href="/search/cs?searchtype=author&query=Glenn%2C+A">Ari Glenn</a>, <a href="/search/cs?searchtype=author&query=Sivashankar%2C+V">Vikram Sivashankar</a>, <a href="/search/cs?searchtype=author&query=Zamoshchin%2C+D">Daniel Zamoshchin</a>, <a href="/search/cs?searchtype=author&query=Glikbarg%2C+L">Leo Glikbarg</a>, <a href="/search/cs?searchtype=author&query=Askaryar%2C+D">Derek Askaryar</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+M">Mike Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Teddy Zhang</a>, <a href="/search/cs?searchtype=author&query=Alluri%2C+R">Rishi Alluri</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nathan Tran</a>, <a href="/search/cs?searchtype=author&query=Sangpisit%2C+R">Rinnara Sangpisit</a>, <a href="/search/cs?searchtype=author&query=Yiorkadjis%2C+P">Polycarpos Yiorkadjis</a>, <a href="/search/cs?searchtype=author&query=Osele%2C+K">Kenny Osele</a>, <a href="/search/cs?searchtype=author&query=Raghupathi%2C+G">Gautham Raghupathi</a>, <a href="/search/cs?searchtype=author&query=Boneh%2C+D">Dan Boneh</a> , et al. (2 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="2408.08926v3-abstract-short" style="display: inline;"> Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08926v3-abstract-full').style.display = 'inline'; document.getElementById('2408.08926v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08926v3-abstract-full" style="display: none;"> Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks for each task, which break down a task into intermediary steps for a more detailed evaluation. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 8 models: GPT-4o, OpenAI o1-preview, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. For the top performing models (GPT-4o and Claude 3.5 Sonnet), we further investigate performance across 4 agent scaffolds (structed bash, action-only, pseudoterminal, and web search). Without subtask guidance, agents leveraging Claude 3.5 Sonnet, GPT-4o, OpenAI o1-preview, and Claude 3 Opus successfully solved complete tasks that took human teams up to 11 minutes to solve. In comparison, the most difficult task took human teams 24 hours and 54 minutes to solve. All code and data are publicly available at https://cybench.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08926v3-abstract-full').style.display = 'none'; document.getElementById('2408.08926v3-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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">151 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.16497">arXiv:2407.16497</a> <span> [<a href="https://arxiv.org/pdf/2407.16497">pdf</a>, <a href="https://arxiv.org/format/2407.16497">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"> Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khanh%2C+T+L+B">Trinh Le Ba Khanh</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Huy-Hung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+L+H">Long Hoang Pham</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+D+N">Duong Nguyen-Ngoc Tran</a>, <a href="/search/cs?searchtype=author&query=Jeon%2C+J+W">Jae Wook Jeon</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="2407.16497v1-abstract-short" style="display: inline;"> In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, UDA's reliance on labeled source data restricts its adaptability in privacy-related scenarios. This study focuses on source-free object detection (SFOD), which adapts a source-trained detector to an unlabeled target domain without using labeled s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16497v1-abstract-full').style.display = 'inline'; document.getElementById('2407.16497v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.16497v1-abstract-full" style="display: none;"> In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, UDA's reliance on labeled source data restricts its adaptability in privacy-related scenarios. This study focuses on source-free object detection (SFOD), which adapts a source-trained detector to an unlabeled target domain without using labeled source data. Recent advancements in self-training, particularly with the Mean Teacher (MT) framework, show promise for SFOD deployment. However, the absence of source supervision significantly compromises the stability of these approaches. We identify two primary issues, (1) uncontrollable degradation of the teacher model due to inopportune updates from the student model, and (2) the student model's tendency to replicate errors from incorrect pseudo labels, leading to it being trapped in a local optimum. Both factors contribute to a detrimental circular dependency, resulting in rapid performance degradation in recent self-training frameworks. To tackle these challenges, we propose the Dynamic Retraining-Updating (DRU) mechanism, which actively manages the student training and teacher updating processes to achieve co-evolutionary training. Additionally, we introduce Historical Student Loss to mitigate the influence of incorrect pseudo labels. Our method achieves state-of-the-art performance in the SFOD setting on multiple domain adaptation benchmarks, comparable to or even surpassing advanced UDA methods. The code will be released at https://github.com/lbktrinh/DRU <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16497v1-abstract-full').style.display = 'none'; document.getElementById('2407.16497v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 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">ECCV 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/2407.07421">arXiv:2407.07421</a> <span> [<a href="https://arxiv.org/pdf/2407.07421">pdf</a>, <a href="https://arxiv.org/format/2407.07421">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="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TNET.2024.3423780">10.1109/TNET.2024.3423780 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Federated PCA on Grassmann Manifold for IoT Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung-Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+L+T">Long Tan Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+D">Tuan Dung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+W">Wei Bao</a>, <a href="/search/cs?searchtype=author&query=Seneviratne%2C+S">Suranga Seneviratne</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</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="2407.07421v1-abstract-short" style="display: inline;"> With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with hi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07421v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07421v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07421v1-abstract-full" style="display: none;"> With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with high dimensionality. Recent unsupervised ML-IDS approaches such as AutoEncoders and Generative Adversarial Networks (GAN) offer alternative solutions but pose challenges in deployment onto resource-constrained IoT devices and in interpretability. To address these concerns, this paper proposes a novel federated unsupervised anomaly detection framework, FedPCA, that leverages Principal Component Analysis (PCA) and the Alternating Directions Method Multipliers (ADMM) to learn common representations of distributed non-i.i.d. datasets. Building on the FedPCA framework, we propose two algorithms, FEDPE in Euclidean space and FEDPG on Grassmann manifolds. Our approach enables real-time threat detection and mitigation at the device level, enhancing network resilience while ensuring privacy. Moreover, the proposed algorithms are accompanied by theoretical convergence rates even under a subsampling scheme, a novel result. Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to nonlinear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07421v1-abstract-full').style.display = 'none'; document.getElementById('2407.07421v1-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 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">Accepted for publication at IEEE/ACM Transactions on Networking</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE/ACM Transactions on Networking On page(s): 1-16 Print ISSN: 1063-6692 Online ISSN: 1558-2566 Digital Object Identifier: 10.1109/TNET.2024.3423780 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19522">arXiv:2406.19522</a> <span> [<a href="https://arxiv.org/pdf/2406.19522">pdf</a>, <a href="https://arxiv.org/format/2406.19522">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"> Reliable edge machine learning hardware for scientific applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baldi%2C+T">Tommaso Baldi</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+J">Javier Campos</a>, <a href="/search/cs?searchtype=author&query=Hawks%2C+B">Ben Hawks</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Diaz%2C+D">Daniel Diaz</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Kastner%2C+R">Ryan Kastner</a>, <a href="/search/cs?searchtype=author&query=Meza%2C+A">Andres Meza</a>, <a href="/search/cs?searchtype=author&query=Quinnan%2C+M">Melissa Quinnan</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+O">Olivia Weng</a>, <a href="/search/cs?searchtype=author&query=Geniesse%2C+C">Caleb Geniesse</a>, <a href="/search/cs?searchtype=author&query=Gholami%2C+A">Amir Gholami</a>, <a href="/search/cs?searchtype=author&query=Mahoney%2C+M+W">Michael W. Mahoney</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Agar%2C+J">Joshua Agar</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+S">Shuyu Qin</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="2406.19522v1-abstract-short" style="display: inline;"> Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19522v1-abstract-full').style.display = 'inline'; document.getElementById('2406.19522v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19522v1-abstract-full" style="display: none;"> Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19522v1-abstract-full').style.display = 'none'; document.getElementById('2406.19522v1-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> <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">IEEE VLSI Test Symposium 2024 (VTS)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-CONF-24-0116-CSAID </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.09737">arXiv:2406.09737</a> <span> [<a href="https://arxiv.org/pdf/2406.09737">pdf</a>, <a href="https://arxiv.org/format/2406.09737">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> A Multivocal Review of MLOps Practices, Challenges and Open Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eken%2C+B">Beyza Eken</a>, <a href="/search/cs?searchtype=author&query=Pallewatta%2C+S">Samodha Pallewatta</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+K">Nguyen Khoi Tran</a>, <a href="/search/cs?searchtype=author&query=Tosun%2C+A">Ayse Tosun</a>, <a href="/search/cs?searchtype=author&query=Babar%2C+M+A">Muhammad Ali Babar</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="2406.09737v1-abstract-short" style="display: inline;"> With the increasing trend of Machine Learning (ML) enabled software applications, the paradigm of ML Operations (MLOps) has gained tremendous attention of researchers and practitioners. MLOps encompasses the practices and technologies for streamlining the resources and monitoring needs of operationalizing ML models. Software development practitioners need access to the detailed and easily understa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09737v1-abstract-full').style.display = 'inline'; document.getElementById('2406.09737v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.09737v1-abstract-full" style="display: none;"> With the increasing trend of Machine Learning (ML) enabled software applications, the paradigm of ML Operations (MLOps) has gained tremendous attention of researchers and practitioners. MLOps encompasses the practices and technologies for streamlining the resources and monitoring needs of operationalizing ML models. Software development practitioners need access to the detailed and easily understandable knowledge of MLOps workflows, practices, challenges and solutions to effectively and efficiently support the adoption of MLOps. Whilst the academic and industry literature on the MLOps has been growing rapidly, there have been relatively a few attempts at systematically synthesizing and analyzing the vast amount of existing literature of MLOps for improving ease of access and understanding. We conducted a Multivocal Literature Review (MLR) of 150 relevant academic studies and 48 gray literature to provide a comprehensive body of knowledge on MLOps. Through this MLR, we identified the emerging MLOps practices, adoption challenges and solutions related to various areas, including development and operation of complex pipelines, managing production at scale, managing artifacts, and ensuring quality, security, governance, and ethical aspects. We also report the socio-technical aspect of MLOps relating to diverse roles involved and collaboration practices across them through the MLOps lifecycle. We assert that this MLR provides valuable insights to researchers and practitioners seeking to navigate the rapidly evolving landscape of MLOps. We also identify the open issues that need to be addressed in order to advance the current state-of-the-art of MLOps. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09737v1-abstract-full').style.display = 'none'; document.getElementById('2406.09737v1-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 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">45 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.08680">arXiv:2406.08680</a> <span> [<a href="https://arxiv.org/pdf/2406.08680">pdf</a>, <a href="https://arxiv.org/format/2406.08680">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"> Analyzing Large Language Models for Classroom Discussion Assessment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhat Tran</a>, <a href="/search/cs?searchtype=author&query=Pierce%2C+B">Benjamin Pierce</a>, <a href="/search/cs?searchtype=author&query=Litman%2C+D">Diane Litman</a>, <a href="/search/cs?searchtype=author&query=Correnti%2C+R">Richard Correnti</a>, <a href="/search/cs?searchtype=author&query=Matsumura%2C+L+C">Lindsay Clare Matsumura</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="2406.08680v1-abstract-short" style="display: inline;"> Automatically assessing classroom discussion quality is becoming increasingly feasible with the help of new NLP advancements such as large language models (LLMs). In this work, we examine how the assessment performance of 2 LLMs interacts with 3 factors that may affect performance: task formulation, context length, and few-shot examples. We also explore the computational efficiency and predictive… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08680v1-abstract-full').style.display = 'inline'; document.getElementById('2406.08680v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.08680v1-abstract-full" style="display: none;"> Automatically assessing classroom discussion quality is becoming increasingly feasible with the help of new NLP advancements such as large language models (LLMs). In this work, we examine how the assessment performance of 2 LLMs interacts with 3 factors that may affect performance: task formulation, context length, and few-shot examples. We also explore the computational efficiency and predictive consistency of the 2 LLMs. Our results suggest that the 3 aforementioned factors do affect the performance of the tested LLMs and there is a relation between consistency and performance. We recommend a LLM-based assessment approach that has a good balance in terms of predictive performance, computational efficiency, and consistency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08680v1-abstract-full').style.display = 'none'; document.getElementById('2406.08680v1-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 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">EDM 2024 Short Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.00837">arXiv:2406.00837</a> <span> [<a href="https://arxiv.org/pdf/2406.00837">pdf</a>, <a href="https://arxiv.org/format/2406.00837">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"> Arena 3.0: Advancing Social Navigation in Collaborative and Highly Dynamic Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=K%C3%A4stner%2C+L">Linh K盲stner</a>, <a href="/search/cs?searchtype=author&query=Shcherbyna%2C+V">Volodymyir Shcherbyna</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+H">Huajian Zeng</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+A">Tuan Anh Le</a>, <a href="/search/cs?searchtype=author&query=Schreff%2C+M+H">Maximilian Ho-Kyoung Schreff</a>, <a href="/search/cs?searchtype=author&query=Osmaev%2C+H">Halid Osmaev</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+T">Nam Truong Tran</a>, <a href="/search/cs?searchtype=author&query=Diaz%2C+D">Diego Diaz</a>, <a href="/search/cs?searchtype=author&query=Golebiowski%2C+J">Jan Golebiowski</a>, <a href="/search/cs?searchtype=author&query=Soh%2C+H">Harold Soh</a>, <a href="/search/cs?searchtype=author&query=Lambrecht%2C+J">Jens Lambrecht</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="2406.00837v1-abstract-short" style="display: inline;"> Building upon our previous contributions, this paper introduces Arena 3.0, an extension of Arena-Bench, Arena 1.0, and Arena 2.0. Arena 3.0 is a comprehensive software stack containing multiple modules and simulation environments focusing on the development, simulation, and benchmarking of social navigation approaches in collaborative environments. We significantly enhance the realism of human beh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00837v1-abstract-full').style.display = 'inline'; document.getElementById('2406.00837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00837v1-abstract-full" style="display: none;"> Building upon our previous contributions, this paper introduces Arena 3.0, an extension of Arena-Bench, Arena 1.0, and Arena 2.0. Arena 3.0 is a comprehensive software stack containing multiple modules and simulation environments focusing on the development, simulation, and benchmarking of social navigation approaches in collaborative environments. We significantly enhance the realism of human behavior simulation by incorporating a diverse array of new social force models and interaction patterns, encompassing both human-human and human-robot dynamics. The platform provides a comprehensive set of new task modes, designed for extensive benchmarking and testing and is capable of generating realistic and human-centric environments dynamically, catering to a broad spectrum of social navigation scenarios. In addition, the platform's functionalities have been abstracted across three widely used simulators, each tailored for specific training and testing purposes. The platform's efficacy has been validated through an extensive benchmark and user evaluations of the platform by a global community of researchers and students, which noted the substantial improvement compared to previous versions and expressed interests to utilize the platform for future research and development. Arena 3.0 is openly available at https://github.com/Arena-Rosnav. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00837v1-abstract-full').style.display = 'none'; document.getElementById('2406.00837v1-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 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">11 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Robotics Science and Systems 2024, Delft Netherlands </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.17582">arXiv:2405.17582</a> <span> [<a href="https://arxiv.org/pdf/2405.17582">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="Systems and Control">eess.SY</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/10.5281/zenodo.6190227">10.5281/zenodo.6190227 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Building a temperature forecasting model for the city with the regression neural network (RNN) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+P">Nguyen Phuc Tran</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+D+T">Duy Thanh Tran</a>, <a href="/search/cs?searchtype=author&query=Duong%2C+T+T+N">Thi Thuy Nga Duong</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="2405.17582v1-abstract-short" style="display: inline;"> In recent years, a study by environmental organizations in the world and Vietnam shows that weather change is quite complex. global warming has become a serious problem in the modern world, which is a concern for scientists. last century, it was difficult to forecast the weather due to missing weather monitoring stations and technological limitations. this made it hard to collect data for building… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17582v1-abstract-full').style.display = 'inline'; document.getElementById('2405.17582v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.17582v1-abstract-full" style="display: none;"> In recent years, a study by environmental organizations in the world and Vietnam shows that weather change is quite complex. global warming has become a serious problem in the modern world, which is a concern for scientists. last century, it was difficult to forecast the weather due to missing weather monitoring stations and technological limitations. this made it hard to collect data for building predictive models to make accurate simulations. in Vietnam, research on weather forecast models is a recent development, having only begun around 2000. along with advancements in computer science, mathematical models are being built and applied with machine learning techniques to create more accurate and reliable predictive models. this article will summarize the research and solutions for applying recurrent neural networks to forecast urban temperatures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17582v1-abstract-full').style.display = 'none'; document.getElementById('2405.17582v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">6 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> The 6th International Conference for Small & Medium Business in 2020 (ICSMB 2020) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.15779">arXiv:2405.15779</a> <span> [<a href="https://arxiv.org/pdf/2405.15779">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> LiteNeXt: A Novel Lightweight ConvMixer-based Model with Self-embedding Representation Parallel for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Ngoc-Du Tran</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T">Thi-Thao Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+Q">Quang-Huy Nguyen</a>, <a href="/search/cs?searchtype=author&query=Vu%2C+M">Manh-Hung Vu</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+V">Van-Truong Pham</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="2405.15779v1-abstract-short" style="display: inline;"> The emergence of deep learning techniques has advanced the image segmentation task, especially for medical images. Many neural network models have been introduced in the last decade bringing the automated segmentation accuracy close to manual segmentation. However, cutting-edge models like Transformer-based architectures rely on large scale annotated training data, and are generally designed with… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15779v1-abstract-full').style.display = 'inline'; document.getElementById('2405.15779v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15779v1-abstract-full" style="display: none;"> The emergence of deep learning techniques has advanced the image segmentation task, especially for medical images. Many neural network models have been introduced in the last decade bringing the automated segmentation accuracy close to manual segmentation. However, cutting-edge models like Transformer-based architectures rely on large scale annotated training data, and are generally designed with densely consecutive layers in the encoder, decoder, and skip connections resulting in large number of parameters. Additionally, for better performance, they often be pretrained on a larger data, thus requiring large memory size and increasing resource expenses. In this study, we propose a new lightweight but efficient model, namely LiteNeXt, based on convolutions and mixing modules with simplified decoder, for medical image segmentation. The model is trained from scratch with small amount of parameters (0.71M) and Giga Floating Point Operations Per Second (0.42). To handle boundary fuzzy as well as occlusion or clutter in objects especially in medical image regions, we propose the Marginal Weight Loss that can help effectively determine the marginal boundary between object and background. Furthermore, we propose the Self-embedding Representation Parallel technique, that can help augment the data in a self-learning manner. Experiments on public datasets including Data Science Bowls, GlaS, ISIC2018, PH2, and Sunnybrook data show promising results compared to other state-of-the-art CNN-based and Transformer-based architectures. Our code will be published at: https://github.com/tranngocduvnvp/LiteNeXt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15779v1-abstract-full').style.display = 'none'; document.getElementById('2405.15779v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">35 pages, 9 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/2405.15230">arXiv:2405.15230</a> <span> [<a href="https://arxiv.org/pdf/2405.15230">pdf</a>, <a href="https://arxiv.org/format/2405.15230">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"> $i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+L+T">Long Tan Le</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+H">Han Shu</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung-Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</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="2405.15230v2-abstract-short" style="display: inline;"> While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15230v2-abstract-full').style.display = 'inline'; document.getElementById('2405.15230v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15230v2-abstract-full" style="display: none;"> While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited by their overfitting to pre-collected hard-label datasets. In this paper, we propose a novel LLM alignment framework named $i$REPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. Particularly, $i$REPO employs self-generated datasets labeled by empirical human (or AI annotator) preference to iteratively refine the aligned policy through a novel regression-based loss function. Furthermore, we introduce an innovative algorithm backed by theoretical guarantees for achieving optimal results under ideal assumptions and providing a practical performance-gap result without such assumptions. Experimental results with Phi-2 and Mistral-7B demonstrate that $i$REPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators. Furthermore, our approach surpasses preference optimization baselines in evaluations using the Language Model Evaluation Harness and Multi-turn benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15230v2-abstract-full').style.display = 'none'; document.getElementById('2405.15230v2-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 24 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">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/2405.13899">arXiv:2405.13899</a> <span> [<a href="https://arxiv.org/pdf/2405.13899">pdf</a>, <a href="https://arxiv.org/format/2405.13899">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">stat.ML</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"> Symmetric Linear Bandits with Hidden Symmetry </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+P">Nam Phuong Tran</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+T+A">The Anh Ta</a>, <a href="/search/cs?searchtype=author&query=Mandal%2C+D">Debmalya Mandal</a>, <a href="/search/cs?searchtype=author&query=Tran-Thanh%2C+L">Long Tran-Thanh</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="2405.13899v2-abstract-short" style="display: inline;"> High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be available in practice. Symmetry, where the reward is invariant under certain groups of transformations on the set of arms, is another important inductive bias in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13899v2-abstract-full').style.display = 'inline'; document.getElementById('2405.13899v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.13899v2-abstract-full" style="display: none;"> High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be available in practice. Symmetry, where the reward is invariant under certain groups of transformations on the set of arms, is another important inductive bias in the high-dimensional case that covers many standard structures, including sparsity. In this work, we study high-dimensional symmetric linear bandits where the symmetry is hidden from the learner, and the correct symmetry needs to be learned in an online setting. We examine the structure of a collection of hidden symmetry and provide a method based on model selection within the collection of low-dimensional subspaces. Our algorithm achieves a regret bound of $ O(d_0^{2/3} T^{2/3} \log(d))$, where $d$ is the ambient dimension which is potentially very large, and $d_0$ is the dimension of the true low-dimensional subspace such that $d_0 \ll d$. With an extra assumption on well-separated models, we can further improve the regret to $ O(d_0\sqrt{T\log(d)} )$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13899v2-abstract-full').style.display = 'none'; document.getElementById('2405.13899v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.04713">arXiv:2405.04713</a> <span> [<a href="https://arxiv.org/pdf/2405.04713">pdf</a>, <a href="https://arxiv.org/format/2405.04713">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhat Tran</a>, <a href="/search/cs?searchtype=author&query=Litman%2C+D">Diane Litman</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="2405.04713v1-abstract-short" style="display: inline;"> Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, impr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04713v1-abstract-full').style.display = 'inline'; document.getElementById('2405.04713v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.04713v1-abstract-full" style="display: none;"> Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04713v1-abstract-full').style.display = 'none'; document.getElementById('2405.04713v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">LREC-COLING 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/2404.18705">arXiv:2404.18705</a> <span> [<a href="https://arxiv.org/pdf/2404.18705">pdf</a>, <a href="https://arxiv.org/format/2404.18705">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"> Wireless Information and Energy Transfer in the Era of 6G Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Psomas%2C+C">Constantinos Psomas</a>, <a href="/search/cs?searchtype=author&query=Ntougias%2C+K">Konstantinos Ntougias</a>, <a href="/search/cs?searchtype=author&query=Shanin%2C+N">Nikita Shanin</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Dongfang Xu</a>, <a href="/search/cs?searchtype=author&query=Mayer%2C+K+M">Kenneth MacSporran Mayer</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+M">Nguyen Minh Tran</a>, <a href="/search/cs?searchtype=author&query=Cottatellucci%2C+L">Laura Cottatellucci</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+K+W">Kae Won Choi</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+D+I">Dong In Kim</a>, <a href="/search/cs?searchtype=author&query=Schober%2C+R">Robert Schober</a>, <a href="/search/cs?searchtype=author&query=Krikidis%2C+I">Ioannis Krikidis</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="2404.18705v2-abstract-short" style="display: inline;"> Wireless information and energy transfer (WIET) represents an emerging paradigm which employs controllable transmission of radio-frequency signals for the dual purpose of data communication and wireless charging. As such, WIET is widely regarded as an enabler of envisioned 6G use cases that rely on energy-sustainable Internet-of-Things (IoT) networks, such as smart cities and smart grids. Meeting… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18705v2-abstract-full').style.display = 'inline'; document.getElementById('2404.18705v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.18705v2-abstract-full" style="display: none;"> Wireless information and energy transfer (WIET) represents an emerging paradigm which employs controllable transmission of radio-frequency signals for the dual purpose of data communication and wireless charging. As such, WIET is widely regarded as an enabler of envisioned 6G use cases that rely on energy-sustainable Internet-of-Things (IoT) networks, such as smart cities and smart grids. Meeting the quality-of-service demands of WIET, in terms of both data transfer and power delivery, requires effective co-design of the information and energy signals. In this article, we present the main principles and design aspects of WIET, focusing on its integration in 6G networks. First, we discuss how conventional communication notions such as resource allocation and waveform design need to be revisited in the context of WIET. Next, we consider various candidate 6G technologies that can boost WIET efficiency, namely, holographic multiple-input multiple-output, near-field beamforming, terahertz communication, intelligent reflecting surfaces (IRSs), and reconfigurable (fluid) antenna arrays. We introduce respective WIET design methods, analyze the promising performance gains of these WIET systems, and discuss challenges, open issues, and future research directions. Finally, a near-field energy beamforming scheme and a power-based IRS beamforming algorithm are experimentally validated using a wireless energy transfer testbed. The vision of WIET in communication systems has been gaining momentum in recent years, with constant progress with respect to theoretical but also practical aspects. The comprehensive overview of the state of the art of WIET presented in this paper highlights the potentials of WIET systems as well as their overall benefits in 6G networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18705v2-abstract-full').style.display = 'none'; document.getElementById('2404.18705v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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 IEEE, 36 pages, 33 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/2404.18383">arXiv:2404.18383</a> <span> [<a href="https://arxiv.org/pdf/2404.18383">pdf</a>, <a href="https://arxiv.org/format/2404.18383">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"> A Framework for Learning and Reusing Robotic Skills </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hertel%2C+B">Brendan Hertel</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhu Tran</a>, <a href="/search/cs?searchtype=author&query=Elkoudi%2C+M">Meriem Elkoudi</a>, <a href="/search/cs?searchtype=author&query=Azadeh%2C+R">Reza Azadeh</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="2404.18383v2-abstract-short" style="display: inline;"> In this paper, we present our work in progress towards creating a library of motion primitives. This library facilitates easier and more intuitive learning and reusing of robotic skills. Users can teach robots complex skills through Learning from Demonstration, which is automatically segmented into primitives and stored in clusters of similar skills. We propose a novel multimodal segmentation meth… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18383v2-abstract-full').style.display = 'inline'; document.getElementById('2404.18383v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.18383v2-abstract-full" style="display: none;"> In this paper, we present our work in progress towards creating a library of motion primitives. This library facilitates easier and more intuitive learning and reusing of robotic skills. Users can teach robots complex skills through Learning from Demonstration, which is automatically segmented into primitives and stored in clusters of similar skills. We propose a novel multimodal segmentation method as well as a novel trajectory clustering method. Then, when needed for reuse, we transform primitives into new environments using trajectory editing. We present simulated results for our framework with demonstrations taken on real-world robots. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18383v2-abstract-full').style.display = 'none'; document.getElementById('2404.18383v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">4 pages, 4 figures. Accepted for publication as work-in-progress paper at Ubiquitous Robots (UR) 2024. Code available here: https://github.com/brenhertel/Probabilistic-Segmentation and here: https://github.com/brenhertel/Elastic-Clustering</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 20th International Conference on Ubiquitous Robots (UR) 801-804 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.15497">arXiv:2404.15497</a> <span> [<a href="https://arxiv.org/pdf/2404.15497">pdf</a>, <a href="https://arxiv.org/format/2404.15497">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Soft Condensed Matter">cond-mat.soft</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"> Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+P+N">Phu N. Tran</a>, <a href="/search/cs?searchtype=author&query=Ray%2C+S">Sattvic Ray</a>, <a href="/search/cs?searchtype=author&query=Lemma%2C+L">Linnea Lemma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunrui Li</a>, <a href="/search/cs?searchtype=author&query=Sweeney%2C+R">Reef Sweeney</a>, <a href="/search/cs?searchtype=author&query=Baskaran%2C+A">Aparna Baskaran</a>, <a href="/search/cs?searchtype=author&query=Dogic%2C+Z">Zvonimir Dogic</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+P">Pengyu Hong</a>, <a href="/search/cs?searchtype=author&query=Hagan%2C+M+F">Michael F. Hagan</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="2404.15497v2-abstract-short" style="display: inline;"> Deep learning-based optical flow (DLOF) extracts features in adjacent video frames with deep convolutional neural networks. It uses those features to estimate the inter-frame motions of objects at the pixel level. In this article, we evaluate the ability of optical flow to quantify the spontaneous flows of MT-based active nematics under different labeling conditions. We compare DLOF against the co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15497v2-abstract-full').style.display = 'inline'; document.getElementById('2404.15497v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.15497v2-abstract-full" style="display: none;"> Deep learning-based optical flow (DLOF) extracts features in adjacent video frames with deep convolutional neural networks. It uses those features to estimate the inter-frame motions of objects at the pixel level. In this article, we evaluate the ability of optical flow to quantify the spontaneous flows of MT-based active nematics under different labeling conditions. We compare DLOF against the commonly used technique, particle imaging velocimetry (PIV). We obtain flow velocity ground truths either by performing semi-automated particle tracking on samples with sparsely labeled filaments, or from passive tracer beads. We find that DLOF produces significantly more accurate velocity fields than PIV for densely labeled samples. We show that the breakdown of PIV arises because the algorithm cannot reliably distinguish contrast variations at high densities, particularly in directions parallel to the nematic director. DLOF overcomes this limitation. For sparsely labeled samples, DLOF and PIV produce results with similar accuracy, but DLOF gives higher-resolution fields. Our work establishes DLOF as a versatile tool for measuring fluid flows in a broad class of active, soft, and biophysical systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15497v2-abstract-full').style.display = 'none'; document.getElementById('2404.15497v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14610">arXiv:2404.14610</a> <span> [<a href="https://arxiv.org/pdf/2404.14610">pdf</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 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/10.1145/3613905.3651075">10.1145/3613905.3651075 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Sign Language-Based versus Touch-Based Input for Deaf Users with Interactive Personal Assistants in Simulated Kitchen Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=DeVries%2C+P">Paige DeVries</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nina Tran</a>, <a href="/search/cs?searchtype=author&query=Delk%2C+K">Keith Delk</a>, <a href="/search/cs?searchtype=author&query=Miga%2C+M">Melanie Miga</a>, <a href="/search/cs?searchtype=author&query=Taulbee%2C+R">Richard Taulbee</a>, <a href="/search/cs?searchtype=author&query=Pidathala%2C+P">Pranav Pidathala</a>, <a href="/search/cs?searchtype=author&query=Glasser%2C+A">Abraham Glasser</a>, <a href="/search/cs?searchtype=author&query=Kushlanagar%2C+R">Raja Kushlanagar</a>, <a href="/search/cs?searchtype=author&query=Vogler%2C+C">Christian Vogler</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="2404.14610v1-abstract-short" style="display: inline;"> In this study, we assess the usability of interactive personal assistants (IPAs), such as Amazon Alexa, in a simulated kitchen smart home environment, with deaf and hard of hearing users. Participants engage in activities in a way that causes their hands to get dirty. With these dirty hands, they are tasked with two different input methods for IPAs: American Sign Language (ASL) in a Wizard-of-Oz d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14610v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14610v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14610v1-abstract-full" style="display: none;"> In this study, we assess the usability of interactive personal assistants (IPAs), such as Amazon Alexa, in a simulated kitchen smart home environment, with deaf and hard of hearing users. Participants engage in activities in a way that causes their hands to get dirty. With these dirty hands, they are tasked with two different input methods for IPAs: American Sign Language (ASL) in a Wizard-of-Oz design, and smart home apps with a touchscreen. Usability ratings show that participants significantly preferred ASL over touch-based apps with dirty hands, although not to a larger extent than in comparable previous work with clean hands. Participants also expressed significant enthusiasm for ASL-based IPA interaction in Netpromoter scores and in questions about their overall preferences. Preliminary observations further suggest that having dirty hands may affect the way people sign, which may pose challenges for building IPAs that natively support sign language input. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14610v1-abstract-full').style.display = 'none'; document.getElementById('2404.14610v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">To appear in Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA 2024, May 11-16, 2024, Honolulu, HI, USA. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3613905.3651075</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14605">arXiv:2404.14605</a> <span> [<a href="https://arxiv.org/pdf/2404.14605">pdf</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 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/10.1145/3613904.3642094">10.1145/3613904.3642094 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Assessment of Sign Language-Based versus Touch-Based Input for Deaf Users Interacting with Intelligent Personal Assistants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nina Tran</a>, <a href="/search/cs?searchtype=author&query=DeVries%2C+P">Paige DeVries</a>, <a href="/search/cs?searchtype=author&query=Seita%2C+M">Matthew Seita</a>, <a href="/search/cs?searchtype=author&query=Kushalnagar%2C+R">Raja Kushalnagar</a>, <a href="/search/cs?searchtype=author&query=Glasser%2C+A">Abraham Glasser</a>, <a href="/search/cs?searchtype=author&query=Vogler%2C+C">Christian Vogler</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="2404.14605v1-abstract-short" style="display: inline;"> With the recent advancements in intelligent personal assistants (IPAs), their popularity is rapidly increasing when it comes to utilizing Automatic Speech Recognition within households. In this study, we used a Wizard-of-Oz methodology to evaluate and compare the usability of American Sign Language (ASL), Tap to Alexa, and smart home apps among 23 deaf participants within a limited-domain smart ho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14605v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14605v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14605v1-abstract-full" style="display: none;"> With the recent advancements in intelligent personal assistants (IPAs), their popularity is rapidly increasing when it comes to utilizing Automatic Speech Recognition within households. In this study, we used a Wizard-of-Oz methodology to evaluate and compare the usability of American Sign Language (ASL), Tap to Alexa, and smart home apps among 23 deaf participants within a limited-domain smart home environment. Results indicate a slight usability preference for ASL. Linguistic analysis of the participants' signing reveals a diverse range of expressions and vocabulary as they interacted with IPAs in the context of a restricted-domain application. On average, deaf participants exhibited a vocabulary of 47 +/- 17 signs with an additional 10 +/- 7 fingerspelled words, for a total of 246 different signs and 93 different fingerspelled words across all participants. We discuss the implications for the design of limited-vocabulary applications as a stepping-stone toward general-purpose ASL recognition in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14605v1-abstract-full').style.display = 'none'; document.getElementById('2404.14605v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">To appear in Proceedings of the Conference on Human Factors in Computing Systems CHI 24, May 11-16, Honolulu, HI, USA, 15 pages. https://doi.org/10.1145/3613904.3642094</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.05393">arXiv:2404.05393</a> <span> [<a href="https://arxiv.org/pdf/2404.05393">pdf</a>, <a href="https://arxiv.org/format/2404.05393">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"> PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Do%2C+K">Khoi Do</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Duong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+D">Viet Dung Nguyen</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="2404.05393v4-abstract-short" style="display: inline;"> Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05393v4-abstract-full').style.display = 'inline'; document.getElementById('2404.05393v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05393v4-abstract-full" style="display: none;"> Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization, and 2) pixel-wise class-specific loss adaptation (PCLA). First, the class-wise gradient magnitude homogenization helps alleviate the imbalance among label masks by ensuring equal consideration of the class-wise impact on model updates. Second, PCLA tackles the detrimental impact of both rare classes within the long-tailed distribution and inaccurate predictions from previous training stages by encouraging learning classes with low prediction confidence and guarding against forgetting classes with high confidence. This combined approach fosters robust learning while preventing the model from forgetting previously learned knowledge. PAT exhibits significant performance improvements, surpassing the current state-of-the-art by 2.2% in the NyU dataset. Moreover, it enhances overall pixel-wise accuracy by 2.85% and intersection over union value by 2.07%, with a particularly notable declination of 0.39% in detecting rare classes compared to Balance Logits Variation, as demonstrated on the three popular datasets, i.e., OxfordPetIII, CityScape, and NYU. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05393v4-abstract-full').style.display = 'none'; document.getElementById('2404.05393v4-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">v1</span> submitted 8 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01530">arXiv:2404.01530</a> <span> [<a href="https://arxiv.org/pdf/2404.01530">pdf</a>, <a href="https://arxiv.org/format/2404.01530">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/EuCNC/6GSummit58263.2023.10188363">10.1109/EuCNC/6GSummit58263.2023.10188363 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> ML KPI Prediction in 5G and B5G Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+P">Nguyen Phuc Tran</a>, <a href="/search/cs?searchtype=author&query=Delgado%2C+O">Oscar Delgado</a>, <a href="/search/cs?searchtype=author&query=Jaumard%2C+B">Brigitte Jaumard</a>, <a href="/search/cs?searchtype=author&query=Bishay%2C+F">Fadi Bishay</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="2404.01530v1-abstract-short" style="display: inline;"> Network operators are facing new challenges when meeting the needs of their customers. The challenges arise due to the rise of new services, such as HD video streaming, IoT, autonomous driving, etc., and the exponential growth of network traffic. In this context, 5G and B5G networks have been evolving to accommodate a wide range of applications and use cases. Additionally, this evolution brings ne… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01530v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01530v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01530v1-abstract-full" style="display: none;"> Network operators are facing new challenges when meeting the needs of their customers. The challenges arise due to the rise of new services, such as HD video streaming, IoT, autonomous driving, etc., and the exponential growth of network traffic. In this context, 5G and B5G networks have been evolving to accommodate a wide range of applications and use cases. Additionally, this evolution brings new features, like the ability to create multiple end-to-end isolated virtual networks using network slicing. Nevertheless, to ensure the quality of service, operators must maintain and optimize their networks in accordance with the key performance indicators (KPIs) and the slice service-level agreements (SLAs). In this paper, we introduce a machine learning (ML) model used to estimate throughput in 5G and B5G networks with end-to-end (E2E) network slices. Then, we combine the predicted throughput with the current network state to derive an estimate of other network KPIs, which can be used to further improve service assurance. To assess the efficiency of our solution, a performance metric was proposed. Numerical evaluations demonstrate that our KPI prediction model outperforms those derived from other methods with the same or nearly the same computational time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01530v1-abstract-full').style.display = 'none'; document.getElementById('2404.01530v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01523">arXiv:2404.01523</a> <span> [<a href="https://arxiv.org/pdf/2404.01523">pdf</a>, <a href="https://arxiv.org/format/2404.01523">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Proactive Service Assurance in 5G and B5G Networks: A Closed-Loop Algorithm for End-to-End Network Slicing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+P">Nguyen Phuc Tran</a>, <a href="/search/cs?searchtype=author&query=Delgado%2C+O">Oscar Delgado</a>, <a href="/search/cs?searchtype=author&query=Jaumard%2C+B">Brigitte Jaumard</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="2404.01523v3-abstract-short" style="display: inline;"> The customization of services in Fifth-generation (5G) and Beyond 5G (B5G) networks relies heavily on network slicing, which creates multiple virtual networks on a shared physical infrastructure, tailored to meet specific requirements of distinct applications, using Software Defined Networking (SDN) and Network Function Virtualization (NFV). It is imperative to ensure that network services meet th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01523v3-abstract-full').style.display = 'inline'; document.getElementById('2404.01523v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01523v3-abstract-full" style="display: none;"> The customization of services in Fifth-generation (5G) and Beyond 5G (B5G) networks relies heavily on network slicing, which creates multiple virtual networks on a shared physical infrastructure, tailored to meet specific requirements of distinct applications, using Software Defined Networking (SDN) and Network Function Virtualization (NFV). It is imperative to ensure that network services meet the performance and reliability requirements of various applications and users, thus, service assurance is one of the critical components in network slicing. One of the key functionalities of network slicing is the ability to scale Virtualized Network Functions (VNFs) in response to changing resource demand and to meet Customer Service Level agreements (SLAs). In this paper, we introduce a proactive closed-loop algorithm for end-to-end network orchestration, designed to provide service assurance in 5G and B5G networks. We focus on dynamically scaling resources to meet key performance indicators (KPIs) specific to each network slice and operate in parallel across multiple slices, making it scalable and capable of managing completely automatically real-time service assurance. Through our experiments, we demonstrate that the proposed algorithm effectively fulfills service assurance requirements for different network slice types, thereby minimizing network resource utilization and reducing the over-provisioning of spare resources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01523v3-abstract-full').style.display = 'none'; document.getElementById('2404.01523v3-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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 work has been submitted to the IEEE 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/2403.18871">arXiv:2403.18871</a> <span> [<a href="https://arxiv.org/pdf/2403.18871">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.jbi.2024.104673">10.1016/j.jbi.2024.104673 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+H">Han Yuan</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C">Chuan Hong</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+P">Pengtao Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+G">Gangming Zhao</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+T+A">Nguyen Tuan Anh Tran</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xinxing Xu</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Y+Y">Yet Yen Yan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+N">Nan 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="2403.18871v1-abstract-short" style="display: inline;"> Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. To address the opaqueness often associated with deep learning (DL) models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax diagnoses made by DL models. However, these explanations sometimes diverge from actual le… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.18871v1-abstract-full').style.display = 'inline'; document.getElementById('2403.18871v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.18871v1-abstract-full" style="display: none;"> Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. To address the opaqueness often associated with deep learning (DL) models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax diagnoses made by DL models. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. Method: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of these explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods with and without our template guidance when explaining two DL models in two real-world datasets. Results: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. Conclusions: In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving AI explanations. We anticipate that our template guidance will forge a fresh approach to elucidating AI models by integrating clinical domain expertise. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.18871v1-abstract-full').style.display = 'none'; document.getElementById('2403.18871v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.12049">arXiv:2403.12049</a> <span> [<a href="https://arxiv.org/pdf/2403.12049">pdf</a>, <a href="https://arxiv.org/format/2403.12049">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"> Toward Improving Robustness of Object Detectors Against Domain Shift </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+L">Le-Anh Tran</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+C+N">Chung Nguyen Tran</a>, <a href="/search/cs?searchtype=author&query=Park%2C+D">Dong-Chul Park</a>, <a href="/search/cs?searchtype=author&query=Carrabina%2C+J">Jordi Carrabina</a>, <a href="/search/cs?searchtype=author&query=Castells-Rufas%2C+D">David Castells-Rufas</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="2403.12049v1-abstract-short" style="display: inline;"> This paper proposes a data augmentation method for improving the robustness of driving object detectors against domain shift. Domain shift problem arises when there is a significant change between the distribution of the source data domain used in the training phase and that of the target data domain in the deployment phase. Domain shift is known as one of the most popular reasons resulting in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12049v1-abstract-full').style.display = 'inline'; document.getElementById('2403.12049v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.12049v1-abstract-full" style="display: none;"> This paper proposes a data augmentation method for improving the robustness of driving object detectors against domain shift. Domain shift problem arises when there is a significant change between the distribution of the source data domain used in the training phase and that of the target data domain in the deployment phase. Domain shift is known as one of the most popular reasons resulting in the considerable drop in the performance of deep neural network models. In order to address this problem, one effective approach is to increase the diversity of training data. To this end, we propose a data synthesis module that can be utilized to train more robust and effective object detectors. By adopting YOLOv4 as a base object detector, we have witnessed a remarkable improvement in performance on both the source and target domain data. The code of this work is publicly available at https://github.com/tranleanh/haze-synthesis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12049v1-abstract-full').style.display = 'none'; document.getElementById('2403.12049v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.08980">arXiv:2403.08980</a> <span> [<a href="https://arxiv.org/pdf/2403.08980">pdf</a>, <a href="https://arxiv.org/format/2403.08980">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="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weng%2C+O">Olivia Weng</a>, <a href="/search/cs?searchtype=author&query=Redding%2C+A">Alexander Redding</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J+M">Javier Mauricio Duarte</a>, <a href="/search/cs?searchtype=author&query=Kastner%2C+R">Ryan Kastner</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="2403.08980v1-abstract-short" style="display: inline;"> With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters stored on-chip. In many of these applications, there is not enough time to go off-chip and retrieve weights. Even more so, off-chip memory such as DRAM does not have the bandwidth required to process these NNs as fast as… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08980v1-abstract-full').style.display = 'inline'; document.getElementById('2403.08980v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.08980v1-abstract-full" style="display: none;"> With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters stored on-chip. In many of these applications, there is not enough time to go off-chip and retrieve weights. Even more so, off-chip memory such as DRAM does not have the bandwidth required to process these NNs as fast as the data is being produced (e.g., every 25 ns). As such, these extreme latency and bandwidth requirements have architectural implications for the hardware intended to run these NNs: 1) all NN parameters must fit on-chip, and 2) codesigning custom/reconfigurable logic is often required to meet these latency and bandwidth constraints. In our work, we show that many scientific NN applications must run fully on chip, in the extreme case requiring a custom chip to meet such stringent constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08980v1-abstract-full').style.display = 'none'; document.getElementById('2403.08980v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.07027">arXiv:2403.07027</a> <span> [<a href="https://arxiv.org/pdf/2403.07027">pdf</a>, <a href="https://arxiv.org/ps/2403.07027">ps</a>, <a href="https://arxiv.org/format/2403.07027">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"> FWin transformer for dengue prediction under climate and ocean influence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+T">Nhat Thanh Tran</a>, <a href="/search/cs?searchtype=author&query=Xin%2C+J">Jack Xin</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+G">Guofa Zhou</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="2403.07027v1-abstract-short" style="display: inline;"> Dengue fever is one of the most deadly mosquito-born tropical infectious diseases. Detailed long range forecast model is vital in controlling the spread of disease and making mitigation efforts. In this study, we examine methods used to forecast dengue cases for long range predictions. The dataset consists of local climate/weather in addition to global climate indicators of Singapore from 2000 to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07027v1-abstract-full').style.display = 'inline'; document.getElementById('2403.07027v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.07027v1-abstract-full" style="display: none;"> Dengue fever is one of the most deadly mosquito-born tropical infectious diseases. Detailed long range forecast model is vital in controlling the spread of disease and making mitigation efforts. In this study, we examine methods used to forecast dengue cases for long range predictions. The dataset consists of local climate/weather in addition to global climate indicators of Singapore from 2000 to 2019. We utilize newly developed deep neural networks to learn the intricate relationship between the features. The baseline models in this study are in the class of recent transformers for long sequence forecasting tasks. We found that a Fourier mixed window attention (FWin) based transformer performed the best in terms of both the mean square error and the maximum absolute error on the long range dengue forecast up to 60 weeks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07027v1-abstract-full').style.display = 'none'; document.getElementById('2403.07027v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.13822">arXiv:2402.13822</a> <span> [<a href="https://arxiv.org/pdf/2402.13822">pdf</a>, <a href="https://arxiv.org/format/2402.13822">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"> MSTAR: Multi-Scale Backbone Architecture Search for Timeseries Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cao%2C+T+M">Tue M. Cao</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nhat H. Tran</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+H+H">Hieu H. Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+T">Hung T. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+P">Le P. Nguyen</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="2402.13822v1-abstract-short" style="display: inline;"> Most of the previous approaches to Time Series Classification (TSC) highlight the significance of receptive fields and frequencies while overlooking the time resolution. Hence, unavoidably suffered from scalability issues as they integrated an extensive range of receptive fields into classification models. Other methods, while having a better adaptation for large datasets, require manual design an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.13822v1-abstract-full').style.display = 'inline'; document.getElementById('2402.13822v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.13822v1-abstract-full" style="display: none;"> Most of the previous approaches to Time Series Classification (TSC) highlight the significance of receptive fields and frequencies while overlooking the time resolution. Hence, unavoidably suffered from scalability issues as they integrated an extensive range of receptive fields into classification models. Other methods, while having a better adaptation for large datasets, require manual design and yet not being able to reach the optimal architecture due to the uniqueness of each dataset. We overcome these challenges by proposing a novel multi-scale search space and a framework for Neural architecture search (NAS), which addresses both the problem of frequency and time resolution, discovering the suitable scale for a specific dataset. We further show that our model can serve as a backbone to employ a powerful Transformer module with both untrained and pre-trained weights. Our search space reaches the state-of-the-art performance on four datasets on four different domains while introducing more than ten highly fine-tuned models for each data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.13822v1-abstract-full').style.display = 'none'; document.getElementById('2402.13822v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07067">arXiv:2402.07067</a> <span> [<a href="https://arxiv.org/pdf/2402.07067">pdf</a>, <a href="https://arxiv.org/format/2402.07067">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learning the Expected Core of Strictly Convex Stochastic Cooperative Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N+P">Nam Phuong Tran</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+T+A">The Anh Ta</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+S">Shuqing Shi</a>, <a href="/search/cs?searchtype=author&query=Mandal%2C+D">Debmalya Mandal</a>, <a href="/search/cs?searchtype=author&query=Du%2C+Y">Yali Du</a>, <a href="/search/cs?searchtype=author&query=Tran-Thanh%2C+L">Long Tran-Thanh</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="2402.07067v3-abstract-short" style="display: inline;"> Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in reward allocation is the core, which is the set of stable allocations where no agent has the motivation to deviate from the grand coalition. In previous works, computing the core requires either knowledge of the reward function in dete… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07067v3-abstract-full').style.display = 'inline'; document.getElementById('2402.07067v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07067v3-abstract-full" style="display: none;"> Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in reward allocation is the core, which is the set of stable allocations where no agent has the motivation to deviate from the grand coalition. In previous works, computing the core requires either knowledge of the reward function in deterministic games or the reward distribution in stochastic games. However, this is unrealistic, as the reward function or distribution is often only partially known and may be subject to uncertainty. In this paper, we consider the core learning problem in stochastic cooperative games, where the reward distribution is unknown. Our goal is to learn the expected core, that is, the set of allocations that are stable in expectation, given an oracle that returns a stochastic reward for an enquired coalition each round. Within the class of strictly convex games, we present an algorithm named \texttt{Common-Points-Picking} that returns a point in the expected core given a polynomial number of samples, with high probability. To analyse the algorithm, we develop a new extension of the separation hyperplane theorem for multiple convex sets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07067v3-abstract-full').style.display = 'none'; document.getElementById('2402.07067v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.05498">arXiv:2402.05498</a> <span>  </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"> A Solution for Commercializing, Decentralizing and Storing Electronic Medical Records by Integrating Proxy Re-Encryption, IPFS, and Blockchain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+P">Phong Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Thong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+L">Long Chu</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhi Tran</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+H">Hang Ta</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="2402.05498v2-abstract-short" style="display: inline;"> The rapid expansion of user medical records across global systems presents not only opportunities but also new challenges in maintaining effective application models that ensure user privacy, controllability, and the ability to commercialize patient medical records. Moreover, the proliferation of data analysis models in healthcare institutions necessitates the decentralization and restorability of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05498v2-abstract-full').style.display = 'inline'; document.getElementById('2402.05498v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.05498v2-abstract-full" style="display: none;"> The rapid expansion of user medical records across global systems presents not only opportunities but also new challenges in maintaining effective application models that ensure user privacy, controllability, and the ability to commercialize patient medical records. Moreover, the proliferation of data analysis models in healthcare institutions necessitates the decentralization and restorability of medical record data. It is imperative that user medical data collected from these systems can be easily analyzed and utilized even years after collection, without the risk of data loss due to numerous factors. Additionally, medical information must be authorized by the data owner, granting patients the right to accept or decline data usage requests from medical research agencies. In response, we propose an innovative solution for implementing a decentralized system utilizing an EVM-compatible blockchain and IPFS for decentralized storage. To ensure privacy and control, we employ Proxy Re-Encryption (PRE), a cryptographic authorized method, within the medical data marketplace. Our proposed architecture significantly reduces costs associated with granting read access to healthcare research agencies by minimizing the encryption and decryption time of stored records. Furthermore, it empowers users with enhanced control over their health data through tamperproof blockchain smart contracts and IPFS, safeguarding the integrity and privacy of their medical records. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05498v2-abstract-full').style.display = 'none'; document.getElementById('2402.05498v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">Withdrawn due to lack of consensus among authors</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.05484">arXiv:2402.05484</a> <span> [<a href="https://arxiv.org/pdf/2402.05484">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Leveraging AI for Enhanced Software Effort Estimation: A Comprehensive Study and Framework Proposal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhi Tran</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+T">Tan Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N">Nam Nguyen</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="2402.05484v1-abstract-short" style="display: inline;"> This paper presents an extensive study on the application of AI techniques for software effort estimation in the past five years from 2017 to 2023. By overcoming the limitations of traditional methods, the study aims to improve accuracy and reliability. Through performance evaluation and comparison with diverse Machine Learning models, including Artificial Neural Network (ANN), Support Vector Mach… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05484v1-abstract-full').style.display = 'inline'; document.getElementById('2402.05484v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.05484v1-abstract-full" style="display: none;"> This paper presents an extensive study on the application of AI techniques for software effort estimation in the past five years from 2017 to 2023. By overcoming the limitations of traditional methods, the study aims to improve accuracy and reliability. Through performance evaluation and comparison with diverse Machine Learning models, including Artificial Neural Network (ANN), Support Vector Machine (SVM), Linear Regression, Random Forest and other techniques, the most effective method is identified. The proposed AI-based framework holds the potential to enhance project planning and resource allocation, contributing to the research area of software project effort estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05484v1-abstract-full').style.display = 'none'; document.getElementById('2402.05484v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.08777">arXiv:2401.08777</a> <span> [<a href="https://arxiv.org/pdf/2401.08777">pdf</a>, <a href="https://arxiv.org/format/2401.08777">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Phenomenology">hep-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> </div> </div> <p class="title is-5 mathjax"> Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gandrakota%2C+A">Abhijith Gandrakota</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lily Zhang</a>, <a href="/search/cs?searchtype=author&query=Puli%2C+A">Aahlad Puli</a>, <a href="/search/cs?searchtype=author&query=Cranmer%2C+K">Kyle Cranmer</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Ranganath%2C+R">Rajesh Ranganath</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</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="2401.08777v1-abstract-short" style="display: inline;"> Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08777v1-abstract-full').style.display = 'inline'; document.getElementById('2401.08777v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08777v1-abstract-full" style="display: none;"> Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for anomaly detection. We demonstrate the benefit of the proposed robust multi-background anomaly detection algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08777v1-abstract-full').style.display = 'none'; document.getElementById('2401.08777v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-23-675-CMS-CSAID </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.06406">arXiv:2401.06406</a> <span> [<a href="https://arxiv.org/pdf/2401.06406">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis: A review </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mao%2C+L">Lingchao Mao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hairong Wang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L+S">Leland S. Hu</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+L">Nhan L Tran</a>, <a href="/search/cs?searchtype=author&query=Canoll%2C+P+D">Peter D Canoll</a>, <a href="/search/cs?searchtype=author&query=Swanson%2C+K+R">Kristin R Swanson</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jing Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.06406v1-abstract-short" style="display: inline;"> Cancer remains one of the most challenging diseases to treat in the medical field. Machine learning has enabled in-depth analysis of rich multi-omics profiles and medical imaging for cancer diagnosis and prognosis. Despite these advancements, machine learning models face challenges stemming from limited labeled sample sizes, the intricate interplay of high-dimensionality data types, the inherent h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06406v1-abstract-full').style.display = 'inline'; document.getElementById('2401.06406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.06406v1-abstract-full" style="display: none;"> Cancer remains one of the most challenging diseases to treat in the medical field. Machine learning has enabled in-depth analysis of rich multi-omics profiles and medical imaging for cancer diagnosis and prognosis. Despite these advancements, machine learning models face challenges stemming from limited labeled sample sizes, the intricate interplay of high-dimensionality data types, the inherent heterogeneity observed among patients and within tumors, and concerns about interpretability and consistency with existing biomedical knowledge. One approach to surmount these challenges is to integrate biomedical knowledge into data-driven models, which has proven potential to improve the accuracy, robustness, and interpretability of model results. Here, we review the state-of-the-art machine learning studies that adopted the fusion of biomedical knowledge and data, termed knowledge-informed machine learning, for cancer diagnosis and prognosis. Emphasizing the properties inherent in four primary data types including clinical, imaging, molecular, and treatment data, we highlight modeling considerations relevant to these contexts. We provide an overview of diverse forms of knowledge representation and current strategies of knowledge integration into machine learning pipelines with concrete examples. We conclude the review article by discussing future directions to advance cancer research through knowledge-informed machine learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06406v1-abstract-full').style.display = 'none'; document.getElementById('2401.06406v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">41 pages, 4 figures, 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 92B99 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.00128">arXiv:2401.00128</a> <span> [<a href="https://arxiv.org/pdf/2401.00128">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+L">Lujia Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hairong Wang</a>, <a href="/search/cs?searchtype=author&query=D%27Angelo%2C+F">Fulvio D'Angelo</a>, <a href="/search/cs?searchtype=author&query=Curtin%2C+L">Lee Curtin</a>, <a href="/search/cs?searchtype=author&query=Sereduk%2C+C+P">Christopher P. Sereduk</a>, <a href="/search/cs?searchtype=author&query=De+Leon%2C+G">Gustavo De Leon</a>, <a href="/search/cs?searchtype=author&query=Singleton%2C+K+W">Kyle W. Singleton</a>, <a href="/search/cs?searchtype=author&query=Urcuyo%2C+J">Javier Urcuyo</a>, <a href="/search/cs?searchtype=author&query=Hawkins-Daarud%2C+A">Andrea Hawkins-Daarud</a>, <a href="/search/cs?searchtype=author&query=Jackson%2C+P+R">Pamela R. Jackson</a>, <a href="/search/cs?searchtype=author&query=Krishna%2C+C">Chandan Krishna</a>, <a href="/search/cs?searchtype=author&query=Zimmerman%2C+R+S">Richard S. Zimmerman</a>, <a href="/search/cs?searchtype=author&query=Patra%2C+D+P">Devi P. Patra</a>, <a href="/search/cs?searchtype=author&query=Bendok%2C+B+R">Bernard R. Bendok</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+K+A">Kris A. Smith</a>, <a href="/search/cs?searchtype=author&query=Nakaji%2C+P">Peter Nakaji</a>, <a href="/search/cs?searchtype=author&query=Donev%2C+K">Kliment Donev</a>, <a href="/search/cs?searchtype=author&query=Baxter%2C+L+C">Leslie C. Baxter</a>, <a href="/search/cs?searchtype=author&query=Mruga%C5%82a%2C+M+M">Maciej M. Mruga艂a</a>, <a href="/search/cs?searchtype=author&query=Ceccarelli%2C+M">Michele Ceccarelli</a>, <a href="/search/cs?searchtype=author&query=Iavarone%2C+A">Antonio Iavarone</a>, <a href="/search/cs?searchtype=author&query=Swanson%2C+K+R">Kristin R. Swanson</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+L">Nhan L. Tran</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L+S">Leland S. Hu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jing Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.00128v1-abstract-short" style="display: inline;"> Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic se… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.00128v1-abstract-full').style.display = 'inline'; document.getElementById('2401.00128v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.00128v1-abstract-full" style="display: none;"> Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcomes. We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA, and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. The classification accuracy of each gene was compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.00128v1-abstract-full').style.display = 'none'; document.getElementById('2401.00128v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">36 pages, 8 figures, 3 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/2312.17372">arXiv:2312.17372</a> <span> [<a href="https://arxiv.org/pdf/2312.17372">pdf</a>, <a href="https://arxiv.org/format/2312.17372">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="Accelerator Physics">physics.acc-ph</span> </div> </div> <p class="title is-5 mathjax"> Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+C">Chenwei Xu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J+Y">Jerry Yao-Chieh Hu</a>, <a href="/search/cs?searchtype=author&query=Narayanan%2C+A">Aakaash Narayanan</a>, <a href="/search/cs?searchtype=author&query=Thieme%2C+M">Mattson Thieme</a>, <a href="/search/cs?searchtype=author&query=Nagaslaev%2C+V">Vladimir Nagaslaev</a>, <a href="/search/cs?searchtype=author&query=Austin%2C+M">Mark Austin</a>, <a href="/search/cs?searchtype=author&query=Arnold%2C+J">Jeremy Arnold</a>, <a href="/search/cs?searchtype=author&query=Berlioz%2C+J">Jose Berlioz</a>, <a href="/search/cs?searchtype=author&query=Hanlet%2C+P">Pierrick Hanlet</a>, <a href="/search/cs?searchtype=author&query=Ibrahim%2C+A">Aisha Ibrahim</a>, <a href="/search/cs?searchtype=author&query=Nicklaus%2C+D">Dennis Nicklaus</a>, <a href="/search/cs?searchtype=author&query=Mitrevski%2C+J">Jovan Mitrevski</a>, <a href="/search/cs?searchtype=author&query=John%2C+J+M+S">Jason Michael St. John</a>, <a href="/search/cs?searchtype=author&query=Pradhan%2C+G">Gauri Pradhan</a>, <a href="/search/cs?searchtype=author&query=Saewert%2C+A">Andrea Saewert</a>, <a href="/search/cs?searchtype=author&query=Seiya%2C+K">Kiyomi Seiya</a>, <a href="/search/cs?searchtype=author&query=Schupbach%2C+B">Brian Schupbach</a>, <a href="/search/cs?searchtype=author&query=Thurman-Keup%2C+R">Randy Thurman-Keup</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+R">Rui Shi</a>, <a href="/search/cs?searchtype=author&query=Ogrenci%2C+S">Seda Ogrenci</a>, <a href="/search/cs?searchtype=author&query=Shuping%2C+A+M">Alexis Maya-Isabelle Shuping</a>, <a href="/search/cs?searchtype=author&query=Hazelwood%2C+K">Kyle Hazelwood</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Han 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="2312.17372v1-abstract-short" style="display: inline;"> We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron Conversion Experiment (Mu2e) at Fermi National Accelerator Laboratory (Fermilab). Our primary objective is to regulate the spill process to ensure a consistent intensity profile, with the ultimate goal of creating an aut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17372v1-abstract-full').style.display = 'inline'; document.getElementById('2312.17372v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.17372v1-abstract-full" style="display: none;"> We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron Conversion Experiment (Mu2e) at Fermi National Accelerator Laboratory (Fermilab). Our primary objective is to regulate the spill process to ensure a consistent intensity profile, with the ultimate goal of creating an automated controller capable of providing real-time feedback and calibration of the Spill Regulation System (SRS) parameters on a millisecond timescale. We treat the Mu2e accelerator system as a Markov Decision Process suitable for Reinforcement Learning (RL), utilizing PPO to reduce bias and enhance training stability. A key innovation in our approach is the integration of a neuralized Proportional-Integral-Derivative (PID) controller into the policy function, resulting in a significant improvement in the Spill Duty Factor (SDF) by 13.6%, surpassing the performance of the current PID controller baseline by an additional 1.6%. This paper presents the preliminary offline results based on a differentiable simulator of the Mu2e accelerator. It paves the groundwork for real-time implementations and applications, representing a crucial step towards automated proton beam intensity control for the Mu2e experiment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17372v1-abstract-full').style.display = 'none'; document.getElementById('2312.17372v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </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, accepted at NeurIPS 2023 ML4Phy Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.17255">arXiv:2312.17255</a> <span> [<a href="https://arxiv.org/pdf/2312.17255">pdf</a>, <a href="https://arxiv.org/format/2312.17255">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Single-channel speech enhancement using learnable loss mixup </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chang%2C+O">Oscar Chang</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+D+N">Dung N. Tran</a>, <a href="/search/cs?searchtype=author&query=Koishida%2C+K">Kazuhito Koishida</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="2312.17255v1-abstract-short" style="display: inline;"> Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless training diagram, to improve the generalization of deep learning-based speech enhancement models. Loss mixup, of which learnable loss mixup is a special variant, optimizes a mixture of the loss functions of random sample pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17255v1-abstract-full').style.display = 'inline'; document.getElementById('2312.17255v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.17255v1-abstract-full" style="display: none;"> Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless training diagram, to improve the generalization of deep learning-based speech enhancement models. Loss mixup, of which learnable loss mixup is a special variant, optimizes a mixture of the loss functions of random sample pairs to train a model on virtual training data constructed from these pairs of samples. In learnable loss mixup, by conditioning on the mixed data, the loss functions are mixed using a non-linear mixing function automatically learned via neural parameterization. Our experimental results on the VCTK benchmark show that learnable loss mixup achieves 3.26 PESQ, outperforming the state-of-the-art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17255v1-abstract-full').style.display = 'none'; document.getElementById('2312.17255v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.09445">arXiv:2312.09445</a> <span> [<a href="https://arxiv.org/pdf/2312.09445">pdf</a>, <a href="https://arxiv.org/format/2312.09445">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> IncepSE: Leveraging InceptionTime's performance with Squeeze and Excitation mechanism in ECG analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cao%2C+T+M">Tue Minh Cao</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nhat Hong Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+P">Le Phi Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+H+H">Hieu Huy Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+T">Hung Thanh Nguyen</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="2312.09445v1-abstract-short" style="display: inline;"> Our study focuses on the potential for modifications of Inception-like architecture within the electrocardiogram (ECG) domain. To this end, we introduce IncepSE, a novel network characterized by strategic architectural incorporation that leverages the strengths of both InceptionTime and channel attention mechanisms. Furthermore, we propose a training setup that employs stabilization techniques tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09445v1-abstract-full').style.display = 'inline'; document.getElementById('2312.09445v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.09445v1-abstract-full" style="display: none;"> Our study focuses on the potential for modifications of Inception-like architecture within the electrocardiogram (ECG) domain. To this end, we introduce IncepSE, a novel network characterized by strategic architectural incorporation that leverages the strengths of both InceptionTime and channel attention mechanisms. Furthermore, we propose a training setup that employs stabilization techniques that are aimed at tackling the formidable challenges of severe imbalance dataset PTB-XL and gradient corruption. By this means, we manage to set a new height for deep learning model in a supervised learning manner across the majority of tasks. Our model consistently surpasses InceptionTime by substantial margins compared to other state-of-the-arts in this domain, noticeably 0.013 AUROC score improvement in the "all" task, while also mitigating the inherent dataset fluctuations during training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09445v1-abstract-full').style.display = 'none'; document.getElementById('2312.09445v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </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=Tran%2C+N&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Tran%2C+N&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </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