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 440 results for author: <span class="mathjax">Mukherjee, S</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=Mukherjee%2C+S">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="Mukherjee, S"> </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=Mukherjee%2C+S&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="Mukherjee, S"> <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=Mukherjee%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.13333">arXiv:2502.13333</a> <span> [<a href="https://arxiv.org/pdf/2502.13333">pdf</a>, <a href="https://arxiv.org/format/2502.13333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</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"> An Uncertainty-Aware Data-Driven Predictive Controller for Hybrid Power Plants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Desai%2C+M">Manavendra Desai</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+H">Himanshu Sharma</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Glavaski%2C+S">Sonja Glavaski</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="2502.13333v1-abstract-short" style="display: inline;"> Given the advancements in data-driven modeling for complex engineering and scientific applications, this work utilizes a data-driven predictive control method, namely subspace predictive control, to coordinate hybrid power plant components and meet a desired power demand despite the presence of weather uncertainties. An uncertainty-aware data-driven predictive controller is proposed, and its poten… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13333v1-abstract-full').style.display = 'inline'; document.getElementById('2502.13333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.13333v1-abstract-full" style="display: none;"> Given the advancements in data-driven modeling for complex engineering and scientific applications, this work utilizes a data-driven predictive control method, namely subspace predictive control, to coordinate hybrid power plant components and meet a desired power demand despite the presence of weather uncertainties. An uncertainty-aware data-driven predictive controller is proposed, and its potential is analyzed using real-world electricity demand profiles. For the analysis, a hybrid power plant with wind, solar, and co-located energy storage capacity of 4 MW each is considered. The analysis shows that the predictive controller can track a real-world-inspired electricity demand profile despite the presence of weather-induced uncertainties and be an intelligent forecaster for HPP performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.13333v1-abstract-full').style.display = 'none'; document.getElementById('2502.13333v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11767">arXiv:2502.11767</a> <span> [<a href="https://arxiv.org/pdf/2502.11767">pdf</a>, <a href="https://arxiv.org/format/2502.11767">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> From Selection to Generation: A Survey of LLM-based Active Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhojyoti Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Z">Zhouhang Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xintong Li</a>, <a href="/search/cs?searchtype=author&query=Aponte%2C+R">Ryan Aponte</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+H">Hanjia Lyu</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongjie Chen</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Kveton%2C+B">Branislav Kveton</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhengmian Hu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yue Zhao</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+T+K">Ting-Hao Kenneth Huang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zichao Wang</a> , et al. (9 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="2502.11767v1-abstract-short" style="display: inline;"> Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generating entirely new data instances and providing more cost-effective annotations. Motivated by the incre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11767v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11767v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11767v1-abstract-full" style="display: none;"> Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generating entirely new data instances and providing more cost-effective annotations. Motivated by the increasing importance of high-quality data and efficient model training in the era of LLMs, we present a comprehensive survey on LLM-based Active Learning. We introduce an intuitive taxonomy that categorizes these techniques and discuss the transformative roles LLMs can play in the active learning loop. We further examine the impact of AL on LLM learning paradigms and its applications across various domains. Finally, we identify open challenges and propose future research directions. This survey aims to serve as an up-to-date resource for researchers and practitioners seeking to gain an intuitive understanding of LLM-based AL techniques and deploy them to new applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11767v1-abstract-full').style.display = 'none'; document.getElementById('2502.11767v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09341">arXiv:2502.09341</a> <span> [<a href="https://arxiv.org/pdf/2502.09341">pdf</a>, <a href="https://arxiv.org/format/2502.09341">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"> Neural Spatiotemporal Point Processes: Trends and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumantrak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Elhamdi%2C+M">Mouad Elhamdi</a>, <a href="/search/cs?searchtype=author&query=Mohler%2C+G">George Mohler</a>, <a href="/search/cs?searchtype=author&query=Selby%2C+D+A">David A. Selby</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Yao Xie</a>, <a href="/search/cs?searchtype=author&query=Vollmer%2C+S">Sebastian Vollmer</a>, <a href="/search/cs?searchtype=author&query=Grossmann%2C+G">Gerrit Grossmann</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="2502.09341v1-abstract-short" style="display: inline;"> Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit intricate dependencies and heterogeneous dynamics. By incorporating modern deep learning techniques, STPPs can model these complexities more effectively than traditional approaches. Consequently, the fusion of neural methods with STPPs has become an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09341v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09341v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09341v1-abstract-full" style="display: none;"> Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit intricate dependencies and heterogeneous dynamics. By incorporating modern deep learning techniques, STPPs can model these complexities more effectively than traditional approaches. Consequently, the fusion of neural methods with STPPs has become an active and rapidly evolving research area. In this review, we categorize existing approaches, unify key design choices, and explain the challenges of working with this data modality. We further highlight emerging trends and diverse application domains. Finally, we identify open challenges and gaps in the literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09341v1-abstract-full').style.display = 'none'; document.getElementById('2502.09341v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.08233">arXiv:2502.08233</a> <span> [<a href="https://arxiv.org/pdf/2502.08233">pdf</a>, <a href="https://arxiv.org/format/2502.08233">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"> Plantation Monitoring Using Drone Images: A Dataset and Performance Review </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karumanchi%2C+Y">Yashwanth Karumanchi</a>, <a href="/search/cs?searchtype=author&query=Prasanna%2C+G+L">Gudala Laxmi Prasanna</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Snehasis Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Kolagani%2C+N">Nagesh Kolagani</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="2502.08233v1-abstract-short" style="display: inline;"> Automatic monitoring of tree plantations plays a crucial role in agriculture. Flawless monitoring of tree health helps farmers make informed decisions regarding their management by taking appropriate action. Use of drone images for automatic plantation monitoring can enhance the accuracy of the monitoring process, while still being affordable to small farmers in developing countries such as India.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08233v1-abstract-full').style.display = 'inline'; document.getElementById('2502.08233v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08233v1-abstract-full" style="display: none;"> Automatic monitoring of tree plantations plays a crucial role in agriculture. Flawless monitoring of tree health helps farmers make informed decisions regarding their management by taking appropriate action. Use of drone images for automatic plantation monitoring can enhance the accuracy of the monitoring process, while still being affordable to small farmers in developing countries such as India. Small, low cost drones equipped with an RGB camera can capture high-resolution images of agricultural fields, allowing for detailed analysis of the well-being of the plantations. Existing methods of automated plantation monitoring are mostly based on satellite images, which are difficult to get for the farmers. We propose an automated system for plantation health monitoring using drone images, which are becoming easier to get for the farmers. We propose a dataset of images of trees with three categories: ``Good health", ``Stunted", and ``Dead". We annotate the dataset using CVAT annotation tool, for use in research purposes. We experiment with different well-known CNN models to observe their performance on the proposed dataset. The initial low accuracy levels show the complexity of the proposed dataset. Further, our study revealed that, depth-wise convolution operation embedded in a deep CNN model, can enhance the performance of the model on drone dataset. Further, we apply state-of-the-art object detection models to identify individual trees to better monitor them automatically. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08233v1-abstract-full').style.display = 'none'; document.getElementById('2502.08233v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.07369">arXiv:2502.07369</a> <span> [<a href="https://arxiv.org/pdf/2502.07369">pdf</a>, <a href="https://arxiv.org/format/2502.07369">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> </div> </div> <p class="title is-5 mathjax"> Uniform Kernel Prober </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Soumya Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Sriperumbudur%2C+B+K">Bharath K. Sriperumbudur</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="2502.07369v1-abstract-short" style="display: inline;"> The ability to identify useful features or representations of the input data based on training data that achieves low prediction error on test data across multiple prediction tasks is considered the key to multitask learning success. In practice, however, one faces the issue of the choice of prediction tasks and the availability of test data from the chosen tasks while comparing the relative perfo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07369v1-abstract-full').style.display = 'inline'; document.getElementById('2502.07369v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.07369v1-abstract-full" style="display: none;"> The ability to identify useful features or representations of the input data based on training data that achieves low prediction error on test data across multiple prediction tasks is considered the key to multitask learning success. In practice, however, one faces the issue of the choice of prediction tasks and the availability of test data from the chosen tasks while comparing the relative performance of different features. In this work, we develop a class of pseudometrics called Uniform Kernel Prober (UKP) for comparing features or representations learned by different statistical models such as neural networks when the downstream prediction tasks involve kernel ridge regression. The proposed pseudometric, UKP, between any two representations, provides a uniform measure of prediction error on test data corresponding to a general class of kernel ridge regression tasks for a given choice of a kernel without access to test data. Additionally, desired invariances in representations can be successfully captured by UKP only through the choice of the kernel function and the pseudometric can be efficiently estimated from $n$ input data samples with $O(\frac{1}{\sqrt{n}})$ estimation error. We also experimentally demonstrate the ability of UKP to discriminate between different types of features or representations based on their generalization performance on downstream kernel ridge regression tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07369v1-abstract-full').style.display = 'none'; document.getElementById('2502.07369v1-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 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">34 pages, 10 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/2502.06806">arXiv:2502.06806</a> <span> [<a href="https://arxiv.org/pdf/2502.06806">pdf</a>, <a href="https://arxiv.org/format/2502.06806">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Logits are All We Need to Adapt Closed Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hiranandani%2C+G">Gaurush Hiranandani</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Haolun Wu</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhojyoti Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Koyejo%2C+S">Sanmi Koyejo</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="2502.06806v2-abstract-short" style="display: inline;"> Many commercial Large Language Models (LLMs) are often closed-source, limiting developers to prompt tuning for aligning content generation with specific applications. While these models currently do not provide access to token logits, we argue that if such access were available, it would enable more powerful adaptation techniques beyond prompt engineering. In this paper, we propose a token-level p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06806v2-abstract-full').style.display = 'inline'; document.getElementById('2502.06806v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.06806v2-abstract-full" style="display: none;"> Many commercial Large Language Models (LLMs) are often closed-source, limiting developers to prompt tuning for aligning content generation with specific applications. While these models currently do not provide access to token logits, we argue that if such access were available, it would enable more powerful adaptation techniques beyond prompt engineering. In this paper, we propose a token-level probability reweighting framework that, given access to logits and a small amount of task-specific data, can effectively steer black-box LLMs toward application-specific content generation. Our approach views next-token prediction through the lens of supervised classification. We show that aligning black-box LLMs with task-specific data can be formulated as a label noise correction problem, leading to \emph{Plugin} model -- an autoregressive probability reweighting model that operates solely on logits. We provide theoretical justification for why reweighting logits alone is sufficient for task adaptation. Extensive experiments with multiple datasets, LLMs, and reweighting models demonstrate the effectiveness of our method, advocating for broader access to token logits in closed-source models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06806v2-abstract-full').style.display = 'none'; document.getElementById('2502.06806v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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">33 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.04718">arXiv:2502.04718</a> <span> [<a href="https://arxiv.org/pdf/2502.04718">pdf</a>, <a href="https://arxiv.org/format/2502.04718">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"> Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ojha%2C+A+K">Atul Kr. Ojha</a>, <a href="/search/cs?searchtype=author&query=McCrae%2C+J+P">John P. McCrae</a>, <a href="/search/cs?searchtype=author&query=Dusek%2C+O">Ondrej Dusek</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="2502.04718v1-abstract-short" style="display: inline;"> Text Style Transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy, content preservation, and naturalness. Using human evaluation is ideal but costly, same as in other natural language processing (NLP) tasks, however, automatic m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04718v1-abstract-full').style.display = 'inline'; document.getElementById('2502.04718v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.04718v1-abstract-full" style="display: none;"> Text Style Transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy, content preservation, and naturalness. Using human evaluation is ideal but costly, same as in other natural language processing (NLP) tasks, however, automatic metrics for TST have not received as much attention as metrics for, e.g., machine translation or summarization. In this paper, we examine both set of existing and novel metrics from broader NLP tasks for TST evaluation, focusing on two popular subtasks-sentiment transfer and detoxification-in a multilingual context comprising English, Hindi, and Bengali. By conducting meta-evaluation through correlation with human judgments, we demonstrate the effectiveness of these metrics when used individually and in ensembles. Additionally, we investigate the potential of Large Language Models (LLMs) as tools for TST evaluation. Our findings highlight that certain advanced NLP metrics and experimental-hybrid-techniques, provide better insights than existing TST metrics for delivering more accurate, consistent, and reproducible TST evaluations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04718v1-abstract-full').style.display = 'none'; document.getElementById('2502.04718v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.02668">arXiv:2502.02668</a> <span> [<a href="https://arxiv.org/pdf/2502.02668">pdf</a>, <a href="https://arxiv.org/ps/2502.02668">ps</a>, <a href="https://arxiv.org/format/2502.02668">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"> Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eppert%2C+M">Martin Eppert</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Satyaki Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ghoshdastidar%2C+D">Debarghya Ghoshdastidar</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="2502.02668v1-abstract-short" style="display: inline;"> Projection Pursuit is a classic exploratory technique for finding interesting projections of a dataset. We propose a method for recovering projections containing either Imbalanced Clusters or a Bernoulli-Rademacher distribution using a gradient-based technique to optimize the projection index. As sample complexity is a major limiting factor in Projection Pursuit, we analyze our algorithm's sample… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02668v1-abstract-full').style.display = 'inline'; document.getElementById('2502.02668v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.02668v1-abstract-full" style="display: none;"> Projection Pursuit is a classic exploratory technique for finding interesting projections of a dataset. We propose a method for recovering projections containing either Imbalanced Clusters or a Bernoulli-Rademacher distribution using a gradient-based technique to optimize the projection index. As sample complexity is a major limiting factor in Projection Pursuit, we analyze our algorithm's sample complexity within a Planted Vector setting where we can observe that Imbalanced Clusters can be recovered more easily than balanced ones. Additionally, we give a generalized result that works for a variety of data distributions and projection indices. We compare these results to computational lower bounds in the Low-Degree-Polynomial Framework. Finally, we experimentally evaluate our method's applicability to real-world data using FashionMNIST and the Human Activity Recognition Dataset, where our algorithm outperforms others when only a few samples are available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02668v1-abstract-full').style.display = 'none'; document.getElementById('2502.02668v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.02362">arXiv:2502.02362</a> <span> [<a href="https://arxiv.org/pdf/2502.02362">pdf</a>, <a href="https://arxiv.org/format/2502.02362">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"> Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sagnik Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Chinta%2C+A">Abhinav Chinta</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+T">Takyoung Kim</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+T+A">Tarun Anoop Sharma</a>, <a href="/search/cs?searchtype=author&query=Hakkani-T%C3%BCr%2C+D">Dilek Hakkani-T眉r</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="2502.02362v3-abstract-short" style="display: inline;"> Chain-of-Thought (CoT) prompting enhances mathematical reasoning in large language models (LLMs) by enabling detailed step-by-step solutions. However, due to the verbosity of LLMs, the resulting reasoning chains can be long, making it harder to verify the reasoning steps and trace issues resulting from dependencies between the steps that may be farther away in the sequence of steps. Importantly, m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02362v3-abstract-full').style.display = 'inline'; document.getElementById('2502.02362v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.02362v3-abstract-full" style="display: none;"> Chain-of-Thought (CoT) prompting enhances mathematical reasoning in large language models (LLMs) by enabling detailed step-by-step solutions. However, due to the verbosity of LLMs, the resulting reasoning chains can be long, making it harder to verify the reasoning steps and trace issues resulting from dependencies between the steps that may be farther away in the sequence of steps. Importantly, mathematical reasoning allows each step to be derived from a small set of premises, which are a subset of the preceding steps in the reasoning chain. In this paper, we present a framework that identifies the premises for each step, to improve the evaluation of reasoning. We restructure conventional linear reasoning chains into Premise Augmented Reasoning Chains (PARC) by introducing premise links, resulting in a directed acyclic graph where the nodes are the steps and the edges are the premise links. Through experiments with a PARC-based dataset that we built, namely PERL (Premises and ERrors identification in LLMs), we demonstrate that LLMs can reliably identify premises within complex reasoning chains. In particular, even open-source LLMs achieve 90% recall in premise identification. We also show that PARC helps to identify errors in reasoning chains more reliably. The accuracy of error identification improves by 6% to 16% absolute when step-by-step verification is carried out in PARC under the premises. Our findings highlight the utility of premise-centric representations in addressing complex problem-solving tasks and open new avenues for improving the reliability of LLM-based reasoning evaluations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02362v3-abstract-full').style.display = 'none'; document.getElementById('2502.02362v3-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">v1</span> submitted 4 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.00968">arXiv:2502.00968</a> <span> [<a href="https://arxiv.org/pdf/2502.00968">pdf</a>, <a href="https://arxiv.org/format/2502.00968">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> CoDe: Blockwise Control for Denoising Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Anuj Singh</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Beirami%2C+A">Ahmad Beirami</a>, <a href="/search/cs?searchtype=author&query=Jamali-Rad%2C+H">Hadi Jamali-Rad</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="2502.00968v1-abstract-short" style="display: inline;"> Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time gradient-free guidance approach, called controlled denoising (CoDe), that circumvents the need for differentiable guidance functions and model finetuning. CoDe is a block… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00968v1-abstract-full').style.display = 'inline'; document.getElementById('2502.00968v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.00968v1-abstract-full" style="display: none;"> Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time gradient-free guidance approach, called controlled denoising (CoDe), that circumvents the need for differentiable guidance functions and model finetuning. CoDe is a blockwise sampling method applied during intermediate denoising steps, allowing for alignment with downstream rewards. Our experiments demonstrate that, despite its simplicity, CoDe offers a favorable trade-off between reward alignment, prompt instruction following, and inference cost, achieving a competitive performance against the state-of-the-art baselines. Our code is available at: https://github.com/anujinho/code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00968v1-abstract-full').style.display = 'none'; document.getElementById('2502.00968v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.19283">arXiv:2501.19283</a> <span> [<a href="https://arxiv.org/pdf/2501.19283">pdf</a>, <a href="https://arxiv.org/format/2501.19283">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Application of Generative Adversarial Network (GAN) for Synthetic Training Data Creation to improve performance of ANN Classifier for extracting Built-Up pixels from Landsat Satellite Imagery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+A">Amritendu Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+D+S">Dipanwita Sinha Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ramachandran%2C+P">Parthasarathy Ramachandran</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="2501.19283v1-abstract-short" style="display: inline;"> Training a neural network for pixel based classification task using low resolution Landsat images is difficult as the size of the training data is usually small due to less number of available pixels that represent a single class without any mixing with other classes. Due to this scarcity of training data, neural network may not be able to attain expected level of accuracy. This limitation could b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19283v1-abstract-full').style.display = 'inline'; document.getElementById('2501.19283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.19283v1-abstract-full" style="display: none;"> Training a neural network for pixel based classification task using low resolution Landsat images is difficult as the size of the training data is usually small due to less number of available pixels that represent a single class without any mixing with other classes. Due to this scarcity of training data, neural network may not be able to attain expected level of accuracy. This limitation could be overcome using a generative network that aims to generate synthetic data having the same distribution as the sample data with which it is trained. In this work, we have proposed a methodology for improving the performance of ANN classifier to identify built-up pixels in the Landsat$7$ image with the help of developing a simple GAN architecture that could generate synthetic training pixels when trained using original set of sample built-up pixels. To ensure that the marginal and joint distributions of all the bands corresponding to the generated and original set of pixels are indistinguishable, non-parametric Kolmogorov Smirnov Test and Ball Divergence based Equality of Distributions Test have been performed respectively. It has been observed that the overall accuracy and kappa coefficient of the ANN model for built-up classification have continuously improved from $0.9331$ to $0.9983$ and $0.8277$ to $0.9958$ respectively, with the inclusion of generated sets of built-up pixels to the original one. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19283v1-abstract-full').style.display = 'none'; document.getElementById('2501.19283v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 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">ACM Class:</span> I.4.6; I.5.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.03479">arXiv:2501.03479</a> <span> [<a href="https://arxiv.org/pdf/2501.03479">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Women, Infamous, and Exotic Beings: What Honorific Usages in Wikipedia Reveal about the Socio-Cultural Norms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Teotia%2C+S">Soumya Teotia</a>, <a href="/search/cs?searchtype=author&query=Saha%2C+S">Sougata Saha</a>, <a href="/search/cs?searchtype=author&query=Choudhury%2C+M">Monojit Choudhury</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="2501.03479v1-abstract-short" style="display: inline;"> Honorifics serve as powerful linguistic markers that reflect social hierarchies and cultural values. This paper presents a large-scale, cross-linguistic exploration of usage of honorific pronouns in Bengali and Hindi Wikipedia articles, shedding light on how socio-cultural factors shape language. Using LLM (GPT-4o), we annotated 10, 000 articles of real and fictional beings in each language for se… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03479v1-abstract-full').style.display = 'inline'; document.getElementById('2501.03479v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.03479v1-abstract-full" style="display: none;"> Honorifics serve as powerful linguistic markers that reflect social hierarchies and cultural values. This paper presents a large-scale, cross-linguistic exploration of usage of honorific pronouns in Bengali and Hindi Wikipedia articles, shedding light on how socio-cultural factors shape language. Using LLM (GPT-4o), we annotated 10, 000 articles of real and fictional beings in each language for several sociodemographic features such as gender, age, fame, and exoticness, and the use of honorifics. We find that across all feature combinations, use of honorifics is consistently more common in Bengali than Hindi. For both languages, the use non-honorific pronouns is more commonly observed for infamous, juvenile, and exotic beings. Notably, we observe a gender bias in use of honorifics in Hindi, with men being more commonly referred to with honorifics than women. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03479v1-abstract-full').style.display = 'none'; document.getElementById('2501.03479v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2025; <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/2501.00309">arXiv:2501.00309</a> <span> [<a href="https://arxiv.org/pdf/2501.00309">pdf</a>, <a href="https://arxiv.org/format/2501.00309">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <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"> Retrieval-Augmented Generation with Graphs (GraphRAG) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+H">Haoyu Han</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Shomer%2C+H">Harry Shomer</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+K">Kai Guo</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+J">Jiayuan Ding</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yongjia Lei</a>, <a href="/search/cs?searchtype=author&query=Halappanavar%2C+M">Mahantesh Halappanavar</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+X">Xianfeng Tang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Q">Qi He</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+Z">Zhigang Hua</a>, <a href="/search/cs?searchtype=author&query=Long%2C+B">Bo Long</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Tong Zhao</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+N">Neil Shah</a>, <a href="/search/cs?searchtype=author&query=Javari%2C+A">Amin Javari</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yinglong Xia</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiliang Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.00309v2-abstract-short" style="display: inline;"> Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a resu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00309v2-abstract-full').style.display = 'inline'; document.getElementById('2501.00309v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.00309v2-abstract-full" style="display: none;"> Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a result, we have recently witnessed increasing attention on equipping RAG with Graph, i.e., GraphRAG. However, unlike conventional RAG, where the retriever, generator, and external data sources can be uniformly designed in the neural-embedding space, the uniqueness of graph-structured data, such as diverse-formatted and domain-specific relational knowledge, poses unique and significant challenges when designing GraphRAG for different domains. Given the broad applicability, the associated design challenges, and the recent surge in GraphRAG, a systematic and up-to-date survey of its key concepts and techniques is urgently desired. Following this motivation, we present a comprehensive and up-to-date survey on GraphRAG. Our survey first proposes a holistic GraphRAG framework by defining its key components, including query processor, retriever, organizer, generator, and data source. Furthermore, recognizing that graphs in different domains exhibit distinct relational patterns and require dedicated designs, we review GraphRAG techniques uniquely tailored to each domain. Finally, we discuss research challenges and brainstorm directions to inspire cross-disciplinary opportunities. Our survey repository is publicly maintained at https://github.com/Graph-RAG/GraphRAG/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00309v2-abstract-full').style.display = 'none'; document.getElementById('2501.00309v2-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">v1</span> submitted 31 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/2412.19802">arXiv:2412.19802</a> <span> [<a href="https://arxiv.org/pdf/2412.19802">pdf</a>, <a href="https://arxiv.org/format/2412.19802">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Probability">math.PR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> LASER: A new method for locally adaptive nonparametric regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Sabyasachi Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Goswami%2C+S">Subhajit Goswami</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S+S">Soumendu Sundar Mukherjee</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="2412.19802v1-abstract-short" style="display: inline;"> In this article, we introduce \textsf{LASER} (Locally Adaptive Smoothing Estimator for Regression), a computationally efficient locally adaptive nonparametric regression method that performs variable bandwidth local polynomial regression. We prove that it adapts (near-)optimally to the local H枚lder exponent of the underlying regression function \texttt{simultaneously} at all points in its domain.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19802v1-abstract-full').style.display = 'inline'; document.getElementById('2412.19802v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.19802v1-abstract-full" style="display: none;"> In this article, we introduce \textsf{LASER} (Locally Adaptive Smoothing Estimator for Regression), a computationally efficient locally adaptive nonparametric regression method that performs variable bandwidth local polynomial regression. We prove that it adapts (near-)optimally to the local H枚lder exponent of the underlying regression function \texttt{simultaneously} at all points in its domain. Furthermore, we show that there is a single ideal choice of a global tuning parameter under which the above mentioned local adaptivity holds. Despite the vast literature on nonparametric regression, instances of practicable methods with provable guarantees of such a strong notion of local adaptivity are rare. The proposed method achieves excellent performance across a broad range of numerical experiments in comparison to popular alternative locally adaptive methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19802v1-abstract-full').style.display = 'none'; document.getElementById('2412.19802v1-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 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">29 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/2412.12827">arXiv:2412.12827</a> <span> [<a href="https://arxiv.org/pdf/2412.12827">pdf</a>, <a href="https://arxiv.org/format/2412.12827">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"> TabSniper: Towards Accurate Table Detection & Structure Recognition for Bank Statements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trivedi%2C+A">Abhishek Trivedi</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourajit Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+R+K">Rajat Kumar Singh</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+V">Vani Agarwal</a>, <a href="/search/cs?searchtype=author&query=Ramakrishnan%2C+S">Sriranjani Ramakrishnan</a>, <a href="/search/cs?searchtype=author&query=Bhatt%2C+H+S">Himanshu S. Bhatt</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="2412.12827v1-abstract-short" style="display: inline;"> Extraction of transaction information from bank statements is required to assess one's financial well-being for credit rating and underwriting decisions. Unlike other financial documents such as tax forms or financial statements, extracting the transaction descriptions from bank statements can provide a comprehensive and recent view into the cash flows and spending patterns. With multiple variatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12827v1-abstract-full').style.display = 'inline'; document.getElementById('2412.12827v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.12827v1-abstract-full" style="display: none;"> Extraction of transaction information from bank statements is required to assess one's financial well-being for credit rating and underwriting decisions. Unlike other financial documents such as tax forms or financial statements, extracting the transaction descriptions from bank statements can provide a comprehensive and recent view into the cash flows and spending patterns. With multiple variations in layout and templates across several banks, extracting transactional level information from different table categories is an arduous task. Existing table structure recognition approaches produce sub optimal results for long, complex tables and are unable to capture all transactions accurately. This paper proposes TabSniper, a novel approach for efficient table detection, categorization and structure recognition from bank statements. The pipeline starts with detecting and categorizing tables of interest from the bank statements. The extracted table regions are then processed by the table structure recognition model followed by a post-processing module to transform the transactional data into a structured and standardised format. The detection and structure recognition architectures are based on DETR, fine-tuned with diverse bank statements along with additional feature enhancements. Results on challenging datasets demonstrate that TabSniper outperforms strong baselines and produces high-quality extraction of transaction information from bank and other financial documents across multiple layouts and templates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12827v1-abstract-full').style.display = 'none'; document.getElementById('2412.12827v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 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/2412.12049">arXiv:2412.12049</a> <span> [<a href="https://arxiv.org/pdf/2412.12049">pdf</a>, <a href="https://arxiv.org/format/2412.12049">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <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"> Bilevel Learning with Inexact Stochastic Gradients </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Salehi%2C+M+S">Mohammad Sadegh Salehi</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhadip Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Roberts%2C+L">Lindon Roberts</a>, <a href="/search/cs?searchtype=author&query=Ehrhardt%2C+M+J">Matthias J. Ehrhardt</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="2412.12049v1-abstract-short" style="display: inline;"> Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The large-scale nature of these problems has led to the development of inexact and computationally efficient methods. Existing adaptive methods predominantly rely on deterministic formul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12049v1-abstract-full').style.display = 'inline'; document.getElementById('2412.12049v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.12049v1-abstract-full" style="display: none;"> Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The large-scale nature of these problems has led to the development of inexact and computationally efficient methods. Existing adaptive methods predominantly rely on deterministic formulations, while stochastic approaches often adopt a doubly-stochastic framework with impractical variance assumptions, enforces a fixed number of lower-level iterations, and requires extensive tuning. In this work, we focus on bilevel learning with strongly convex lower-level problems and a nonconvex sum-of-functions in the upper-level. Stochasticity arises from data sampling in the upper-level which leads to inexact stochastic hypergradients. We establish their connection to state-of-the-art stochastic optimization theory for nonconvex objectives. Furthermore, we prove the convergence of inexact stochastic bilevel optimization under mild assumptions. Our empirical results highlight significant speed-ups and improved generalization in imaging tasks such as image denoising and deblurring in comparison with adaptive deterministic bilevel methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12049v1-abstract-full').style.display = 'none'; document.getElementById('2412.12049v1-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> 16 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/2412.10717">arXiv:2412.10717</a> <span> [<a href="https://arxiv.org/pdf/2412.10717">pdf</a>, <a href="https://arxiv.org/format/2412.10717">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> HITgram: A Platform for Experimenting with n-gram Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dasgupta%2C+S">Shibaranjani Dasgupta</a>, <a href="/search/cs?searchtype=author&query=Maity%2C+C">Chandan Maity</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Somdip Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+R">Rohan Singh</a>, <a href="/search/cs?searchtype=author&query=Dutta%2C+D">Diptendu Dutta</a>, <a href="/search/cs?searchtype=author&query=Jana%2C+D">Debasish Jana</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="2412.10717v1-abstract-short" style="display: inline;"> Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimentation, ideal for resource-constrained environments. It supports unigrams to 4-grams and incorporates features like context sensitive weighting, Laplace smoothing, and dynamic corpus management to e-hance prediction accura… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10717v1-abstract-full').style.display = 'inline'; document.getElementById('2412.10717v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10717v1-abstract-full" style="display: none;"> Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimentation, ideal for resource-constrained environments. It supports unigrams to 4-grams and incorporates features like context sensitive weighting, Laplace smoothing, and dynamic corpus management to e-hance prediction accuracy, even for unseen word sequences. Experiments demonstrate HITgram's efficiency, achieving 50,000 tokens/second and generating 2-grams from a 320MB corpus in 62 seconds. HITgram scales efficiently, constructing 4-grams from a 1GB file in under 298 seconds on an 8 GB RAM system. Planned enhancements include multilingual support, advanced smoothing, parallel processing, and model saving, further broadening its utility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10717v1-abstract-full').style.display = 'none'; document.getElementById('2412.10717v1-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 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/2412.08563">arXiv:2412.08563</a> <span> [<a href="https://arxiv.org/pdf/2412.08563">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="Graphics">cs.GR</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/10.52783/jes.7210">10.52783/jes.7210 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Physics Based Differentiable Rendering for Inverse Problems and Beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kakkar%2C+P">Preetish Kakkar</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Srijani Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ragothaman%2C+H">Hariharan Ragothaman</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+V">Vishal Mehta</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="2412.08563v2-abstract-short" style="display: inline;"> Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be applied to enhance object attributes like geometry, substances, and lighting by adding physical models of light propagation and materials interaction. Due to th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08563v2-abstract-full').style.display = 'inline'; document.getElementById('2412.08563v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.08563v2-abstract-full" style="display: none;"> Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be applied to enhance object attributes like geometry, substances, and lighting by adding physical models of light propagation and materials interaction. Due to these capabilities, distinguished rendering has been employed in a wider range of sectors such as autonomous navigation, scene reconstruction, and material design. We provide an extensive overview of PBDR techniques in this study, emphasizing their creation, effectiveness, and limitations while managing inverse situations. We demonstrate modern techniques and examine their value in everyday situations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08563v2-abstract-full').style.display = 'none'; document.getElementById('2412.08563v2-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">v1</span> submitted 11 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> Journal of Electrical systems, Vol. 20 No. 11s (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.07539">arXiv:2412.07539</a> <span> [<a href="https://arxiv.org/pdf/2412.07539">pdf</a>, <a href="https://arxiv.org/ps/2412.07539">ps</a>, <a href="https://arxiv.org/format/2412.07539">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"> Anomaly detection using Diffusion-based methods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bhosale%2C+A">Aryan Bhosale</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Samrat Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Banerjee%2C+B">Biplab Banerjee</a>, <a href="/search/cs?searchtype=author&query=Cuzzolin%2C+F">Fabio Cuzzolin</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="2412.07539v1-abstract-short" style="display: inline;"> This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs), are evaluated for their performance using reconstruction objectives. By leveraging the strength… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07539v1-abstract-full').style.display = 'inline'; document.getElementById('2412.07539v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.07539v1-abstract-full" style="display: none;"> This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs), are evaluated for their performance using reconstruction objectives. By leveraging the strengths of these models, this study benchmarks their performance against traditional anomaly detection methods such as Isolation Forests, One-Class SVMs, and COPOD. The results demonstrate the superior adaptability, scalability, and robustness of diffusion-based methods in handling complex real-world anomaly detection tasks. Key findings highlight the role of reconstruction error in enhancing detection accuracy and underscore the scalability of these models to high-dimensional datasets. Future directions include optimizing encoder-decoder architectures and exploring multi-modal datasets to further advance diffusion-based anomaly detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07539v1-abstract-full').style.display = 'none'; document.getElementById('2412.07539v1-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">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/2412.07112">arXiv:2412.07112</a> <span> [<a href="https://arxiv.org/pdf/2412.07112">pdf</a>, <a href="https://arxiv.org/format/2412.07112">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Maya: An Instruction Finetuned Multilingual Multimodal Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alam%2C+N">Nahid Alam</a>, <a href="/search/cs?searchtype=author&query=Kanjula%2C+K+R">Karthik Reddy Kanjula</a>, <a href="/search/cs?searchtype=author&query=Guthikonda%2C+S">Surya Guthikonda</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+T">Timothy Chung</a>, <a href="/search/cs?searchtype=author&query=Vegesna%2C+B+K+S">Bala Krishna S Vegesna</a>, <a href="/search/cs?searchtype=author&query=Das%2C+A">Abhipsha Das</a>, <a href="/search/cs?searchtype=author&query=Susevski%2C+A">Anthony Susevski</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+R+S">Ryan Sze-Yin Chan</a>, <a href="/search/cs?searchtype=author&query=Uddin%2C+S+M+I">S M Iftekhar Uddin</a>, <a href="/search/cs?searchtype=author&query=Islam%2C+S+B">Shayekh Bin Islam</a>, <a href="/search/cs?searchtype=author&query=Santhosh%2C+R">Roshan Santhosh</a>, <a href="/search/cs?searchtype=author&query=A%2C+S">Snegha A</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+D">Drishti Sharma</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chen Liu</a>, <a href="/search/cs?searchtype=author&query=Chaturvedi%2C+I">Isha Chaturvedi</a>, <a href="/search/cs?searchtype=author&query=Winata%2C+G+I">Genta Indra Winata</a>, <a href="/search/cs?searchtype=author&query=S%2C+A">Ashvanth. S</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Snehanshu Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Aji%2C+A+F">Alham Fikri Aji</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="2412.07112v1-abstract-short" style="display: inline;"> The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to und… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07112v1-abstract-full').style.display = 'inline'; document.getElementById('2412.07112v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.07112v1-abstract-full" style="display: none;"> The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07112v1-abstract-full').style.display = 'none'; document.getElementById('2412.07112v1-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 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/2412.05469">arXiv:2412.05469</a> <span> [<a href="https://arxiv.org/pdf/2412.05469">pdf</a>, <a href="https://arxiv.org/format/2412.05469">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"> Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhojyoti Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Lalitha%2C+A">Anusha Lalitha</a>, <a href="/search/cs?searchtype=author&query=Sengupta%2C+S">Sailik Sengupta</a>, <a href="/search/cs?searchtype=author&query=Deshmukh%2C+A">Aniket Deshmukh</a>, <a href="/search/cs?searchtype=author&query=Kveton%2C+B">Branislav Kveton</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="2412.05469v1-abstract-short" style="display: inline;"> Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective optimization (MOO), where human preferences are known at training or inference time. In contrast, when human preferences are unknown or difficult to quantify, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05469v1-abstract-full').style.display = 'inline'; document.getElementById('2412.05469v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05469v1-abstract-full" style="display: none;"> Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective optimization (MOO), where human preferences are known at training or inference time. In contrast, when human preferences are unknown or difficult to quantify, a natural approach is to cover the Pareto front by multiple diverse solutions. We propose an algorithm HaM for learning diverse LLM policies that maximizes their hypervolume. This is the first application of a-posteriori MOO to MOAHF. HaM is computationally and space efficient, and empirically superior across objectives such as harmlessness, helpfulness, humor, faithfulness, and hallucination, on various datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05469v1-abstract-full').style.display = 'none'; document.getElementById('2412.05469v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 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/2412.01937">arXiv:2412.01937</a> <span> [<a href="https://arxiv.org/pdf/2412.01937">pdf</a>, <a href="https://arxiv.org/format/2412.01937">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="Discrete Mathematics">cs.DM</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="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Approximately Optimal Search on a Higher-dimensional Sliding Puzzle </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Merleau%2C+N+S">Nono SC Merleau</a>, <a href="/search/cs?searchtype=author&query=O%27Malley%2C+M">Miguel O'Malley</a>, <a href="/search/cs?searchtype=author&query=Rold%C3%A1n%2C+%C3%89">脡rika Rold谩n</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayan Mukherjee</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="2412.01937v1-abstract-short" style="display: inline;"> Higher-dimensional sliding puzzles are constructed on the vertices of a $d$-dimensional hypercube, where $2^d-l$ vertices are distinctly coloured. Rings with the same colours are initially set randomly on the vertices of the hypercube. The goal of the puzzle is to move each of the $2^d-l$ rings to pre-defined target vertices on the cube. In this setting, the $k$-rule constraint represents a genera… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01937v1-abstract-full').style.display = 'inline'; document.getElementById('2412.01937v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01937v1-abstract-full" style="display: none;"> Higher-dimensional sliding puzzles are constructed on the vertices of a $d$-dimensional hypercube, where $2^d-l$ vertices are distinctly coloured. Rings with the same colours are initially set randomly on the vertices of the hypercube. The goal of the puzzle is to move each of the $2^d-l$ rings to pre-defined target vertices on the cube. In this setting, the $k$-rule constraint represents a generalisation of edge collision for the movement of colours between vertices, allowing movement only when a hypercube face of dimension $k$ containing a ring is completely free of other rings. Starting from an initial configuration, what is the minimum number of moves needed to make ring colours match the vertex colours? An algorithm that provides us with such a number is called God's algorithm. When such an algorithm exists, it does not have a polynomial time complexity, at least in the case of the 15-puzzle corresponding to $k=1$ in the cubical puzzle. This paper presents a comprehensive computational study of different scenarios of the higher-dimensional puzzle. A benchmark of three computational techniques, an exact algorithm (the A* search) and two approximately optimal search techniques (an evolutionary algorithm (EA) and reinforcement learning (RL)) is presented in this work. The experiments show that all three methods can successfully solve the puzzle of dimension three for different face dimensions and across various difficulty levels. When the dimension increases, the A* search fails, and RL and EA methods can still provide a generally acceptable solution, i.e. a distribution of a number of moves with a median value of less than $30$. Overall, the EA method consistently requires less computational time, while failing in most cases to minimise the number of moves for the puzzle dimensions $d=4$ and $d=5$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01937v1-abstract-full').style.display = 'none'; document.getElementById('2412.01937v1-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 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">20 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00860">arXiv:2412.00860</a> <span> [<a href="https://arxiv.org/pdf/2412.00860">pdf</a>, <a href="https://arxiv.org/format/2412.00860">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Deep evolving semi-supervised anomaly detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belham%2C+J">Jack Belham</a>, <a href="/search/cs?searchtype=author&query=Bhosale%2C+A">Aryan Bhosale</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Samrat Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Banerjee%2C+B">Biplab Banerjee</a>, <a href="/search/cs?searchtype=author&query=Cuzzolin%2C+F">Fabio Cuzzolin</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="2412.00860v1-abstract-short" style="display: inline;"> The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible. After an overview of the relevant definitions of continual semi-supervised learning, its components, anomaly detection extension, and the training protocols; the p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00860v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00860v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00860v1-abstract-full" style="display: none;"> The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible. After an overview of the relevant definitions of continual semi-supervised learning, its components, anomaly detection extension, and the training protocols; the paper introduces a baseline model of a variational autoencoder (VAE) to work with semi-supervised data along with a continual learning method of deep generative replay with outlier rejection. The results show that such a use of extreme value theory (EVT) applied to anomaly detection can provide promising results even in comparison to an upper baseline of joint training. The results explore the effects of how much labelled and unlabelled data is present, of which class, and where it is located in the data stream. Outlier rejection shows promising initial results where it often surpasses a baseline method of Elastic Weight Consolidation (EWC). A baseline for CSAD is put forward along with the specific dataset setups used for reproducability and testability for other practitioners. Future research directions include other CSAD settings and further research into efficient continual hyperparameter tuning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00860v1-abstract-full').style.display = 'none'; document.getElementById('2412.00860v1-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, 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/2411.03575">arXiv:2411.03575</a> <span> [<a href="https://arxiv.org/pdf/2411.03575">pdf</a>, <a href="https://arxiv.org/format/2411.03575">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Semantic Navigation for AI-assisted Ideation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sandholm%2C+T">Thomas Sandholm</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+S">Sarah Dong</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayandev Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Feland%2C+J">John Feland</a>, <a href="/search/cs?searchtype=author&query=Huberman%2C+B+A">Bernardo A. Huberman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03575v1-abstract-short" style="display: inline;"> We present a novel AI-based ideation assistant and evaluate it in a user study with a group of innovators. The key contribution of our work is twofold: we propose a method of idea exploration in a constrained domain by means of LLM-supported semantic navigation of problem and solution spaces, and employ novel automated data input filtering to improve generations. We found that semantic exploration… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03575v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03575v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03575v1-abstract-full" style="display: none;"> We present a novel AI-based ideation assistant and evaluate it in a user study with a group of innovators. The key contribution of our work is twofold: we propose a method of idea exploration in a constrained domain by means of LLM-supported semantic navigation of problem and solution spaces, and employ novel automated data input filtering to improve generations. We found that semantic exploration is preferred to the traditional prompt-output interactions, measured both in explicit survey rankings, and in terms of innovation assistant engagement, where 2.1x more generations were performed using semantic exploration. We also show that filtering input data with metrics such as relevancy, coherence and human alignment leads to improved generations in the same metrics as well as enhanced quality of experience among innovators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03575v1-abstract-full').style.display = 'none'; document.getElementById('2411.03575v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:2402.06053</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03028">arXiv:2411.03028</a> <span> [<a href="https://arxiv.org/pdf/2411.03028">pdf</a>, <a href="https://arxiv.org/format/2411.03028">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Graph Agnostic Causal Bayesian Optimisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumantrak Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/cs?searchtype=author&query=Vollmer%2C+S+J">Sebastian Josef Vollmer</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03028v1-abstract-short" style="display: inline;"> We study the problem of globally optimising a target variable of an unknown causal graph on which a sequence of soft or hard interventions can be performed. The problem of optimising the target variable associated with a causal graph is formalised as Causal Bayesian Optimisation (CBO). We study the CBO problem under the cumulative regret objective with unknown causal graphs for two settings, namel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03028v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03028v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03028v1-abstract-full" style="display: none;"> We study the problem of globally optimising a target variable of an unknown causal graph on which a sequence of soft or hard interventions can be performed. The problem of optimising the target variable associated with a causal graph is formalised as Causal Bayesian Optimisation (CBO). We study the CBO problem under the cumulative regret objective with unknown causal graphs for two settings, namely structural causal models with hard interventions and function networks with soft interventions. We propose Graph Agnostic Causal Bayesian Optimisation (GACBO), an algorithm that actively discovers the causal structure that contributes to achieving optimal rewards. GACBO seeks to balance exploiting the actions that give the best rewards against exploring the causal structures and functions. To the best of our knowledge, our work is the first to study causal Bayesian optimization with cumulative regret objectives in scenarios where the graph is unknown or partially known. We show our proposed algorithm outperforms baselines in simulated experiments and real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03028v1-abstract-full').style.display = 'none'; document.getElementById('2411.03028v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19054">arXiv:2410.19054</a> <span> [<a href="https://arxiv.org/pdf/2410.19054">pdf</a>, <a href="https://arxiv.org/format/2410.19054">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Infogent: An Agent-Based Framework for Web Information Aggregation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reddy%2C+R+G">Revanth Gangi Reddy</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sagnik Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jeonghwan Kim</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhenhailong Wang</a>, <a href="/search/cs?searchtype=author&query=Hakkani-Tur%2C+D">Dilek Hakkani-Tur</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+H">Heng Ji</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19054v1-abstract-short" style="display: inline;"> Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of linear sequence of actions with an end state that marks task completion. In contrast, our work focuses on web navigation for information aggregation, wherein the agent must explore different websites to gather informatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19054v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19054v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19054v1-abstract-full" style="display: none;"> Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of linear sequence of actions with an end state that marks task completion. In contrast, our work focuses on web navigation for information aggregation, wherein the agent must explore different websites to gather information for a complex query. We consider web information aggregation from two different perspectives: (i) Direct API-driven Access relies on a text-only view of the Web, leveraging external tools such as Google Search API to navigate the web and a scraper to extract website contents. (ii) Interactive Visual Access uses screenshots of the webpages and requires interaction with the browser to navigate and access information. Motivated by these diverse information access settings, we introduce Infogent, a novel modular framework for web information aggregation involving three distinct components: Navigator, Extractor and Aggregator. Experiments on different information access settings demonstrate Infogent beats an existing SOTA multi-agent search framework by 7% under Direct API-Driven Access on FRAMES, and improves over an existing information-seeking web agent by 4.3% under Interactive Visual Access on AssistantBench. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19054v1-abstract-full').style.display = 'none'; document.getElementById('2410.19054v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12441">arXiv:2410.12441</a> <span> [<a href="https://arxiv.org/pdf/2410.12441">pdf</a>, <a href="https://arxiv.org/format/2410.12441">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <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="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> A Primal-dual algorithm for image reconstruction with ICNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wong%2C+H+S">Hok Shing Wong</a>, <a href="/search/cs?searchtype=author&query=Ehrhardt%2C+M+J">Matthias J. Ehrhardt</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhadip Mukherjee</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="2410.12441v1-abstract-short" style="display: inline;"> We address the optimization problem in a data-driven variational reconstruction framework, where the regularizer is parameterized by an input-convex neural network (ICNN). While gradient-based methods are commonly used to solve such problems, they struggle to effectively handle non-smoothness which often leads to slow convergence. Moreover, the nested structure of the neural network complicates th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12441v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12441v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12441v1-abstract-full" style="display: none;"> We address the optimization problem in a data-driven variational reconstruction framework, where the regularizer is parameterized by an input-convex neural network (ICNN). While gradient-based methods are commonly used to solve such problems, they struggle to effectively handle non-smoothness which often leads to slow convergence. Moreover, the nested structure of the neural network complicates the application of standard non-smooth optimization techniques, such as proximal algorithms. To overcome these challenges, we reformulate the problem and eliminate the network's nested structure. By relating this reformulation to epigraphical projections of the activation functions, we transform the problem into a convex optimization problem that can be efficiently solved using a primal-dual algorithm. We also prove that this reformulation is equivalent to the original variational problem. Through experiments on several imaging tasks, we demonstrate that the proposed approach outperforms subgradient methods in terms of both speed and stability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12441v1-abstract-full').style.display = 'none'; document.getElementById('2410.12441v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 65K10; 90C06; 90C25; 94A08 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11186">arXiv:2410.11186</a> <span> [<a href="https://arxiv.org/pdf/2410.11186">pdf</a>, <a href="https://arxiv.org/format/2410.11186">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Synthesizing Proton-Density Fat Fraction and $R_2^*$ from 2-point Dixon MRI with Generative Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Anand%2C+S">Suma Anand</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+K">Kaiwen Xu</a>, <a href="/search/cs?searchtype=author&query=O%27Dushlaine%2C+C">Colm O'Dushlaine</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumit Mukherjee</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="2410.11186v1-abstract-short" style="display: inline;"> Magnetic Resonance Imaging (MRI) is the gold standard for measuring fat and iron content non-invasively in the body via measures known as Proton Density Fat Fraction (PDFF) and $R_2^*$, respectively. However, conventional PDFF and $R_2^*$ quantification methods operate on MR images voxel-wise and require at least three measurements to estimate three quantities: water, fat, and $R_2^*$. Alternative… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11186v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11186v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11186v1-abstract-full" style="display: none;"> Magnetic Resonance Imaging (MRI) is the gold standard for measuring fat and iron content non-invasively in the body via measures known as Proton Density Fat Fraction (PDFF) and $R_2^*$, respectively. However, conventional PDFF and $R_2^*$ quantification methods operate on MR images voxel-wise and require at least three measurements to estimate three quantities: water, fat, and $R_2^*$. Alternatively, the two-point Dixon MRI protocol is widely used and fast because it acquires only two measurements; however, these cannot be used to estimate three quantities voxel-wise. Leveraging the fact that neighboring voxels have similar values, we propose using a generative machine learning approach to learn PDFF and $R_2^*$ from Dixon MRI. We use paired Dixon-IDEAL data from UK Biobank in the liver and a Pix2Pix conditional GAN to demonstrate the first large-scale $R_2^*$ imputation from two-point Dixon MRIs. Using our proposed approach, we synthesize PDFF and $R_2^*$ maps that show significantly greater correlation with ground-truth than conventional voxel-wise baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11186v1-abstract-full').style.display = 'none'; document.getElementById('2410.11186v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07586">arXiv:2410.07586</a> <span> [<a href="https://arxiv.org/pdf/2410.07586">pdf</a>, <a href="https://arxiv.org/format/2410.07586">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Cloud in the Sky: Geo-Aware On-board Data Services for LEO Satellites </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sandholm%2C+T">Thomas Sandholm</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayandev Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Huberman%2C+B+A">Bernardo A Huberman</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="2410.07586v2-abstract-short" style="display: inline;"> We propose an architecture with accompanying protocol for on-board satellite data infrastructure designed for Low Earth Orbit (LEO) constellations offering communication services, such as direct-to-cell connectivity. Our design leverages the unused or under-used computing and communication resources of LEO satellites that are orbiting over uninhabited parts of the earth, like the oceans. We show h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07586v2-abstract-full').style.display = 'inline'; document.getElementById('2410.07586v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07586v2-abstract-full" style="display: none;"> We propose an architecture with accompanying protocol for on-board satellite data infrastructure designed for Low Earth Orbit (LEO) constellations offering communication services, such as direct-to-cell connectivity. Our design leverages the unused or under-used computing and communication resources of LEO satellites that are orbiting over uninhabited parts of the earth, like the oceans. We show how blockchain-backed distributed transactions can be run efficiently on this architecture to offer smart contract services. A key aspect of the proposed architecture that sets it apart from other blockchain systems is that migration of the ledger is not done solely to recover from failures. Rather, migration is also performed periodically and continuously as the satellites circle around in their orbits and enter and leave the blockchain service area. We show in simulations how message and blockchain processing overhead can be contained using different sizes of dynamic geo-aware service areas. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07586v2-abstract-full').style.display = 'none'; document.getElementById('2410.07586v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 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/2410.06114">arXiv:2410.06114</a> <span> [<a href="https://arxiv.org/pdf/2410.06114">pdf</a>, <a href="https://arxiv.org/format/2410.06114">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"> UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reddy%2C+K+S+G">Kovvuri Sai Gopal Reddy</a>, <a href="/search/cs?searchtype=author&query=Saran%2C+B">Bodduluri Saran</a>, <a href="/search/cs?searchtype=author&query=Adityaja%2C+A+M">A. Mudit Adityaja</a>, <a href="/search/cs?searchtype=author&query=Shigwan%2C+S+J">Saurabh J. Shigwan</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+N">Nitin Kumar</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Snehasis Mukherjee</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="2410.06114v1-abstract-short" style="display: inline;"> The data-hungry approach of supervised classification drives the interest of the researchers toward unsupervised approaches, especially for problems such as medical image segmentation, where labeled data are difficult to get. Motivated by the recent success of Vision transformers (ViT) in various computer vision tasks, we propose an unsupervised segmentation framework with a pre-trained ViT. Moreo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06114v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06114v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06114v1-abstract-full" style="display: none;"> The data-hungry approach of supervised classification drives the interest of the researchers toward unsupervised approaches, especially for problems such as medical image segmentation, where labeled data are difficult to get. Motivated by the recent success of Vision transformers (ViT) in various computer vision tasks, we propose an unsupervised segmentation framework with a pre-trained ViT. Moreover, by harnessing the graph structure inherent within the image, the proposed method achieves a notable performance in segmentation, especially in medical images. We further introduce a modularity-based loss function coupled with an Auto-Regressive Moving Average (ARMA) filter to capture the inherent graph topology within the image. Finally, we observe that employing Scaled Exponential Linear Unit (SELU) and SILU (Swish) activation functions within the proposed Graph Neural Network (GNN) architecture enhances the performance of segmentation. The proposed method provides state-of-the-art performance (even comparable to supervised methods) on benchmark image segmentation datasets such as ECSSD, DUTS, and CUB, as well as challenging medical image segmentation datasets such as KVASIR, CVC-ClinicDB, ISIC-2018. The github repository of the code is available on \url{https://github.com/ksgr5566/UnSeGArmaNet}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06114v1-abstract-full').style.display = 'none'; document.getElementById('2410.06114v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at BMVC-2024. arXiv admin note: text overlap with arXiv:2405.06057</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05274">arXiv:2410.05274</a> <span> [<a href="https://arxiv.org/pdf/2410.05274">pdf</a>, <a href="https://arxiv.org/format/2410.05274">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"> Scale-Invariant Object Detection by Adaptive Convolution with Unified Global-Local Context </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Amrita Singh</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Snehasis Mukherjee</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="2410.05274v1-abstract-short" style="display: inline;"> Dense features are important for detecting minute objects in images. Unfortunately, despite the remarkable efficacy of the CNN models in multi-scale object detection, CNN models often fail to detect smaller objects in images due to the loss of dense features during the pooling process. Atrous convolution addresses this issue by applying sparse kernels. However, sparse kernels often can lose the mu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05274v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05274v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05274v1-abstract-full" style="display: none;"> Dense features are important for detecting minute objects in images. Unfortunately, despite the remarkable efficacy of the CNN models in multi-scale object detection, CNN models often fail to detect smaller objects in images due to the loss of dense features during the pooling process. Atrous convolution addresses this issue by applying sparse kernels. However, sparse kernels often can lose the multi-scale detection efficacy of the CNN model. In this paper, we propose an object detection model using a Switchable (adaptive) Atrous Convolutional Network (SAC-Net) based on the efficientDet model. A fixed atrous rate limits the performance of the CNN models in the convolutional layers. To overcome this limitation, we introduce a switchable mechanism that allows for dynamically adjusting the atrous rate during the forward pass. The proposed SAC-Net encapsulates the benefits of both low-level and high-level features to achieve improved performance on multi-scale object detection tasks, without losing the dense features. Further, we apply a depth-wise switchable atrous rate to the proposed network, to improve the scale-invariant features. Finally, we apply global context on the proposed model. Our extensive experiments on benchmark datasets demonstrate that the proposed SAC-Net outperforms the state-of-the-art models by a significant margin in terms of accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05274v1-abstract-full').style.display = 'none'; document.getElementById('2410.05274v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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/2409.17458">arXiv:2409.17458</a> <span> [<a href="https://arxiv.org/pdf/2409.17458">pdf</a>, <a href="https://arxiv.org/format/2409.17458">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="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yifan Jiang</a>, <a href="/search/cs?searchtype=author&query=Aggarwal%2C+K">Kriti Aggarwal</a>, <a href="/search/cs?searchtype=author&query=Laud%2C+T">Tanmay Laud</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+K">Kashif Munir</a>, <a href="/search/cs?searchtype=author&query=Pujara%2C+J">Jay Pujara</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhabrata Mukherjee</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="2409.17458v1-abstract-short" style="display: inline;"> The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17458v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17458v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17458v1-abstract-full" style="display: none;"> The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17458v1-abstract-full').style.display = 'none'; document.getElementById('2409.17458v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.13053">arXiv:2409.13053</a> <span> [<a href="https://arxiv.org/pdf/2409.13053">pdf</a>, <a href="https://arxiv.org/format/2409.13053">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="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Towards Unbiased Evaluation of Time-series Anomaly Detector </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bhattacharya%2C+D">Debarpan Bhattacharya</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumanta Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Kamanchi%2C+C">Chandramouli Kamanchi</a>, <a href="/search/cs?searchtype=author&query=Ekambaram%2C+V">Vijay Ekambaram</a>, <a href="/search/cs?searchtype=author&query=Jati%2C+A">Arindam Jati</a>, <a href="/search/cs?searchtype=author&query=Dayama%2C+P">Pankaj Dayama</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="2409.13053v1-abstract-short" style="display: inline;"> Time series anomaly detection (TSAD) is an evolving area of research motivated by its critical applications, such as detecting seismic activity, sensor failures in industrial plants, predicting crashes in the stock market, and so on. Across domains, anomalies occur significantly less frequently than normal data, making the F1-score the most commonly adopted metric for anomaly detection. However, i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13053v1-abstract-full').style.display = 'inline'; document.getElementById('2409.13053v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13053v1-abstract-full" style="display: none;"> Time series anomaly detection (TSAD) is an evolving area of research motivated by its critical applications, such as detecting seismic activity, sensor failures in industrial plants, predicting crashes in the stock market, and so on. Across domains, anomalies occur significantly less frequently than normal data, making the F1-score the most commonly adopted metric for anomaly detection. However, in the case of time series, it is not straightforward to use standard F1-score because of the dissociation between `time points' and `time events'. To accommodate this, anomaly predictions are adjusted, called as point adjustment (PA), before the $F_1$-score evaluation. However, these adjustments are heuristics-based, and biased towards true positive detection, resulting in over-estimated detector performance. In this work, we propose an alternative adjustment protocol called ``Balanced point adjustment'' (BA). It addresses the limitations of existing point adjustment methods and provides guarantees of fairness backed by axiomatic definitions of TSAD evaluation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13053v1-abstract-full').style.display = 'none'; document.getElementById('2409.13053v1-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 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">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/2409.09704">arXiv:2409.09704</a> <span> [<a href="https://arxiv.org/pdf/2409.09704">pdf</a>, <a href="https://arxiv.org/format/2409.09704">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <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.ymeth.2024.04.005">10.1016/j.ymeth.2024.04.005 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AlpaPICO: Extraction of PICO Frames from Clinical Trial Documents Using LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ghosh%2C+M">Madhusudan Ghosh</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Shrimon Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ganguly%2C+A">Asmit Ganguly</a>, <a href="/search/cs?searchtype=author&query=Basuchowdhuri%2C+P">Partha Basuchowdhuri</a>, <a href="/search/cs?searchtype=author&query=Naskar%2C+S+K">Sudip Kumar Naskar</a>, <a href="/search/cs?searchtype=author&query=Ganguly%2C+D">Debasis Ganguly</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="2409.09704v1-abstract-short" style="display: inline;"> In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09704v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09704v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09704v1-abstract-full" style="display: none;"> In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at \url{https://github.com/shrimonmuke0202/AlpaPICO.git}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09704v1-abstract-full').style.display = 'none'; document.getElementById('2409.09704v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at Methods</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05494">arXiv:2409.05494</a> <span> [<a href="https://arxiv.org/pdf/2409.05494">pdf</a>, <a href="https://arxiv.org/format/2409.05494">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"> An Atmospheric Correction Integrated LULC Segmentation Model for High-Resolution Satellite Imagery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Soham Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Dixit%2C+Y">Yash Dixit</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+N">Naman Srivastava</a>, <a href="/search/cs?searchtype=author&query=Joy%2C+J+D">Joel D Joy</a>, <a href="/search/cs?searchtype=author&query=Olikara%2C+R">Rohan Olikara</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+K">Koesha Sinha</a>, <a href="/search/cs?searchtype=author&query=E%2C+S">Swarup E</a>, <a href="/search/cs?searchtype=author&query=Ramesh%2C+R">Rakshit Ramesh</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="2409.05494v2-abstract-short" style="display: inline;"> The integration of fine-scale multispectral imagery with deep learning models has revolutionized land use and land cover (LULC) classification. However, the atmospheric effects present in Top-of-Atmosphere sensor measured Digital Number values must be corrected to retrieve accurate Bottom-of-Atmosphere surface reflectance for reliable analysis. This study employs look-up-table-based radiative tran… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05494v2-abstract-full').style.display = 'inline'; document.getElementById('2409.05494v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05494v2-abstract-full" style="display: none;"> The integration of fine-scale multispectral imagery with deep learning models has revolutionized land use and land cover (LULC) classification. However, the atmospheric effects present in Top-of-Atmosphere sensor measured Digital Number values must be corrected to retrieve accurate Bottom-of-Atmosphere surface reflectance for reliable analysis. This study employs look-up-table-based radiative transfer simulations to estimate the atmospheric path reflectance and transmittance for atmospherically correcting high-resolution CARTOSAT-3 Multispectral (MX) imagery for several Indian cities. The corrected surface reflectance data were subsequently used in supervised and semi-supervised segmentation models, demonstrating stability in multi-class (buildings, roads, trees and water bodies) LULC segmentation accuracy, particularly in scenarios with sparsely labelled data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05494v2-abstract-full').style.display = 'none'; document.getElementById('2409.05494v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.04737">arXiv:2409.04737</a> <span> [<a href="https://arxiv.org/pdf/2409.04737">pdf</a>, <a href="https://arxiv.org/format/2409.04737">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Materials Science">cond-mat.mtrl-sci</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Shrimon Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+M">Madhusudan Ghosh</a>, <a href="/search/cs?searchtype=author&query=Basuchowdhuri%2C+P">Partha Basuchowdhuri</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="2409.04737v1-abstract-short" style="display: inline;"> Application of artificial intelligence (AI) has been ubiquitous in the growth of research in the areas of basic sciences. Frequent use of machine learning (ML) and deep learning (DL) based methodologies by researchers has resulted in significant advancements in the last decade. These techniques led to notable performance enhancements in different tasks such as protein structure prediction, drug-ta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04737v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04737v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04737v1-abstract-full" style="display: none;"> Application of artificial intelligence (AI) has been ubiquitous in the growth of research in the areas of basic sciences. Frequent use of machine learning (ML) and deep learning (DL) based methodologies by researchers has resulted in significant advancements in the last decade. These techniques led to notable performance enhancements in different tasks such as protein structure prediction, drug-target binding affinity prediction, and molecular property prediction. In material science literature, it is well-known that crystalline materials exhibit topological structures. Such topological structures may be represented as graphs and utilization of graph neural network (GNN) based approaches could help encoding them into an augmented representation space. Primarily, such frameworks adopt supervised learning techniques targeted towards downstream property prediction tasks on the basis of electronic properties (formation energy, bandgap, total energy, etc.) and crystalline structures. Generally, such type of frameworks rely highly on the handcrafted atom feature representations along with the structural representations. In this paper, we propose an unsupervised framework namely, CrysAtom, using untagged crystal data to generate dense vector representation of atoms, which can be utilized in existing GNN-based property predictor models to accurately predict important properties of crystals. Empirical results show that our dense representation embeds chemical properties of atoms and enhance the performance of the baseline property predictor models significantly. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04737v1-abstract-full').style.display = 'none'; document.getElementById('2409.04737v1-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 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/2408.12551">arXiv:2408.12551</a> <span> [<a href="https://arxiv.org/pdf/2408.12551">pdf</a>, <a href="https://arxiv.org/format/2408.12551">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Greybox Learning of Languages Recognizable by Event-Recording Automata </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Majumdar%2C+A">Anirban Majumdar</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayan Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Raskin%2C+J">Jean-Fran莽ois Raskin</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="2408.12551v1-abstract-short" style="display: inline;"> In this paper, we revisit the active learning of timed languages recognizable by event-recording automata. Our framework employs a method known as greybox learning, which enables the learning of event-recording automata with a minimal number of control states. This approach avoids learning the region automaton associated with the language, contrasting with existing methods. We have implemented our… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12551v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12551v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12551v1-abstract-full" style="display: none;"> In this paper, we revisit the active learning of timed languages recognizable by event-recording automata. Our framework employs a method known as greybox learning, which enables the learning of event-recording automata with a minimal number of control states. This approach avoids learning the region automaton associated with the language, contrasting with existing methods. We have implemented our greybox learning algorithm with various heuristics to maintain low computational complexity. The efficacy of our approach is demonstrated through several examples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12551v1-abstract-full').style.display = 'none'; document.getElementById('2408.12551v1-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 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">Shorter version of this article has been accepted at ATVA 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/2408.08577">arXiv:2408.08577</a> <span> [<a href="https://arxiv.org/pdf/2408.08577">pdf</a>, <a href="https://arxiv.org/format/2408.08577">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="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biological Physics">physics.bio-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</span> </div> </div> <p class="title is-5 mathjax"> Mechanistic Modeling of Lipid Nanoparticle Formation for the Delivery of Nucleic Acid Therapeutics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Inguva%2C+P+K">Pavan K. Inguva</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Saikat Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Walker%2C+P+J">Pierre J. Walker</a>, <a href="/search/cs?searchtype=author&query=Kanso%2C+M+A">Mona A. Kanso</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jie Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yanchen Wu</a>, <a href="/search/cs?searchtype=author&query=Tenberg%2C+V">Vico Tenberg</a>, <a href="/search/cs?searchtype=author&query=Santra%2C+S">Srimanta Santra</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+S">Shalini Singh</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S+H">Shin Hyuk Kim</a>, <a href="/search/cs?searchtype=author&query=Trout%2C+B+L">Bernhardt L. Trout</a>, <a href="/search/cs?searchtype=author&query=Bazant%2C+M+Z">Martin Z. Bazant</a>, <a href="/search/cs?searchtype=author&query=Myerson%2C+A+S">Allan S. Myerson</a>, <a href="/search/cs?searchtype=author&query=Braatz%2C+R+D">Richard D. Braatz</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="2408.08577v1-abstract-short" style="display: inline;"> Nucleic acids such as mRNA have emerged as a promising therapeutic modality with the capability of addressing a wide range of diseases. Lipid nanoparticles (LNPs) as a delivery platform for nucleic acids were used in the COVID-19 vaccines and have received much attention. While modern manufacturing processes which involve rapidly mixing an organic stream containing the lipids with an aqueous strea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08577v1-abstract-full').style.display = 'inline'; document.getElementById('2408.08577v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08577v1-abstract-full" style="display: none;"> Nucleic acids such as mRNA have emerged as a promising therapeutic modality with the capability of addressing a wide range of diseases. Lipid nanoparticles (LNPs) as a delivery platform for nucleic acids were used in the COVID-19 vaccines and have received much attention. While modern manufacturing processes which involve rapidly mixing an organic stream containing the lipids with an aqueous stream containing the nucleic acids are conceptually straightforward, detailed understanding of LNP formation and structure is still limited and scale-up can be challenging. Mathematical and computational methods are a promising avenue for deepening scientific understanding of the LNP formation process and facilitating improved process development and control. This article describes strategies for the mechanistic modeling of LNP formation, starting with strategies to estimate and predict important physicochemical properties of the various species such as diffusivities and solubilities. Subsequently, a framework is outlined for constructing mechanistic models of reactor- and particle-scale processes. Insights gained from the various models are mapped back to product quality attributes and process insights. Lastly, the use of the models to guide development of advanced process control and optimization strategies is discussed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08577v1-abstract-full').style.display = 'none'; document.getElementById('2408.08577v1-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 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">67 pages, 10 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/2408.07860">arXiv:2408.07860</a> <span> [<a href="https://arxiv.org/pdf/2408.07860">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> A Novel Generative Artificial Intelligence Method for Interference Study on Multiplex Brightfield Immunohistochemistry Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Satarupa Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Martin%2C+J">Jim Martin</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+Y">Yao Nie</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="2408.07860v1-abstract-short" style="display: inline;"> Multiplex brightfield imaging offers the advantage of simultaneously analyzing multiple biomarkers on a single slide, as opposed to single biomarker labeling on multiple consecutive slides. To accurately analyze multiple biomarkers localized at the same cellular compartment, two representative biomarker sets were selected as assay models - cMET-PDL1-EGFR and CD8-LAG3-PDL1, where all three biomarke… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07860v1-abstract-full').style.display = 'inline'; document.getElementById('2408.07860v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.07860v1-abstract-full" style="display: none;"> Multiplex brightfield imaging offers the advantage of simultaneously analyzing multiple biomarkers on a single slide, as opposed to single biomarker labeling on multiple consecutive slides. To accurately analyze multiple biomarkers localized at the same cellular compartment, two representative biomarker sets were selected as assay models - cMET-PDL1-EGFR and CD8-LAG3-PDL1, where all three biomarkers can co-localize on the cell membrane. One of the most crucial preliminary stages for analyzing such assay is identifying each unique chromogen on individual cells. This is a challenging problem due to the co-localization of membrane stains from all the three biomarkers. It requires advanced color unmixing for creating the equivalent singleplex images from each triplex image for each biomarker. In this project, we developed a cycle-Generative Adversarial Network (cycle-GAN) method for unmixing the triplex images generated from the above-mentioned assays. Three different models were designed to generate the singleplex image for each of the three stains Tamra (purple), QM-Dabsyl (yellow) and Green. A notable novelty of our approach was that the input to the network were images in the optical density domain instead of conventionally used RGB images. The use of the optical density domain helped in reducing the blurriness of the synthetic singleplex images, which was often observed when the network was trained on RGB images. The cycle-GAN models were validated on 10,800 lung, gastric and colon images for the cMET-PDL1-EGFR assay and 3600 colon images for the CD8-LAG3-PDL1 assay. Visual as well as quantified assessments demonstrated that the proposed method is effective and efficient when compared with the manual reviewing results and is readily applicable to various multiplex assays. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07860v1-abstract-full').style.display = 'none'; document.getElementById('2408.07860v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.06996">arXiv:2408.06996</a> <span> [<a href="https://arxiv.org/pdf/2408.06996">pdf</a>, <a href="https://arxiv.org/format/2408.06996">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="Statistics Theory">math.ST</span> </div> </div> <p class="title is-5 mathjax"> Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tan%2C+H+Y">Hong Ye Tan</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhadip Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Junqi Tang</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6nlieb%2C+C">Carola-Bibiane Sch枚nlieb</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="2408.06996v1-abstract-short" style="display: inline;"> The manifold hypothesis says that natural high-dimensional data is actually supported on or around a low-dimensional manifold. Recent success of statistical and learning-based methods empirically supports this hypothesis, due to outperforming classical statistical intuition in very high dimensions. A natural step for analysis is thus to assume the manifold hypothesis and derive bounds that are ind… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06996v1-abstract-full').style.display = 'inline'; document.getElementById('2408.06996v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.06996v1-abstract-full" style="display: none;"> The manifold hypothesis says that natural high-dimensional data is actually supported on or around a low-dimensional manifold. Recent success of statistical and learning-based methods empirically supports this hypothesis, due to outperforming classical statistical intuition in very high dimensions. A natural step for analysis is thus to assume the manifold hypothesis and derive bounds that are independent of any embedding space. Theoretical implications in this direction have recently been explored in terms of generalization of ReLU networks and convergence of Langevin methods. We complement existing results by providing theoretical statistical complexity results, which directly relates to generalization properties. In particular, we demonstrate that the statistical complexity required to approximate a class of bounded Sobolev functions on a compact manifold is bounded from below, and moreover that this bound is dependent only on the intrinsic properties of the manifold. These provide complementary bounds for existing approximation results for ReLU networks on manifolds, which give upper bounds on generalization capacity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06996v1-abstract-full').style.display = 'none'; document.getElementById('2408.06996v1-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 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">MSC Class:</span> 41A25; 41A46; 53Z50; </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03599">arXiv:2408.03599</a> <span> [<a href="https://arxiv.org/pdf/2408.03599">pdf</a>, <a href="https://arxiv.org/format/2408.03599">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="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> Activations Through Extensions: A Framework To Boost Performance Of Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kamanchi%2C+C">Chandramouli Kamanchi</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumanta Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Sampath%2C+K">Kameshwaran Sampath</a>, <a href="/search/cs?searchtype=author&query=Dayama%2C+P">Pankaj Dayama</a>, <a href="/search/cs?searchtype=author&query=Jati%2C+A">Arindam Jati</a>, <a href="/search/cs?searchtype=author&query=Ekambaram%2C+V">Vijay Ekambaram</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+D">Dzung Phan</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="2408.03599v2-abstract-short" style="display: inline;"> Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain. In this work, we propose a framework/strategy that unifies several works on activation functions and theoretically explains the performanc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03599v2-abstract-full').style.display = 'inline'; document.getElementById('2408.03599v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03599v2-abstract-full" style="display: none;"> Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain. In this work, we propose a framework/strategy that unifies several works on activation functions and theoretically explains the performance benefits of these works. We also propose novel techniques that originate from the framework and allow us to obtain ``extensions'' (i.e. special generalizations of a given neural network) of neural networks through operations on activation functions. We theoretically and empirically show that ``extensions'' of neural networks have performance benefits compared to vanilla neural networks with insignificant space and time complexity costs on standard test functions. We also show the benefits of neural network ``extensions'' in the time-series domain on real-world datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03599v2-abstract-full').style.display = 'none'; document.getElementById('2408.03599v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01868">arXiv:2408.01868</a> <span> [<a href="https://arxiv.org/pdf/2408.01868">pdf</a>, <a href="https://arxiv.org/format/2408.01868">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Probability">math.PR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> </div> </div> <p class="title is-5 mathjax"> Meta-Posterior Consistency for the Bayesian Inference of Metastable System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Adams%2C+Z+P">Zachary P Adams</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sayan Mukherjee</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="2408.01868v1-abstract-short" style="display: inline;"> The vast majority of the literature on learning dynamical systems or stochastic processes from time series has focused on stable or ergodic systems, for both Bayesian and frequentist inference procedures. However, most real-world systems are only metastable, that is, the dynamics appear to be stable on some time scale, but are in fact unstable over longer time scales. Consistency of inference for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01868v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01868v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01868v1-abstract-full" style="display: none;"> The vast majority of the literature on learning dynamical systems or stochastic processes from time series has focused on stable or ergodic systems, for both Bayesian and frequentist inference procedures. However, most real-world systems are only metastable, that is, the dynamics appear to be stable on some time scale, but are in fact unstable over longer time scales. Consistency of inference for metastable systems may not be possible, but one can ask about metaconsistency: Do inference procedures converge when observations are taken over a large but finite time interval, but diverge on longer time scales? In this paper we introduce, discuss, and quantify metaconsistency in a Bayesian framework. We discuss how metaconsistency can be exploited to efficiently infer a model for a sub-system of a larger system, where inference on the global behavior may require much more data. We also discuss the relation between meta-consistency and the spectral properties of the model dynamical system in the case of uniformly ergodic diffusions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01868v1-abstract-full').style.display = 'none'; document.getElementById('2408.01868v1-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 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">32 pages, 3 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 62F15; 60J70 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.18200">arXiv:2407.18200</a> <span> [<a href="https://arxiv.org/pdf/2407.18200">pdf</a>, <a href="https://arxiv.org/ps/2407.18200">ps</a>, <a href="https://arxiv.org/format/2407.18200">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Sparse Incremental Aggregation in Multi-Hop Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourav Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Razmi%2C+N">Nasrin Razmi</a>, <a href="/search/cs?searchtype=author&query=Dekorsy%2C+A">Armin Dekorsy</a>, <a href="/search/cs?searchtype=author&query=Popovski%2C+P">Petar Popovski</a>, <a href="/search/cs?searchtype=author&query=Matthiesen%2C+B">Bho Matthiesen</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="2407.18200v1-abstract-short" style="display: inline;"> This paper investigates federated learning (FL) in a multi-hop communication setup, such as in constellations with inter-satellite links. In this setup, part of the FL clients are responsible for forwarding other client's results to the parameter server. Instead of using conventional routing, the communication efficiency can be improved significantly by using in-network model aggregation at each i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18200v1-abstract-full').style.display = 'inline'; document.getElementById('2407.18200v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.18200v1-abstract-full" style="display: none;"> This paper investigates federated learning (FL) in a multi-hop communication setup, such as in constellations with inter-satellite links. In this setup, part of the FL clients are responsible for forwarding other client's results to the parameter server. Instead of using conventional routing, the communication efficiency can be improved significantly by using in-network model aggregation at each intermediate hop, known as incremental aggregation (IA). Prior works [1] have indicated diminishing gains for IA under gradient sparsification. Here we study this issue and propose several novel correlated sparsification methods for IA. Numerical results show that, for some of these algorithms, the full potential of IA is still available under sparsification without impairing convergence. We demonstrate a 15x improvement in communication efficiency over conventional routing and a 11x improvement over state-of-the-art (SoA) sparse IA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18200v1-abstract-full').style.display = 'none'; document.getElementById('2407.18200v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted for the 25th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.16737">arXiv:2407.16737</a> <span> [<a href="https://arxiv.org/pdf/2407.16737">pdf</a>, <a href="https://arxiv.org/format/2407.16737">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"> A Survey of Text Style Transfer: Applications and Ethical Implications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Lango%2C+M">Mateusz Lango</a>, <a href="/search/cs?searchtype=author&query=Kasner%2C+Z">Zdenek Kasner</a>, <a href="/search/cs?searchtype=author&query=Du%C5%A1ek%2C+O">Ondrej Du拧ek</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="2407.16737v1-abstract-short" style="display: inline;"> Text style transfer (TST) is an important task in controllable text generation, which aims to control selected attributes of language use, such as politeness, formality, or sentiment, without altering the style-independent content of the text. The field has received considerable research attention in recent years and has already been covered in several reviews, but the focus has mostly been on the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16737v1-abstract-full').style.display = 'inline'; document.getElementById('2407.16737v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.16737v1-abstract-full" style="display: none;"> Text style transfer (TST) is an important task in controllable text generation, which aims to control selected attributes of language use, such as politeness, formality, or sentiment, without altering the style-independent content of the text. The field has received considerable research attention in recent years and has already been covered in several reviews, but the focus has mostly been on the development of new algorithms and learning from different types of data (supervised, unsupervised, out-of-domain, etc.) and not so much on the application side. However, TST-related technologies are gradually reaching a production- and deployment-ready level, and therefore, the inclusion of the application perspective in TST research becomes crucial. Similarly, the often overlooked ethical considerations of TST technology have become a pressing issue. This paper presents a comprehensive review of TST applications that have been researched over the years, using both traditional linguistic approaches and more recent deep learning methods. We discuss current challenges, future research directions, and ethical implications of TST applications in text generation. By providing a holistic overview of the landscape of TST applications, we hope to stimulate further research and contribute to a better understanding of the potential as well as ethical considerations associated with TST. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16737v1-abstract-full').style.display = 'none'; document.getElementById('2407.16737v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.14822">arXiv:2407.14822</a> <span> [<a href="https://arxiv.org/pdf/2407.14822">pdf</a>, <a href="https://arxiv.org/format/2407.14822">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"> Text Style Transfer: An Introductory Overview </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sourabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Du%C5%A1ek%2C+O">Ondrej Du拧ek</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="2407.14822v1-abstract-short" style="display: inline;"> Text Style Transfer (TST) is a pivotal task in natural language generation to manipulate text style attributes while preserving style-independent content. The attributes targeted in TST can vary widely, including politeness, authorship, mitigation of offensive language, modification of feelings, and adjustment of text formality. TST has become a widely researched topic with substantial advancement… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14822v1-abstract-full').style.display = 'inline'; document.getElementById('2407.14822v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.14822v1-abstract-full" style="display: none;"> Text Style Transfer (TST) is a pivotal task in natural language generation to manipulate text style attributes while preserving style-independent content. The attributes targeted in TST can vary widely, including politeness, authorship, mitigation of offensive language, modification of feelings, and adjustment of text formality. TST has become a widely researched topic with substantial advancements in recent years. This paper provides an introductory overview of TST, addressing its challenges, existing approaches, datasets, evaluation measures, subtasks, and applications. This fundamental overview improves understanding of the background and fundamentals of text style transfer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14822v1-abstract-full').style.display = 'none'; document.getElementById('2407.14822v1-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 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 at 4EU+ International Workshop on Recent Advancements in Artificial Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.06015">arXiv:2407.06015</a> <span> [<a href="https://arxiv.org/pdf/2407.06015">pdf</a>, <a href="https://arxiv.org/format/2407.06015">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Simulation-based Benchmarking for Causal Structure Learning in Gene Perturbation Experiments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kova%C4%8Devi%C4%87%2C+L">Luka Kova膷evi膰</a>, <a href="/search/cs?searchtype=author&query=Newsham%2C+I">Izzy Newsham</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sach Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Whittaker%2C+J">John Whittaker</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="2407.06015v1-abstract-short" style="display: inline;"> Causal structure learning (CSL) refers to the task of learning causal relationships from data. Advances in CSL now allow learning of causal graphs in diverse application domains, which has the potential to facilitate data-driven causal decision-making. Real-world CSL performance depends on a number of $\textit{context-specific}$ factors, including context-specific data distributions and non-linear… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06015v1-abstract-full').style.display = 'inline'; document.getElementById('2407.06015v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.06015v1-abstract-full" style="display: none;"> Causal structure learning (CSL) refers to the task of learning causal relationships from data. Advances in CSL now allow learning of causal graphs in diverse application domains, which has the potential to facilitate data-driven causal decision-making. Real-world CSL performance depends on a number of $\textit{context-specific}$ factors, including context-specific data distributions and non-linear dependencies, that are important in practical use-cases. However, our understanding of how to assess and select CSL methods in specific contexts remains limited. To address this gap, we present $\textit{CausalRegNet}$, a multiplicative effect structural causal model that allows for generating observational and interventional data incorporating context-specific properties, with a focus on the setting of gene perturbation experiments. Using real-world gene perturbation data, we show that CausalRegNet generates accurate distributions and scales far better than current simulation frameworks. We illustrate the use of CausalRegNet in assessing CSL methods in the context of interventional experiments in biology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06015v1-abstract-full').style.display = 'none'; document.getElementById('2407.06015v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 8 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.16962">arXiv:2406.16962</a> <span> [<a href="https://arxiv.org/pdf/2406.16962">pdf</a>, <a href="https://arxiv.org/format/2406.16962">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> MetaGreen: Meta-Learning Inspired Transformer Selection for Green Semantic Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Shubhabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Beard%2C+C">Cory Beard</a>, <a href="/search/cs?searchtype=author&query=Song%2C+S">Sejun Song</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.16962v1-abstract-short" style="display: inline;"> Semantic Communication can transform the way we transmit information, prioritizing meaningful and effective content over individual symbols or bits. This evolution promises significant benefits, including reduced latency, lower bandwidth usage, and higher throughput compared to traditional communication. However, the development of Semantic Communication faces a crucial challenge: the need for uni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16962v1-abstract-full').style.display = 'inline'; document.getElementById('2406.16962v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16962v1-abstract-full" style="display: none;"> Semantic Communication can transform the way we transmit information, prioritizing meaningful and effective content over individual symbols or bits. This evolution promises significant benefits, including reduced latency, lower bandwidth usage, and higher throughput compared to traditional communication. However, the development of Semantic Communication faces a crucial challenge: the need for universal metrics to benchmark the joint effects of semantic information loss and energy consumption. This research introduces an innovative solution: the ``Energy-Optimized Semantic Loss'' (EOSL) function, a novel multi-objective loss function that effectively balances semantic information loss and energy consumption. Through comprehensive experiments on transformer models, including energy benchmarking, we demonstrate the remarkable effectiveness of EOSL-based model selection. We have established that EOSL-based transformer model selection achieves up to 83\% better similarity-to-power ratio (SPR) compared to BLEU score-based selection and 67\% better SPR compared to solely lowest power usage-based selection. Furthermore, we extend the applicability of EOSL to diverse and varying contexts, inspired by the principles of Meta-Learning. By cumulatively applying EOSL, we enable the model selection system to adapt to this change, leveraging historical EOSL values to guide the learning process. This work lays the foundation for energy-efficient model selection and the development of green semantic communication. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16962v1-abstract-full').style.display = 'none'; document.getElementById('2406.16962v1-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 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">arXiv admin note: substantial text overlap with arXiv:2310.07592</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.15247">arXiv:2406.15247</a> <span> [<a href="https://arxiv.org/pdf/2406.15247">pdf</a>, <a href="https://arxiv.org/format/2406.15247">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Probability">math.PR</span> </div> </div> <p class="title is-5 mathjax"> On Naive Mean-Field Approximation for high-dimensional canonical GLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sumit Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+J">Jiaze Qiu</a>, <a href="/search/cs?searchtype=author&query=Sen%2C+S">Subhabrata Sen</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="2406.15247v1-abstract-short" style="display: inline;"> We study the validity of the Naive Mean Field (NMF) approximation for canonical GLMs with product priors. This setting is challenging due to the non-conjugacy of the likelihood and the prior. Using the theory of non-linear large deviations (Austin 2019, Chatterjee, Dembo 2016, Eldan 2018), we derive sufficient conditions for the tightness of the NMF approximation to the log-normalizing constant of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.15247v1-abstract-full').style.display = 'inline'; document.getElementById('2406.15247v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.15247v1-abstract-full" style="display: none;"> We study the validity of the Naive Mean Field (NMF) approximation for canonical GLMs with product priors. This setting is challenging due to the non-conjugacy of the likelihood and the prior. Using the theory of non-linear large deviations (Austin 2019, Chatterjee, Dembo 2016, Eldan 2018), we derive sufficient conditions for the tightness of the NMF approximation to the log-normalizing constant of the posterior distribution. As a second contribution, we establish that under minor conditions on the design, any NMF optimizer is a product distribution where each component is a quadratic tilt of the prior. In turn, this suggests novel iterative algorithms for fitting the NMF optimizer to the target posterior. Finally, we establish that if the NMF optimization problem has a "well-separated maximizer", then this optimizer governs the probabilistic properties of the posterior. Specifically, we derive credible intervals with average coverage guarantees, and characterize the prediction performance on an out-of-sample datapoint in terms of this dominant optimizer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.15247v1-abstract-full').style.display = 'none'; document.getElementById('2406.15247v1-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 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">33 pages, 2 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> Primary: 62F15; Secondary: 94A17; 65K10 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.15074">arXiv:2406.15074</a> <span> [<a href="https://arxiv.org/pdf/2406.15074">pdf</a>, <a href="https://arxiv.org/format/2406.15074">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Balancing The Perception of Cheating Detection, Privacy and Fairness: A Mixed-Methods Study of Visual Data Obfuscation in Remote Proctoring </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Suvadeep Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Distler%2C+V">Verena Distler</a>, <a href="/search/cs?searchtype=author&query=Lenzini%2C+G">Gabriele Lenzini</a>, <a href="/search/cs?searchtype=author&query=Cardoso-Leite%2C+P">Pedro Cardoso-Leite</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="2406.15074v1-abstract-short" style="display: inline;"> Remote proctoring technology, a cheating-preventive measure, often raises privacy and fairness concerns that may affect test-takers' experiences and the validity of test results. Our study explores how selectively obfuscating information in video recordings can protect test-takers' privacy while ensuring effective and fair cheating detection. Interviews with experts (N=9) identified four key video… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.15074v1-abstract-full').style.display = 'inline'; document.getElementById('2406.15074v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.15074v1-abstract-full" style="display: none;"> Remote proctoring technology, a cheating-preventive measure, often raises privacy and fairness concerns that may affect test-takers' experiences and the validity of test results. Our study explores how selectively obfuscating information in video recordings can protect test-takers' privacy while ensuring effective and fair cheating detection. Interviews with experts (N=9) identified four key video regions indicative of potential cheating behaviors: the test-taker's face, body, background and the presence of individuals in the background. Experts recommended specific obfuscation methods for each region based on privacy significance and cheating behavior frequency, ranging from conventional blurring to advanced methods like replacement with deepfake, 3D avatars and silhouetting. We then conducted a vignette experiment with potential test-takers (N=259, non-experts) to evaluate their perceptions of cheating detection, visual privacy and fairness, using descriptions and examples of still images for each expert-recommended combination of video regions and obfuscation methods. Our results indicate that the effectiveness of obfuscation methods varies by region. Tailoring remote proctoring with region-specific advanced obfuscation methods can improve the perceptions of privacy and fairness compared to the conventional methods, though it may decrease perceived information sufficiency for detecting cheating. However, non-experts preferred conventional blurring for videos they were more willing to share, highlighting a gap between the perceived effectiveness of the advanced obfuscation methods and their practical acceptance. This study contributes to the field of user-centered privacy by suggesting promising directions to address current remote proctoring challenges and guiding future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.15074v1-abstract-full').style.display = 'none'; document.getElementById('2406.15074v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11661">arXiv:2406.11661</a> <span> [<a href="https://arxiv.org/pdf/2406.11661">pdf</a>, <a href="https://arxiv.org/format/2406.11661">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"> Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Sagnik Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Adilazuarda%2C+M+F">Muhammad Farid Adilazuarda</a>, <a href="/search/cs?searchtype=author&query=Sitaram%2C+S">Sunayana Sitaram</a>, <a href="/search/cs?searchtype=author&query=Bali%2C+K">Kalika Bali</a>, <a href="/search/cs?searchtype=author&query=Aji%2C+A+F">Alham Fikri Aji</a>, <a href="/search/cs?searchtype=author&query=Choudhury%2C+M">Monojit Choudhury</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="2406.11661v2-abstract-short" style="display: inline;"> Socio-demographic prompting is a commonly employed approach to study cultural biases in LLMs as well as for aligning models to certain cultures. In this paper, we systematically probe four LLMs (Llama 3, Mistral v0.2, GPT-3.5 Turbo and GPT-4) with prompts that are conditioned on culturally sensitive and non-sensitive cues, on datasets that are supposed to be culturally sensitive (EtiCor and CALI)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11661v2-abstract-full').style.display = 'inline'; document.getElementById('2406.11661v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11661v2-abstract-full" style="display: none;"> Socio-demographic prompting is a commonly employed approach to study cultural biases in LLMs as well as for aligning models to certain cultures. In this paper, we systematically probe four LLMs (Llama 3, Mistral v0.2, GPT-3.5 Turbo and GPT-4) with prompts that are conditioned on culturally sensitive and non-sensitive cues, on datasets that are supposed to be culturally sensitive (EtiCor and CALI) or neutral (MMLU and ETHICS). We observe that all models except GPT-4 show significant variations in their responses on both kinds of datasets for both kinds of prompts, casting doubt on the robustness of the culturally-conditioned prompting as a method for eliciting cultural bias in models or as an alignment strategy. The work also calls rethinking the control experiment design to tease apart the cultural conditioning of responses from "placebo effect", i.e., random perturbations of model responses due to arbitrary tokens in the prompt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11661v2-abstract-full').style.display = 'none'; document.getElementById('2406.11661v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Mukherjee%2C+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository