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 448 results for author: <span class="mathjax">Mishra, 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=Mishra%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="Mishra, 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=Mishra%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="Mishra, 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=Mishra%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%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/2502.06136">arXiv:2502.06136</a> <span> [<a href="https://arxiv.org/pdf/2502.06136">pdf</a>, <a href="https://arxiv.org/format/2502.06136">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"> Graph Neural Networks at a Fraction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Joshi%2C+R+B">Rucha Bhalchandra Joshi</a>, <a href="/search/cs?searchtype=author&query=Barad%2C+S+P">Sagar Prakash Barad</a>, <a href="/search/cs?searchtype=author&query=Tiwari%2C+N">Nidhi Tiwari</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Subhankar Mishra</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="2502.06136v2-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform well on tasks on graph-structured data. With the aim of reducing the energy footprint, we reduce the model size while maintaining accuracy comparable to that of the original-sized GNNs. This paper introduces Quaternion Mess… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06136v2-abstract-full').style.display = 'inline'; document.getElementById('2502.06136v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.06136v2-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform well on tasks on graph-structured data. With the aim of reducing the energy footprint, we reduce the model size while maintaining accuracy comparable to that of the original-sized GNNs. This paper introduces Quaternion Message Passing Neural Networks (QMPNNs), a framework that leverages quaternion space to compute node representations. Our approach offers a generalizable method for incorporating quaternion representations into GNN architectures at one-fourth of the original parameter count. Furthermore, we present a novel perspective on Graph Lottery Tickets, redefining their applicability within the context of GNNs and QMPNNs. We specifically aim to find the initialization lottery from the subnetwork of the GNNs that can achieve comparable performance to the original GNN upon training. Thereby reducing the trainable model parameters even further. To validate the effectiveness of our proposed QMPNN framework and LTH for both GNNs and QMPNNs, we evaluate their performance on real-world datasets across three fundamental graph-based tasks: node classification, link prediction, and graph classification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06136v2-abstract-full').style.display = 'none'; document.getElementById('2502.06136v2-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">v1</span> submitted 9 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">12 pages, 2 figures, accepted at PAKKD 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.01476">arXiv:2502.01476</a> <span> [<a href="https://arxiv.org/pdf/2502.01476">pdf</a>, <a href="https://arxiv.org/format/2502.01476">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"> Neuro-Symbolic AI for Analytical Solutions of Differential Equations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Oikonomou%2C+O">Orestis Oikonomou</a>, <a href="/search/cs?searchtype=author&query=Lingsch%2C+L">Levi Lingsch</a>, <a href="/search/cs?searchtype=author&query=Grund%2C+D">Dana Grund</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Siddhartha Mishra</a>, <a href="/search/cs?searchtype=author&query=Kissas%2C+G">Georgios Kissas</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="2502.01476v1-abstract-short" style="display: inline;"> Analytical solutions of differential equations offer exact insights into fundamental behaviors of physical processes. Their application, however, is limited as finding these solutions is difficult. To overcome this limitation, we combine two key insights. First, constructing an analytical solution requires a composition of foundational solution components. Second, iterative solvers define paramete… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01476v1-abstract-full').style.display = 'inline'; document.getElementById('2502.01476v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.01476v1-abstract-full" style="display: none;"> Analytical solutions of differential equations offer exact insights into fundamental behaviors of physical processes. Their application, however, is limited as finding these solutions is difficult. To overcome this limitation, we combine two key insights. First, constructing an analytical solution requires a composition of foundational solution components. Second, iterative solvers define parameterized function spaces with constraint-based updates. Our approach merges compositional differential equation solution techniques with iterative refinement by using formal grammars, building a rich space of candidate solutions that are embedded into a low-dimensional (continuous) latent manifold for probabilistic exploration. This integration unifies numerical and symbolic differential equation solvers via a neuro-symbolic AI framework to find analytical solutions of a wide variety of differential equations. By systematically constructing candidate expressions and applying constraint-based refinement, we overcome longstanding barriers to extract such closed-form solutions. We illustrate advantages over commercial solvers, symbolic methods, and approximate neural networks on a diverse set of problems, demonstrating both generality and accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01476v1-abstract-full').style.display = 'none'; document.getElementById('2502.01476v1-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 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/2501.19205">arXiv:2501.19205</a> <span> [<a href="https://arxiv.org/pdf/2501.19205">pdf</a>, <a href="https://arxiv.org/format/2501.19205">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"> RIGNO: A Graph-based framework for robust and accurate operator learning for PDEs on arbitrary domains </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mousavi%2C+S">Sepehr Mousavi</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+S">Shizheng Wen</a>, <a href="/search/cs?searchtype=author&query=Lingsch%2C+L">Levi Lingsch</a>, <a href="/search/cs?searchtype=author&query=Herde%2C+M">Maximilian Herde</a>, <a href="/search/cs?searchtype=author&query=Raoni%C4%87%2C+B">Bogdan Raoni膰</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Siddhartha Mishra</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="2501.19205v1-abstract-short" style="display: inline;"> Learning the solution operators of PDEs on arbitrary domains is challenging due to the diversity of possible domain shapes, in addition to the often intricate underlying physics. We propose an end-to-end graph neural network (GNN) based neural operator to learn PDE solution operators from data on point clouds in arbitrary domains. Our multi-scale model maps data between input/output point clouds b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19205v1-abstract-full').style.display = 'inline'; document.getElementById('2501.19205v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.19205v1-abstract-full" style="display: none;"> Learning the solution operators of PDEs on arbitrary domains is challenging due to the diversity of possible domain shapes, in addition to the often intricate underlying physics. We propose an end-to-end graph neural network (GNN) based neural operator to learn PDE solution operators from data on point clouds in arbitrary domains. Our multi-scale model maps data between input/output point clouds by passing it through a downsampled regional mesh. Many novel elements are also incorporated to ensure resolution invariance and temporal continuity. Our model, termed RIGNO, is tested on a challenging suite of benchmarks, composed of various time-dependent and steady PDEs defined on a diverse set of domains. We demonstrate that RIGNO is significantly more accurate than neural operator baselines and robustly generalizes to unseen spatial resolutions and time instances. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19205v1-abstract-full').style.display = 'none'; document.getElementById('2501.19205v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.18129">arXiv:2501.18129</a> <span> [<a href="https://arxiv.org/pdf/2501.18129">pdf</a>, <a href="https://arxiv.org/format/2501.18129">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Revisiting gender bias research in bibliometrics: Standardizing methodological variability using Scholarly Data Analysis (SoDA) Cards </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+H">HaeJin Lee</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shubhanshu Mishra</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+A">Apratim Mishra</a>, <a href="/search/cs?searchtype=author&query=You%2C+Z">Zhiwen You</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jinseok Kim</a>, <a href="/search/cs?searchtype=author&query=Diesner%2C+J">Jana Diesner</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="2501.18129v1-abstract-short" style="display: inline;"> Gender biases in scholarly metrics remain a persistent concern, despite numerous bibliometric studies exploring their presence and absence across productivity, impact, acknowledgment, and self-citations. However, methodological inconsistencies, particularly in author name disambiguation and gender identification, limit the reliability and comparability of these studies, potentially perpetuating mi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18129v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18129v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18129v1-abstract-full" style="display: none;"> Gender biases in scholarly metrics remain a persistent concern, despite numerous bibliometric studies exploring their presence and absence across productivity, impact, acknowledgment, and self-citations. However, methodological inconsistencies, particularly in author name disambiguation and gender identification, limit the reliability and comparability of these studies, potentially perpetuating misperceptions and hindering effective interventions. A review of 70 relevant publications over the past 12 years reveals a wide range of approaches, from name-based and manual searches to more algorithmic and gold-standard methods, with no clear consensus on best practices. This variability, compounded by challenges such as accurately disambiguating Asian names and managing unassigned gender labels, underscores the urgent need for standardized and robust methodologies. To address this critical gap, we propose the development and implementation of ``Scholarly Data Analysis (SoDA) Cards." These cards will provide a structured framework for documenting and reporting key methodological choices in scholarly data analysis, including author name disambiguation and gender identification procedures. By promoting transparency and reproducibility, SoDA Cards will facilitate more accurate comparisons and aggregations of research findings, ultimately supporting evidence-informed policymaking and enabling the longitudinal tracking of analytical approaches in the study of gender and other social biases in academia. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18129v1-abstract-full').style.display = 'none'; document.getElementById('2501.18129v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">33 pg, 7 figures. Soda Cards: https://github.com/HaeJinLee41/scholarly_bias_study</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> K.4.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.14249">arXiv:2501.14249</a> <span> [<a href="https://arxiv.org/pdf/2501.14249">pdf</a>, <a href="https://arxiv.org/format/2501.14249">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"> Humanity's Last Exam </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+L">Long Phan</a>, <a href="/search/cs?searchtype=author&query=Gatti%2C+A">Alice Gatti</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Ziwen Han</a>, <a href="/search/cs?searchtype=author&query=Li%2C+N">Nathaniel Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Josephina Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hugh Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C+B+C">Chen Bo Calvin Zhang</a>, <a href="/search/cs?searchtype=author&query=Shaaban%2C+M">Mohamed Shaaban</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+J">John Ling</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+S">Sean Shi</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+M">Michael Choi</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+A">Anish Agrawal</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+A">Arnav Chopra</a>, <a href="/search/cs?searchtype=author&query=Khoja%2C+A">Adam Khoja</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+R">Ryan Kim</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+R">Richard Ren</a>, <a href="/search/cs?searchtype=author&query=Hausenloy%2C+J">Jason Hausenloy</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+O">Oliver Zhang</a>, <a href="/search/cs?searchtype=author&query=Mazeika%2C+M">Mantas Mazeika</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Anderson%2C+D">Daron Anderson</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+I+A">Imad Ali Shah</a>, <a href="/search/cs?searchtype=author&query=Doroshenko%2C+M">Mikhail Doroshenko</a>, <a href="/search/cs?searchtype=author&query=Stokes%2C+A+C">Alun Cennyth Stokes</a>, <a href="/search/cs?searchtype=author&query=Mahmood%2C+M">Mobeen Mahmood</a> , et al. (710 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.14249v3-abstract-short" style="display: inline;"> Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14249v3-abstract-full').style.display = 'inline'; document.getElementById('2501.14249v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14249v3-abstract-full" style="display: none;"> Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14249v3-abstract-full').style.display = 'none'; document.getElementById('2501.14249v3-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 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 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/2501.14011">arXiv:2501.14011</a> <span> [<a href="https://arxiv.org/pdf/2501.14011">pdf</a>, <a href="https://arxiv.org/format/2501.14011">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</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"> QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sahil Mishra</a>, <a href="/search/cs?searchtype=author&query=Patni%2C+A">Avi Patni</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+N">Niladri Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Chakraborty%2C+T">Tanmoy Chakraborty</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="2501.14011v1-abstract-short" style="display: inline;"> A taxonomy is a hierarchical graph containing knowledge to provide valuable insights for various web applications. Online retail organizations like Microsoft and Amazon utilize taxonomies to improve product recommendations and optimize advertisement by enhancing query interpretation. However, the manual construction of taxonomies requires significant human effort. As web content continues to expan… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14011v1-abstract-full').style.display = 'inline'; document.getElementById('2501.14011v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14011v1-abstract-full" style="display: none;"> A taxonomy is a hierarchical graph containing knowledge to provide valuable insights for various web applications. Online retail organizations like Microsoft and Amazon utilize taxonomies to improve product recommendations and optimize advertisement by enhancing query interpretation. However, the manual construction of taxonomies requires significant human effort. As web content continues to expand at an unprecedented pace, existing taxonomies risk becoming outdated, struggling to incorporate new and emerging information effectively. As a consequence, there is a growing need for dynamic taxonomy expansion to keep them relevant and up-to-date. Existing taxonomy expansion methods often rely on classical word embeddings to represent entities. However, these embeddings fall short in capturing hierarchical polysemy, where an entity's meaning can vary based on its position in the hierarchy and its surrounding context. To address this challenge, we introduce QuanTaxo, an innovative quantum-inspired framework for taxonomy expansion. QuanTaxo encodes entity representations in quantum space, effectively modeling hierarchical polysemy by leveraging the principles of Hilbert space to capture interference effects between entities, yielding richer and more nuanced representations. Comprehensive experiments on four real-world benchmark datasets show that QuanTaxo significantly outperforms classical embedding models, achieving substantial improvements of 18.45% in accuracy, 20.5% in Mean Reciprocal Rank, and 17.87% in Wu & Palmer metrics across eight classical embedding-based baselines. We further highlight the superiority of QuanTaxo through extensive ablation and case studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14011v1-abstract-full').style.display = 'none'; document.getElementById('2501.14011v1-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 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/2501.08086">arXiv:2501.08086</a> <span> [<a href="https://arxiv.org/pdf/2501.08086">pdf</a>, <a href="https://arxiv.org/format/2501.08086">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="Symbolic Computation">cs.SC</span> </div> </div> <p class="title is-5 mathjax"> NOMTO: Neural Operator-based symbolic Model approximaTion and discOvery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Garmaev%2C+S">Sergei Garmaev</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Siddhartha Mishra</a>, <a href="/search/cs?searchtype=author&query=Fink%2C+O">Olga Fink</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="2501.08086v1-abstract-short" style="display: inline;"> While many physical and engineering processes are most effectively described by non-linear symbolic models, existing non-linear symbolic regression (SR) methods are restricted to a limited set of continuous algebraic functions, thereby limiting their applicability to discover higher order non-linear differential relations. In this work, we introduce the Neural Operator-based symbolic Model approxi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08086v1-abstract-full').style.display = 'inline'; document.getElementById('2501.08086v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.08086v1-abstract-full" style="display: none;"> While many physical and engineering processes are most effectively described by non-linear symbolic models, existing non-linear symbolic regression (SR) methods are restricted to a limited set of continuous algebraic functions, thereby limiting their applicability to discover higher order non-linear differential relations. In this work, we introduce the Neural Operator-based symbolic Model approximaTion and discOvery (NOMTO) method, a novel approach to symbolic model discovery that leverages Neural Operators to encompass a broad range of symbolic operations. We demonstrate that NOMTO can successfully identify symbolic expressions containing elementary functions with singularities, special functions, and derivatives. Additionally, our experiments demonstrate that NOMTO can accurately rediscover second-order non-linear partial differential equations. By broadening the set of symbolic operations available for discovery, NOMTO significantly advances the capabilities of existing SR methods. It provides a powerful and flexible tool for model discovery, capable of capturing complex relations in a variety of physical systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08086v1-abstract-full').style.display = 'none'; document.getElementById('2501.08086v1-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 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/2501.07435">arXiv:2501.07435</a> <span> [<a href="https://arxiv.org/pdf/2501.07435">pdf</a>, <a href="https://arxiv.org/format/2501.07435">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Union: A Trust-minimized Bridge for Rootstock </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Amela%2C+R">Ramon Amela</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shreemoy Mishra</a>, <a href="/search/cs?searchtype=author&query=Lerner%2C+S+D">Sergio Demian Lerner</a>, <a href="/search/cs?searchtype=author&query=Cid-Fuentes%2C+J+%C3%81">Javier 脕lvarez Cid-Fuentes</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="2501.07435v2-abstract-short" style="display: inline;"> We present Union, a trust-minimized bridge protocol that enables secure transfer of BTC between Bitcoin and a secondary blockchain. The growing ecosystem of blockchain systems built around Bitcoin has created a pressing need for secure and efficient bridges to transfer BTC between networks while preserving Bitcoin's security guarantees. Union employs a multi-party variant of BitVMX, an optimistic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07435v2-abstract-full').style.display = 'inline'; document.getElementById('2501.07435v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07435v2-abstract-full" style="display: none;"> We present Union, a trust-minimized bridge protocol that enables secure transfer of BTC between Bitcoin and a secondary blockchain. The growing ecosystem of blockchain systems built around Bitcoin has created a pressing need for secure and efficient bridges to transfer BTC between networks while preserving Bitcoin's security guarantees. Union employs a multi-party variant of BitVMX, an optimistic proving system on Bitcoin, to create a bridge that operates securely under the assumption that at least one participant remains honest. This 1-of-n honest approach is strikingly different from the conventional honest-majority assumption adopted by practically all federated systems. The protocol introduces several innovations: a packet-based architecture that allows security bonds to be reused for multiple bridge operations, improving capital efficiency; a system of enablers to manage functionaries participation and to enforce penalties; a flexible light client framework adaptable to various blockchain architectures; and an efficient stop watch mechanism to optimize time-lock management. Union is a practical and scalable solution for Bitcoin interoperability that maintains strong security guarantees and minimizes trust assumptions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07435v2-abstract-full').style.display = 'none'; document.getElementById('2501.07435v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 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/2501.03687">arXiv:2501.03687</a> <span> [<a href="https://arxiv.org/pdf/2501.03687">pdf</a>, <a href="https://arxiv.org/ps/2501.03687">ps</a>, <a href="https://arxiv.org/format/2501.03687">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cell Behavior">q-bio.CB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biological Physics">physics.bio-ph</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1103/PhysRevE.111.014106">10.1103/PhysRevE.111.014106 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Run-and-tumble chemotaxis using reinforcement learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pramanik%2C+R">Ramesh Pramanik</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shradha Mishra</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Sakuntala Chatterjee</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="2501.03687v1-abstract-short" style="display: inline;"> Bacterial cells use run-and-tumble motion to climb up attractant concentration gradient in their environment. By extending the uphill runs and shortening the downhill runs the cells migrate towards the higher attractant zones. Motivated by this, we formulate a reinforcement learning (RL) algorithm where an agent moves in one dimension in the presence of an attractant gradient. The agent can perfor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03687v1-abstract-full').style.display = 'inline'; document.getElementById('2501.03687v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.03687v1-abstract-full" style="display: none;"> Bacterial cells use run-and-tumble motion to climb up attractant concentration gradient in their environment. By extending the uphill runs and shortening the downhill runs the cells migrate towards the higher attractant zones. Motivated by this, we formulate a reinforcement learning (RL) algorithm where an agent moves in one dimension in the presence of an attractant gradient. The agent can perform two actions: either persistent motion in the same direction or reversal of direction. We assign costs for these actions based on the recent history of the agent's trajectory. We ask the question: which RL strategy works best in different types of attractant environment. We quantify efficiency of the RL strategy by the ability of the agent (a) to localize in the favorable zones after large times, and (b) to learn about its complete environment. Depending on the attractant profile and the initial condition, we find an optimum balance is needed between exploration and exploitation to ensure the most efficient performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03687v1-abstract-full').style.display = 'none'; document.getElementById('2501.03687v1-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 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">Journal ref:</span> Physical Review E 111, 014106 (2025) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.17356">arXiv:2412.17356</a> <span> [<a href="https://arxiv.org/pdf/2412.17356">pdf</a>, <a href="https://arxiv.org/ps/2412.17356">ps</a>, <a href="https://arxiv.org/format/2412.17356">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Optimal Multi-Level ASK Modulations for RIS-Assisted Communications with Energy-Based Noncoherent Reception </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sambit Mishra</a>, <a href="/search/cs?searchtype=author&query=Dash%2C+S+P">Soumya P. Dash</a>, <a href="/search/cs?searchtype=author&query=Alexandropoulos%2C+G+C">George C. Alexandropoulos</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="2412.17356v1-abstract-short" style="display: inline;"> This paper investigates the performance of one- and two-sided amplitude shift keying (ASK) modulations in noncoherent single-input single-output (SISO) wireless communication systems assisted by a reconfigurable intelligent surface (RIS). Novel noncoherent receiver structures are proposed based on the energy of the received symbol and the choice of the modulation scheme for data transmission. The… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17356v1-abstract-full').style.display = 'inline'; document.getElementById('2412.17356v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.17356v1-abstract-full" style="display: none;"> This paper investigates the performance of one- and two-sided amplitude shift keying (ASK) modulations in noncoherent single-input single-output (SISO) wireless communication systems assisted by a reconfigurable intelligent surface (RIS). Novel noncoherent receiver structures are proposed based on the energy of the received symbol and the choice of the modulation scheme for data transmission. The system's performance is assessed in terms of the symbol error rate (SER) and an optimization framework is proposed to determine the most effective one- and two-sided ASKs to minimize the SER, while adhering to average a transmit power constraint. Two scenarios based on the availability of the statistical characteristics of the wireless channel are explored: a) the transceiver pair has complete knowledge of the channel statistics, and b) both end nodes possess knowledge of the statistics of the channel gain up to its fourth moment, and novel algorithms are developed to obtain optimal ASKs for both of them. Extensive numerical evaluations are presented showcasing that there exists a threshold signal-to-noise ratio (SNR) above which the optimal ASKs outperform the traditional equispaced ASKs. The dependencies of the SER performance and the SNR threshold on various system parameters are assessed, providing design guidelines for RIS-assisted noncoherent wireless communication systems with multi-level ASK modulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17356v1-abstract-full').style.display = 'none'; document.getElementById('2412.17356v1-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 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">12 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/2412.15515">arXiv:2412.15515</a> <span> [<a href="https://arxiv.org/pdf/2412.15515">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Reconstruction of Contour Lines During the Digitization of Contour Maps to Build a Digital Elevation Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Subedi%2C+A">Aroj Subedi</a>, <a href="/search/cs?searchtype=author&query=Ganesh%2C+P">Pradip Ganesh</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sandip Mishra</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="2412.15515v1-abstract-short" style="display: inline;"> Contour map has contour lines that are significant in building a Digital Elevation Model (DEM). During the digitization and pre-processing of contour maps, the contour line intersects with each other or break apart resulting in broken contour segments. These broken segments impose a greater risk while building DEM leading to a faulty model. In this project, a simple yet efficient mechanism is used… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15515v1-abstract-full').style.display = 'inline'; document.getElementById('2412.15515v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15515v1-abstract-full" style="display: none;"> Contour map has contour lines that are significant in building a Digital Elevation Model (DEM). During the digitization and pre-processing of contour maps, the contour line intersects with each other or break apart resulting in broken contour segments. These broken segments impose a greater risk while building DEM leading to a faulty model. In this project, a simple yet efficient mechanism is used to match and reconnect the endpoints of the broken segments accurately and efficiently. The matching of the endpoints is done using the concept of minimum Euclidean distance and gradient direction while the Cubic Hermite spline interpolation technique is used to reconnect the endpoints by estimating the values using a mathematical function that minimizes overall surface curvature resulting in a smooth curve. The purpose of this work is to reconnect the broken contour lines generated during the digitization of the contour map, to help build the most appropriate digital elevation model for the corresponding contour map. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15515v1-abstract-full').style.display = 'none'; document.getElementById('2412.15515v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 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> J. ADV COMP ENG TECHNOL, 6(4) Autumn 2020 : 239-250 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.12910">arXiv:2412.12910</a> <span> [<a href="https://arxiv.org/pdf/2412.12910">pdf</a>, <a href="https://arxiv.org/format/2412.12910">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Sequential Harmful Shift Detection Without Labels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Amoukou%2C+S+I">Salim I. Amoukou</a>, <a href="/search/cs?searchtype=author&query=Bewley%2C+T">Tom Bewley</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saumitra Mishra</a>, <a href="/search/cs?searchtype=author&query=Lecue%2C+F">Freddy Lecue</a>, <a href="/search/cs?searchtype=author&query=Magazzeni%2C+D">Daniele Magazzeni</a>, <a href="/search/cs?searchtype=author&query=Veloso%2C+M">Manuela Veloso</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="2412.12910v1-abstract-short" style="display: inline;"> We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels. It builds upon the work of Podkopaev and Ramdas [2022], who address scenarios where labels are available for tracking model errors over time. Our solution extends this framework… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12910v1-abstract-full').style.display = 'inline'; document.getElementById('2412.12910v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.12910v1-abstract-full" style="display: none;"> We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels. It builds upon the work of Podkopaev and Ramdas [2022], who address scenarios where labels are available for tracking model errors over time. Our solution extends this framework to work in the absence of labels, by employing a proxy for the true error. This proxy is derived using the predictions of a trained error estimator. Experiments show that our method has high power and false alarm control under various distribution shifts, including covariate and label shifts and natural shifts over geography and time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12910v1-abstract-full').style.display = 'none'; document.getElementById('2412.12910v1-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> <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 the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.08385">arXiv:2412.08385</a> <span> [<a href="https://arxiv.org/pdf/2412.08385">pdf</a>, <a href="https://arxiv.org/format/2412.08385">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nigam%2C+S+K">Shubham Kumar Nigam</a>, <a href="/search/cs?searchtype=author&query=Patnaik%2C+B+D">Balaramamahanthi Deepak Patnaik</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shivam Mishra</a>, <a href="/search/cs?searchtype=author&query=Shallum%2C+N">Noel Shallum</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+K">Kripabandhu Ghosh</a>, <a href="/search/cs?searchtype=author&query=Bhattacharya%2C+A">Arnab Bhattacharya</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="2412.08385v1-abstract-short" style="display: inline;"> The integration of artificial intelligence (AI) in legal judgment prediction (LJP) has the potential to transform the legal landscape, particularly in jurisdictions like India, where a significant backlog of cases burdens the legal system. This paper introduces NyayaAnumana, the largest and most diverse corpus of Indian legal cases compiled for LJP, encompassing a total of 7,02,945 preprocessed ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08385v1-abstract-full').style.display = 'inline'; document.getElementById('2412.08385v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.08385v1-abstract-full" style="display: none;"> The integration of artificial intelligence (AI) in legal judgment prediction (LJP) has the potential to transform the legal landscape, particularly in jurisdictions like India, where a significant backlog of cases burdens the legal system. This paper introduces NyayaAnumana, the largest and most diverse corpus of Indian legal cases compiled for LJP, encompassing a total of 7,02,945 preprocessed cases. NyayaAnumana, which combines the words "Nyay" (judgment) and "Anuman" (prediction or inference) respectively for most major Indian languages, includes a wide range of cases from the Supreme Court, High Courts, Tribunal Courts, District Courts, and Daily Orders and, thus, provides unparalleled diversity and coverage. Our dataset surpasses existing datasets like PredEx and ILDC, offering a comprehensive foundation for advanced AI research in the legal domain. In addition to the dataset, we present INLegalLlama, a domain-specific generative large language model (LLM) tailored to the intricacies of the Indian legal system. It is developed through a two-phase training approach over a base LLaMa model. First, Indian legal documents are injected using continual pretraining. Second, task-specific supervised finetuning is done. This method allows the model to achieve a deeper understanding of legal contexts. Our experiments demonstrate that incorporating diverse court data significantly boosts model accuracy, achieving approximately 90% F1-score in prediction tasks. INLegalLlama not only improves prediction accuracy but also offers comprehensible explanations, addressing the need for explainability in AI-assisted legal decisions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08385v1-abstract-full').style.display = 'none'; document.getElementById('2412.08385v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted on COLING 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04536">arXiv:2412.04536</a> <span> [<a href="https://arxiv.org/pdf/2412.04536">pdf</a>, <a href="https://arxiv.org/format/2412.04536">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Robotic Wire Arc Additive Manufacturing with Variable Height Layers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Marcotte%2C+J">John Marcotte</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sandipan Mishra</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+J+T">John T. Wen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.04536v1-abstract-short" style="display: inline;"> Robotic wire arc additive manufacturing has been widely adopted due to its high deposition rates and large print volume relative to other metal additive manufacturing processes. For complex geometries, printing with variable height within layers offer the advantage of producing overhangs without the need for support material or geometric decomposition. This approach has been demonstrated for steel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04536v1-abstract-full').style.display = 'inline'; document.getElementById('2412.04536v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04536v1-abstract-full" style="display: none;"> Robotic wire arc additive manufacturing has been widely adopted due to its high deposition rates and large print volume relative to other metal additive manufacturing processes. For complex geometries, printing with variable height within layers offer the advantage of producing overhangs without the need for support material or geometric decomposition. This approach has been demonstrated for steel using precomputed robot speed profiles to achieve consistent geometric quality. In contrast, aluminum exhibits a bead geometry that is tightly coupled to the temperature of the previous layer, resulting in significant changes to the height of the deposited material at different points in the part. This paper presents a closed-loop approach to correcting for variations in the height of the deposited material between layers. We use an IR camera mounted on a separate robot to track the welding flame and estimate the height of deposited material. The robot velocity profile is then updated to account for the error in the previous layer and the nominal planned height profile while factoring in process and system constraints. Implementation of this framework showed significant improvement over the open-loop case and demonstrated robustness to inaccurate model parameters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04536v1-abstract-full').style.display = 'none'; document.getElementById('2412.04536v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">8 pages, 17 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/2412.02647">arXiv:2412.02647</a> <span> [<a href="https://arxiv.org/pdf/2412.02647">pdf</a>, <a href="https://arxiv.org/format/2412.02647">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Quaternary and Component-Binary Spreading Codes with Low Correlation for Navigation Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+P+V">P. Vijay Kumar</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sugandh Mishra</a>, <a href="/search/cs?searchtype=author&query=Dharmappa%2C+D">Dileep Dharmappa</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="2412.02647v1-abstract-short" style="display: inline;"> In the first part of this two-part paper, we construct a family MFD$_2$ of low-correlation quaternary spreading codes having period $2046$. By quaternary, we mean that the spreading code symbols are drawn from $Z_4$ and are designed to be used in conjunction with QPSK modulation. Apart from low auto and crosscorrelation properties, we also require in addition, to our knowledge for the first time,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02647v1-abstract-full').style.display = 'inline'; document.getElementById('2412.02647v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.02647v1-abstract-full" style="display: none;"> In the first part of this two-part paper, we construct a family MFD$_2$ of low-correlation quaternary spreading codes having period $2046$. By quaternary, we mean that the spreading code symbols are drawn from $Z_4$ and are designed to be used in conjunction with QPSK modulation. Apart from low auto and crosscorrelation properties, we also require in addition, to our knowledge for the first time, that the spreading code family IZ4$_2$ obtained by taking the union of the component in-phase and quadrature-phase binary spreading codes associated to each quaternary spreading code in MFD$_2$, also have desirable low-correlation properties. We also investigate the balance of the quaternary and binary spreading codes. The second part is motivated by an application to the design of spreading code, (in this application termed as ranging codes), having parameters suitable for use in a lunar PNT system. Two lengths that are of particular current interest for a planned lunar PNT satellite system are $2046$ and $10230$. We study the applicability of a subset IZ4$_{2S}$ of IZ4$_2$ containing balanced binary spreading codes having length $2046$ to such a lunar PNT system. We show that the spreading codes belonging to IZ4$_{2S}$ compare favorably with the spreading codes of length $2046$ appearing in a recent issue of Inside GNSS. We also show that the IZ4$_{10}$ spreading code family in which the spreading codes have length $10230$, compares well in comparison with spreading codes of length $10230$ described in this article. In addition, the IZ4$_{10}$ and IZ4$_2$ spreading codes have been paired so as to be orthogonal at zero shift despite their different lengths and chipping rates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02647v1-abstract-full').style.display = 'none'; document.getElementById('2412.02647v1-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 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/2412.01935">arXiv:2412.01935</a> <span> [<a href="https://arxiv.org/pdf/2412.01935">pdf</a>, <a href="https://arxiv.org/format/2412.01935">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"> Cross Domain Adaptation using Adversarial networks with Cyclic loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kaur%2C+M">Manpreet Kaur</a>, <a href="/search/cs?searchtype=author&query=Tomar%2C+A">Ankur Tomar</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Srijan Mishra</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+S">Shashwat Verma</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="2412.01935v1-abstract-short" style="display: inline;"> Deep Learning methods are highly local and sensitive to the domain of data they are trained with. Even a slight deviation from the domain distribution affects prediction accuracy of deep networks significantly. In this work, we have investigated a set of techniques aimed at increasing accuracy of generator networks which perform translation from one domain to the other in an adversarial setting. I… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01935v1-abstract-full').style.display = 'inline'; document.getElementById('2412.01935v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01935v1-abstract-full" style="display: none;"> Deep Learning methods are highly local and sensitive to the domain of data they are trained with. Even a slight deviation from the domain distribution affects prediction accuracy of deep networks significantly. In this work, we have investigated a set of techniques aimed at increasing accuracy of generator networks which perform translation from one domain to the other in an adversarial setting. In particular, we experimented with activations, the encoder-decoder network architectures, and introduced a Loss called cyclic loss to constrain the Generator network so that it learns effective source-target translation. This machine learning problem is motivated by myriad applications that can be derived from domain adaptation networks like generating labeled data from synthetic inputs in an unsupervised fashion, and using these translation network in conjunction with the original domain network to generalize deep learning networks across domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01935v1-abstract-full').style.display = 'none'; document.getElementById('2412.01935v1-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">16 pages, 14 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/2412.00224">arXiv:2412.00224</a> <span> [<a href="https://arxiv.org/pdf/2412.00224">pdf</a>, <a href="https://arxiv.org/format/2412.00224">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="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> An AI-Driven Data Mesh Architecture Enhancing Decision-Making in Infrastructure Construction and Public Procurement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saurabh Mishra</a>, <a href="/search/cs?searchtype=author&query=Shinde%2C+M">Mahendra Shinde</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+A">Aniket Yadav</a>, <a href="/search/cs?searchtype=author&query=Ayyub%2C+B">Bilal Ayyub</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+A">Anand Rao</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="2412.00224v1-abstract-short" style="display: inline;"> Infrastructure construction, often dubbed an "industry of industries," is closely linked with government spending and public procurement, offering significant opportunities for improved efficiency and productivity through better transparency and information access. By leveraging these opportunities, we can achieve notable gains in productivity, cost savings, and broader economic benefits. Our appr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00224v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00224v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00224v1-abstract-full" style="display: none;"> Infrastructure construction, often dubbed an "industry of industries," is closely linked with government spending and public procurement, offering significant opportunities for improved efficiency and productivity through better transparency and information access. By leveraging these opportunities, we can achieve notable gains in productivity, cost savings, and broader economic benefits. Our approach introduces an integrated software ecosystem utilizing Data Mesh and Service Mesh architectures. This system includes the largest training dataset for infrastructure and procurement, encompassing over 100 billion tokens, scientific publications, activities, and risk data, all structured by a systematic AI framework. Supported by a Knowledge Graph linked to domain-specific multi-agent tasks and Q&A capabilities, our platform standardizes and ingests diverse data sources, transforming them into structured knowledge. Leveraging large language models (LLMs) and automation, our system revolutionizes data structuring and knowledge creation, aiding decision-making in early-stage project planning, detailed research, market trend analysis, and qualitative assessments. Its web-scalable architecture delivers domain-curated information, enabling AI agents to facilitate reasoning and manage uncertainties, while preparing for future expansions with specialized agents targeting particular challenges. This integration of AI with domain expertise not only boosts efficiency and decision-making in construction and infrastructure but also establishes a framework for enhancing government efficiency and accelerating the transition of traditional industries to digital workflows. This work is poised to significantly influence AI-driven initiatives in this sector and guide best practices in AI Operations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00224v1-abstract-full').style.display = 'none'; document.getElementById('2412.00224v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 November, 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/2411.19865">arXiv:2411.19865</a> <span> [<a href="https://arxiv.org/pdf/2411.19865">pdf</a>, <a href="https://arxiv.org/format/2411.19865">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Reverse Thinking Makes LLMs Stronger Reasoners </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+J+C">Justin Chih-Yao Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zifeng Wang</a>, <a href="/search/cs?searchtype=author&query=Palangi%2C+H">Hamid Palangi</a>, <a href="/search/cs?searchtype=author&query=Han%2C+R">Rujun Han</a>, <a href="/search/cs?searchtype=author&query=Ebrahimi%2C+S">Sayna Ebrahimi</a>, <a href="/search/cs?searchtype=author&query=Le%2C+L">Long Le</a>, <a href="/search/cs?searchtype=author&query=Perot%2C+V">Vincent Perot</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swaroop Mishra</a>, <a href="/search/cs?searchtype=author&query=Bansal%2C+M">Mohit Bansal</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+C">Chen-Yu Lee</a>, <a href="/search/cs?searchtype=author&query=Pfister%2C+T">Tomas Pfister</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="2411.19865v1-abstract-short" style="display: inline;"> Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forward and backward thinking. To enable Large Language Models (LLMs) to perform reverse thinking, we intr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19865v1-abstract-full').style.display = 'inline'; document.getElementById('2411.19865v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.19865v1-abstract-full" style="display: none;"> Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forward and backward thinking. To enable Large Language Models (LLMs) to perform reverse thinking, we introduce Reverse-Enhanced Thinking (RevThink), a framework composed of data augmentation and learning objectives. In RevThink, we augment the dataset by collecting structured forward-backward reasoning from a teacher model, consisting of: (1) the original question, (2) forward reasoning, (3) backward question, and (4) backward reasoning. We then employ three objectives to train a smaller student model in a multi-task learning fashion: (a) generate forward reasoning from a question, (b) generate a backward question from a question, and (c) generate backward reasoning from the backward question. Experiments across 12 datasets covering commonsense, math, and logical reasoning show an average 13.53% improvement over the student model's zero-shot performance and a 6.84% improvement over the strongest knowledge distillation baselines. Moreover, our method demonstrates sample efficiency -- using only 10% of the correct forward reasoning from the training data, it outperforms a standard fine-tuning method trained on 10x more forward reasoning. RevThink also exhibits strong generalization to out-of-distribution held-out datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19865v1-abstract-full').style.display = 'none'; document.getElementById('2411.19865v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 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">20 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.17002">arXiv:2411.17002</a> <span> [<a href="https://arxiv.org/pdf/2411.17002">pdf</a>, <a href="https://arxiv.org/format/2411.17002">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"> Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shambhavi Mishra</a>, <a href="/search/cs?searchtype=author&query=Silva-Rodr%C4%B1guez%2C+J">Julio Silva-Rodr谋guez</a>, <a href="/search/cs?searchtype=author&query=Ayed%2C+I+B">Ismail Ben Ayed</a>, <a href="/search/cs?searchtype=author&query=Pedersoli%2C+M">Marco Pedersoli</a>, <a href="/search/cs?searchtype=author&query=Dolz%2C+J">Jose Dolz</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="2411.17002v1-abstract-short" style="display: inline;"> Vision-language foundation models, such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is significantly degraded. In this work, we explore how to efficiently leverage class text information to mitigate these distribution drifts encountered by large pre-trained visio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17002v1-abstract-full').style.display = 'inline'; document.getElementById('2411.17002v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.17002v1-abstract-full" style="display: none;"> Vision-language foundation models, such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is significantly degraded. In this work, we explore how to efficiently leverage class text information to mitigate these distribution drifts encountered by large pre-trained vision-language models (VLMs) during test-time inference. In particular, we propose to generate pseudo-labels for the test-time samples by exploiting generic class text embeddings as fixed centroids of a label assignment problem, which is efficiently solved with Optimal Transport. Furthermore, the proposed adaptation method (CLIP-OT) integrates a multiple template knowledge distillation approach, which replicates multi-view contrastive learning strategies in unsupervised representation learning but without incurring additional computational complexity. Extensive experiments on multiple popular test-time adaptation benchmarks presenting diverse complexity empirically show the superiority of CLIP-OT, achieving performance gains of up to 7% over recent state-of-the-art methods, yet being computationally and memory efficient. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17002v1-abstract-full').style.display = 'none'; document.getElementById('2411.17002v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.16502">arXiv:2411.16502</a> <span> [<a href="https://arxiv.org/pdf/2411.16502">pdf</a>, <a href="https://arxiv.org/format/2411.16502">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"> Interpreting Language Reward Models via Contrastive Explanations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Junqi Jiang</a>, <a href="/search/cs?searchtype=author&query=Bewley%2C+T">Tom Bewley</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saumitra Mishra</a>, <a href="/search/cs?searchtype=author&query=Lecue%2C+F">Freddy Lecue</a>, <a href="/search/cs?searchtype=author&query=Veloso%2C+M">Manuela Veloso</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="2411.16502v1-abstract-short" style="display: inline;"> Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM responses to the same prompt by predicting and comparing reward scores. However, as they are typically modified versions of LLMs with scalar output heads, RMs are large black boxes whose predictions are not explainable. More tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16502v1-abstract-full').style.display = 'inline'; document.getElementById('2411.16502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.16502v1-abstract-full" style="display: none;"> Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM responses to the same prompt by predicting and comparing reward scores. However, as they are typically modified versions of LLMs with scalar output heads, RMs are large black boxes whose predictions are not explainable. More transparent RMs would enable improved trust in the alignment of LLMs. In this work, we propose to use contrastive explanations to explain any binary response comparison made by an RM. Specifically, we generate a diverse set of new comparisons similar to the original one to characterise the RM's local behaviour. The perturbed responses forming the new comparisons are generated to explicitly modify manually specified high-level evaluation attributes, on which analyses of RM behaviour are grounded. In quantitative experiments, we validate the effectiveness of our method for finding high-quality contrastive explanations. We then showcase the qualitative usefulness of our method for investigating global sensitivity of RMs to each evaluation attribute, and demonstrate how representative examples can be automatically extracted to explain and compare behaviours of different RMs. We see our method as a flexible framework for RM explanation, providing a basis for more interpretable and trustworthy LLM alignment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16502v1-abstract-full').style.display = 'none'; document.getElementById('2411.16502v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.15028">arXiv:2411.15028</a> <span> [<a href="https://arxiv.org/pdf/2411.15028">pdf</a>, <a href="https://arxiv.org/format/2411.15028">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"> FloAt: Flow Warping of Self-Attention for Clothing Animation Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S+S">Swasti Shreya Mishra</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+K">Kuldeep Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Ceylan%2C+D">Duygu Ceylan</a>, <a href="/search/cs?searchtype=author&query=Srinivasan%2C+B+V">Balaji Vasan Srinivasan</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="2411.15028v1-abstract-short" style="display: inline;"> We propose a diffusion model-based approach, FloAtControlNet to generate cinemagraphs composed of animations of human clothing. We focus on human clothing like dresses, skirts and pants. The input to our model is a text prompt depicting the type of clothing and the texture of clothing like leopard, striped, or plain, and a sequence of normal maps that capture the underlying animation that we desir… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15028v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15028v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15028v1-abstract-full" style="display: none;"> We propose a diffusion model-based approach, FloAtControlNet to generate cinemagraphs composed of animations of human clothing. We focus on human clothing like dresses, skirts and pants. The input to our model is a text prompt depicting the type of clothing and the texture of clothing like leopard, striped, or plain, and a sequence of normal maps that capture the underlying animation that we desire in the output. The backbone of our method is a normal-map conditioned ControlNet which is operated in a training-free regime. The key observation is that the underlying animation is embedded in the flow of the normal maps. We utilize the flow thus obtained to manipulate the self-attention maps of appropriate layers. Specifically, the self-attention maps of a particular layer and frame are recomputed as a linear combination of itself and the self-attention maps of the same layer and the previous frame, warped by the flow on the normal maps of the two frames. We show that manipulating the self-attention maps greatly enhances the quality of the clothing animation, making it look more natural as well as suppressing the background artifacts. Through extensive experiments, we show that the method proposed beats all baselines both qualitatively in terms of visual results and user study. Specifically, our method is able to alleviate the background flickering that exists in other diffusion model-based baselines that we consider. In addition, we show that our method beats all baselines in terms of RMSE and PSNR computed using the input normal map sequences and the normal map sequences obtained from the output RGB frames. Further, we show that well-established evaluation metrics like LPIPS, SSIM, and CLIP scores that are generally for visual quality are not necessarily suitable for capturing the subtle motions in human clothing animations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15028v1-abstract-full').style.display = 'none'; document.getElementById('2411.15028v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14959">arXiv:2411.14959</a> <span> [<a href="https://arxiv.org/pdf/2411.14959">pdf</a>, <a href="https://arxiv.org/format/2411.14959">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Design-o-meter: Towards Evaluating and Refining Graphic Designs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Goyal%2C+S">Sahil Goyal</a>, <a href="/search/cs?searchtype=author&query=Mahajan%2C+A">Abhinav Mahajan</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swasti Mishra</a>, <a href="/search/cs?searchtype=author&query=Udhayanan%2C+P">Prateksha Udhayanan</a>, <a href="/search/cs?searchtype=author&query=Shukla%2C+T">Tripti Shukla</a>, <a href="/search/cs?searchtype=author&query=Joseph%2C+K+J">K J Joseph</a>, <a href="/search/cs?searchtype=author&query=Srinivasan%2C+B+V">Balaji Vasan Srinivasan</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="2411.14959v1-abstract-short" style="display: inline;"> Graphic designs are an effective medium for visual communication. They range from greeting cards to corporate flyers and beyond. Off-late, machine learning techniques are able to generate such designs, which accelerates the rate of content production. An automated way of evaluating their quality becomes critical. Towards this end, we introduce Design-o-meter, a data-driven methodology to quantify… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14959v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14959v1-abstract-full" style="display: none;"> Graphic designs are an effective medium for visual communication. They range from greeting cards to corporate flyers and beyond. Off-late, machine learning techniques are able to generate such designs, which accelerates the rate of content production. An automated way of evaluating their quality becomes critical. Towards this end, we introduce Design-o-meter, a data-driven methodology to quantify the goodness of graphic designs. Further, our approach can suggest modifications to these designs to improve its visual appeal. To the best of our knowledge, Design-o-meter is the first approach that scores and refines designs in a unified framework despite the inherent subjectivity and ambiguity of the setting. Our exhaustive quantitative and qualitative analysis of our approach against baselines adapted for the task (including recent Multimodal LLM-based approaches) brings out the efficacy of our methodology. We hope our work will usher more interest in this important and pragmatic problem setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14959v1-abstract-full').style.display = 'none'; document.getElementById('2411.14959v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to WACV 2025. Project page: https://sahilg06.github.io/Design-o-meter/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14119">arXiv:2411.14119</a> <span> [<a href="https://arxiv.org/pdf/2411.14119">pdf</a>, <a href="https://arxiv.org/format/2411.14119">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"> Uncertainty-Aware Regression for Socio-Economic Estimation via Multi-View Remote Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/cs?searchtype=author&query=Ishida%2C+S">Sahoko Ishida</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/cs?searchtype=author&query=Jenson%2C+D">Daniel Jenson</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/cs?searchtype=author&query=Navott%2C+J">Jhonathan Navott</a>, <a href="/search/cs?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2411.14119v1-abstract-short" style="display: inline;"> Remote sensing imagery offers rich spectral data across extensive areas for Earth observation. Many attempts have been made to leverage these data with transfer learning to develop scalable alternatives for estimating socio-economic conditions, reducing reliance on expensive survey-collected data. However, much of this research has primarily focused on daytime satellite imagery due to the limitati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14119v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14119v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14119v1-abstract-full" style="display: none;"> Remote sensing imagery offers rich spectral data across extensive areas for Earth observation. Many attempts have been made to leverage these data with transfer learning to develop scalable alternatives for estimating socio-economic conditions, reducing reliance on expensive survey-collected data. However, much of this research has primarily focused on daytime satellite imagery due to the limitation that most pre-trained models are trained on 3-band RGB images. Consequently, modeling techniques for spectral bands beyond the visible spectrum have not been thoroughly investigated. Additionally, quantifying uncertainty in remote sensing regression has been less explored, yet it is essential for more informed targeting and iterative collection of ground truth survey data. In this paper, we introduce a novel framework that leverages generic foundational vision models to process remote sensing imagery using combinations of three spectral bands to exploit multi-spectral data. We also employ methods such as heteroscedastic regression and Bayesian modeling to generate uncertainty estimates for the predictions. Experimental results demonstrate that our method outperforms existing models that use RGB or multi-spectral models with unstructured band usage. Moreover, our framework helps identify uncertain predictions, guiding future ground truth data acquisition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14119v1-abstract-full').style.display = 'none'; document.getElementById('2411.14119v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11409">arXiv:2411.11409</a> <span> [<a href="https://arxiv.org/pdf/2411.11409">pdf</a>, <a href="https://arxiv.org/format/2411.11409">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yunong Liu</a>, <a href="/search/cs?searchtype=author&query=Eyzaguirre%2C+C">Cristobal Eyzaguirre</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Manling Li</a>, <a href="/search/cs?searchtype=author&query=Khanna%2C+S">Shubh Khanna</a>, <a href="/search/cs?searchtype=author&query=Niebles%2C+J+C">Juan Carlos Niebles</a>, <a href="/search/cs?searchtype=author&query=Ravi%2C+V">Vineeth Ravi</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saumitra Mishra</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weiyu Liu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiajun Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11409v1-abstract-short" style="display: inline;"> Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not yet tackled the 4D grounding of assembly instructions in videos, essential for a holistic understanding of assembly in 3D space over time. We introduce IKEA Vid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11409v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11409v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11409v1-abstract-full" style="display: none;"> Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not yet tackled the 4D grounding of assembly instructions in videos, essential for a holistic understanding of assembly in 3D space over time. We introduce IKEA Video Manuals, a dataset that features 3D models of furniture parts, instructional manuals, assembly videos from the Internet, and most importantly, annotations of dense spatio-temporal alignments between these data modalities. To demonstrate the utility of IKEA Video Manuals, we present five applications essential for shape assembly: assembly plan generation, part-conditioned segmentation, part-conditioned pose estimation, video object segmentation, and furniture assembly based on instructional video manuals. For each application, we provide evaluation metrics and baseline methods. Through experiments on our annotated data, we highlight many challenges in grounding assembly instructions in videos to improve shape assembly, including handling occlusions, varying viewpoints, and extended assembly sequences. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11409v1-abstract-full').style.display = 'none'; document.getElementById('2411.11409v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2024 Datasets and Benchmarks Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08981">arXiv:2411.08981</a> <span> [<a href="https://arxiv.org/pdf/2411.08981">pdf</a>, <a href="https://arxiv.org/format/2411.08981">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="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Reliability, Resilience and Human Factors Engineering for Trustworthy AI Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saurabh Mishra</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+A">Anand Rao</a>, <a href="/search/cs?searchtype=author&query=Krishnan%2C+R">Ramayya Krishnan</a>, <a href="/search/cs?searchtype=author&query=Ayyub%2C+B">Bilal Ayyub</a>, <a href="/search/cs?searchtype=author&query=Aria%2C+A">Amin Aria</a>, <a href="/search/cs?searchtype=author&query=Zio%2C+E">Enrico Zio</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="2411.08981v1-abstract-short" style="display: inline;"> As AI systems become integral to critical operations across industries and services, ensuring their reliability and safety is essential. We offer a framework that integrates established reliability and resilience engineering principles into AI systems. By applying traditional metrics such as failure rate and Mean Time Between Failures (MTBF) along with resilience engineering and human reliability… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08981v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08981v1-abstract-full" style="display: none;"> As AI systems become integral to critical operations across industries and services, ensuring their reliability and safety is essential. We offer a framework that integrates established reliability and resilience engineering principles into AI systems. By applying traditional metrics such as failure rate and Mean Time Between Failures (MTBF) along with resilience engineering and human reliability analysis, we propose an integrate framework to manage AI system performance, and prevent or efficiently recover from failures. Our work adapts classical engineering methods to AI systems and outlines a research agenda for future technical studies. We apply our framework to a real-world AI system, using system status data from platforms such as openAI, to demonstrate its practical applicability. This framework aligns with emerging global standards and regulatory frameworks, providing a methodology to enhance the trustworthiness of AI systems. Our aim is to guide policy, regulation, and the development of reliable, safe, and adaptable AI technologies capable of consistent performance in real-world environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08981v1-abstract-full').style.display = 'none'; document.getElementById('2411.08981v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.07853">arXiv:2411.07853</a> <span> [<a href="https://arxiv.org/pdf/2411.07853">pdf</a>, <a href="https://arxiv.org/format/2411.07853">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"> Evidential time-to-event prediction with calibrated uncertainty quantification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+L">Ling Huang</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+Y">Yucheng Xing</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/cs?searchtype=author&query=Denoeux%2C+T">Thierry Denoeux</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+M">Mengling Feng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.07853v2-abstract-short" style="display: inline;"> Time-to-event analysis provides insights into clinical prognosis and treatment recommendations. However, this task is more challenging than standard regression problems due to the presence of censored observations. Additionally, the lack of confidence assessment, model robustness, and prediction calibration raises concerns about the reliability of predictions. To address these challenges, we propo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07853v2-abstract-full').style.display = 'inline'; document.getElementById('2411.07853v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07853v2-abstract-full" style="display: none;"> Time-to-event analysis provides insights into clinical prognosis and treatment recommendations. However, this task is more challenging than standard regression problems due to the presence of censored observations. Additionally, the lack of confidence assessment, model robustness, and prediction calibration raises concerns about the reliability of predictions. To address these challenges, we propose an evidential regression model specifically designed for time-to-event prediction. The proposed model quantifies both epistemic and aleatory uncertainties using Gaussian Random Fuzzy Numbers and belief functions, providing clinicians with uncertainty-aware survival time predictions. The model is trained by minimizing a generalized negative log-likelihood function accounting for data censoring. Experimental evaluations using simulated datasets with different data distributions and censoring conditions, as well as real-world datasets across diverse clinical applications, demonstrate that our model delivers both accurate and reliable performance, outperforming state-of-the-art methods. These results highlight the potential of our approach for enhancing clinical decision-making in survival analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07853v2-abstract-full').style.display = 'none'; document.getElementById('2411.07853v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <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 submitted to International Journal of Approximate Reasoning</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21589">arXiv:2410.21589</a> <span> [<a href="https://arxiv.org/pdf/2410.21589">pdf</a>, <a href="https://arxiv.org/format/2410.21589">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> The Toxicity Phenomenon Across Social Media </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hanscom%2C+R">Rhett Hanscom</a>, <a href="/search/cs?searchtype=author&query=Lehman%2C+T+S">Tamara Silbergleit Lehman</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+Q">Qin Lv</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shivakant Mishra</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="2410.21589v1-abstract-short" style="display: inline;"> Social media platforms have evolved rapidly in modernity without strong regulation. One clear obstacle faced by current users is that of toxicity. Toxicity on social media manifests through a number of forms, including harassment, negativity, misinformation or other means of divisiveness. In this paper, we characterize literature surrounding toxicity, formalize a definition of toxicity, propose a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21589v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21589v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21589v1-abstract-full" style="display: none;"> Social media platforms have evolved rapidly in modernity without strong regulation. One clear obstacle faced by current users is that of toxicity. Toxicity on social media manifests through a number of forms, including harassment, negativity, misinformation or other means of divisiveness. In this paper, we characterize literature surrounding toxicity, formalize a definition of toxicity, propose a novel cycle of internet extremism, list current approaches to toxicity detection, outline future directions to minimize toxicity in future social media endeavors, and identify current gaps in research space. We present a novel perspective of the negative impacts of social media platforms and fill a gap in literature to help improve the future of social media platforms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21589v1-abstract-full').style.display = 'none'; document.getElementById('2410.21589v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 2 figures, 2 tables, Cycle of Internet Extremism</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> J.4; K.4.1; K.4.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20231">arXiv:2410.20231</a> <span> [<a href="https://arxiv.org/pdf/2410.20231">pdf</a>, <a href="https://arxiv.org/format/2410.20231">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"> CAVE-Net: Classifying Abnormalities in Video Capsule Endoscopy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Harish%2C+I">Ishita Harish</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saurav Mishra</a>, <a href="/search/cs?searchtype=author&query=Bhadoria%2C+N">Neha Bhadoria</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+R">Rithik Kumar</a>, <a href="/search/cs?searchtype=author&query=Arora%2C+M">Madhav Arora</a>, <a href="/search/cs?searchtype=author&query=Zahra%2C+S+R">Syed Rameem Zahra</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+A">Ankur Gupta</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="2410.20231v3-abstract-short" style="display: inline;"> Accurate classification of medical images is critical for detecting abnormalities in the gastrointestinal tract, a domain where misclassification can significantly impact patient outcomes. We propose an ensemble-based approach to improve diagnostic accuracy in analyzing complex image datasets. Using a Convolutional Block Attention Module along with a Deep Neural Network, we leverage the unique fea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20231v3-abstract-full').style.display = 'inline'; document.getElementById('2410.20231v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20231v3-abstract-full" style="display: none;"> Accurate classification of medical images is critical for detecting abnormalities in the gastrointestinal tract, a domain where misclassification can significantly impact patient outcomes. We propose an ensemble-based approach to improve diagnostic accuracy in analyzing complex image datasets. Using a Convolutional Block Attention Module along with a Deep Neural Network, we leverage the unique feature extraction capabilities of each model to enhance the overall accuracy. The classification models, such as Random Forest, XGBoost, Support Vector Machine and K-Nearest Neighbors are introduced to further diversify the predictive power of proposed ensemble. By using these methods, the proposed framework, CAVE-Net, provides robust feature discrimination and improved classification results. Experimental evaluations demonstrate that the CAVE-Net achieves high accuracy and robustness across challenging and imbalanced classes, showing significant promise for broader applications in computer vision tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20231v3-abstract-full').style.display = 'none'; document.getElementById('2410.20231v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20004">arXiv:2410.20004</a> <span> [<a href="https://arxiv.org/pdf/2410.20004">pdf</a>, <a href="https://arxiv.org/format/2410.20004">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Lightweight, Secure and Stateful Serverless Computing with PSL </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thomas%2C+A">Alexander Thomas</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shubham Mishra</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">Kaiyuan Chen</a>, <a href="/search/cs?searchtype=author&query=Kubiatowicz%2C+J">John Kubiatowicz</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="2410.20004v1-abstract-short" style="display: inline;"> We present PSL, a lightweight, secure and stateful Function-as-a-Serivce (FaaS) framework for Trusted Execution Environments (TEEs). The framework provides rich programming language support on heterogeneous TEE hardware for statically compiled binaries and/or WebAssembly (WASM) bytecodes, with a familiar Key-Value Store (KVS) interface to secure, performant, network-embedded storage. It achieves n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20004v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20004v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20004v1-abstract-full" style="display: none;"> We present PSL, a lightweight, secure and stateful Function-as-a-Serivce (FaaS) framework for Trusted Execution Environments (TEEs). The framework provides rich programming language support on heterogeneous TEE hardware for statically compiled binaries and/or WebAssembly (WASM) bytecodes, with a familiar Key-Value Store (KVS) interface to secure, performant, network-embedded storage. It achieves near-native execution speeds by utilizing the dynamic memory mapping capabilities of Intel SGX2 to create an in-enclave WASM runtime with Just-In-Time (JIT) compilation. PSL is designed to efficiently operate within an asynchronous environment with a distributed tamper-proof confidential storage system, assuming minority failures. The system exchanges eventually-consistent state updates across nodes while utilizing release-consistent locking mechanisms to enhance transactional capabilities. The execution of PSL is up to 3.7x faster than the state-of-the-art SGX WASM runtime. PSL reaches 95k ops/s with YCSB 100% read workload and 89k ops/s with 50% read/write workload. We demonstrate the scalability and adaptivity of PSL through a case study of secure and distributed training of deep neural networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20004v1-abstract-full').style.display = 'none'; document.getElementById('2410.20004v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19978">arXiv:2410.19978</a> <span> [<a href="https://arxiv.org/pdf/2410.19978">pdf</a>, <a href="https://arxiv.org/format/2410.19978">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"> Global Graph Counterfactual Explanation: A Subgraph Mapping Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+Y">Yinhan He</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+W">Wendy Zheng</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yaochen Zhu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+J">Jing Ma</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Saumitra Mishra</a>, <a href="/search/cs?searchtype=author&query=Raman%2C+N">Natraj Raman</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+N">Ninghao Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jundong Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19978v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-le… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19978v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19978v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19978v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-level perspective (i.e., generating counterfactuals for each individual graph), which suffers from information overload and lacks insights into the broader cross-graph relationships. To address such issues, we propose GlobalGCE, a novel global-level graph counterfactual explanation method. GlobalGCE aims to identify a collection of subgraph mapping rules as counterfactual explanations for the target GNN. According to these rules, substituting certain significant subgraphs with their counterfactual subgraphs will change the GNN prediction to the desired class for most graphs (i.e., maximum coverage). Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated. Extensive experiments demonstrate the superiority of our GlobalGCE compared to existing baselines. Our code can be found at https://anonymous.4open.science/r/GlobalGCE-92E8. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19978v1-abstract-full').style.display = 'none'; document.getElementById('2410.19978v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14702">arXiv:2410.14702</a> <span> [<a href="https://arxiv.org/pdf/2410.14702">pdf</a>, <a href="https://arxiv.org/format/2410.14702">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"> Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gupta%2C+H">Himanshu Gupta</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+S">Shreyas Verma</a>, <a href="/search/cs?searchtype=author&query=Anantheswaran%2C+U">Ujjwala Anantheswaran</a>, <a href="/search/cs?searchtype=author&query=Scaria%2C+K">Kevin Scaria</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Mihir Parmar</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swaroop Mishra</a>, <a href="/search/cs?searchtype=author&query=Baral%2C+C">Chitta Baral</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="2410.14702v1-abstract-short" style="display: inline;"> Multi-modal Large Language Models (MLLMs) exhibit impressive problem-solving abilities in various domains, but their visual comprehension and abstract reasoning skills remain under-evaluated. To this end, we present PolyMATH, a challenging benchmark aimed at evaluating the general cognitive reasoning abilities of MLLMs. PolyMATH comprises 5,000 manually collected high-quality images of cognitive t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14702v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14702v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14702v1-abstract-full" style="display: none;"> Multi-modal Large Language Models (MLLMs) exhibit impressive problem-solving abilities in various domains, but their visual comprehension and abstract reasoning skills remain under-evaluated. To this end, we present PolyMATH, a challenging benchmark aimed at evaluating the general cognitive reasoning abilities of MLLMs. PolyMATH comprises 5,000 manually collected high-quality images of cognitive textual and visual challenges across 10 distinct categories, including pattern recognition, spatial reasoning, and relative reasoning. We conducted a comprehensive, and quantitative evaluation of 15 MLLMs using four diverse prompting strategies, including Chain-of-Thought and Step-Back. The best scores achieved on PolyMATH are ~41%, ~36%, and ~27%, obtained by Claude-3.5 Sonnet, GPT-4o and Gemini-1.5 Pro respectively - highlighting the logical and visual complexity of these questions. A further fine-grained error analysis reveals that these models struggle to understand spatial relations and perform drawn-out, high-level reasoning. This is further strengthened by our ablation study estimating MLLM performance when given textual descriptions in place of diagrams. As evidenced by ~4% improvement over textual descriptions as opposed to actual images, we discover that models do not truly comprehend visual diagrams and the spatial information therein, and are thus prone to logical errors. Finally, we evaluate the OpenAI o1 models and find that their performance only matches the human baseline, highlighting the difficulty of the benchmark. The results on PolyMATH highlight the room for improvement in multi-modal reasoning and provide unique insights to guide the development of future MLLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14702v1-abstract-full').style.display = 'none'; document.getElementById('2410.14702v1-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 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">49 pages, (10 pages paper, 9 pages references, 30 pages appendix)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12372">arXiv:2410.12372</a> <span> [<a href="https://arxiv.org/pdf/2410.12372">pdf</a>, <a href="https://arxiv.org/format/2410.12372">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="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> GAN Based Top-Down View Synthesis in Reinforcement Learning Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Younus%2C+U">Usama Younus</a>, <a href="/search/cs?searchtype=author&query=Jayasundara%2C+V">Vinoj Jayasundara</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shivam Mishra</a>, <a href="/search/cs?searchtype=author&query=Aslan%2C+S">Suleyman Aslan</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="2410.12372v1-abstract-short" style="display: inline;"> Human actions are based on the mental perception of the environment. Even when all the aspects of an environment are not visible, humans have an internal mental model that can generalize the partially visible scenes to fully constructed and connected views. This internal mental model uses learned abstract representations of spatial and temporal aspects of the environments encountered in the past.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12372v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12372v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12372v1-abstract-full" style="display: none;"> Human actions are based on the mental perception of the environment. Even when all the aspects of an environment are not visible, humans have an internal mental model that can generalize the partially visible scenes to fully constructed and connected views. This internal mental model uses learned abstract representations of spatial and temporal aspects of the environments encountered in the past. Artificial agents in reinforcement learning environments also benefit by learning a representation of the environment from experience. It provides the agent with viewpoints that are not directly visible to it, helping it make better policy decisions. It can also be used to predict the future state of the environment. This project explores learning the top-down view of an RL environment based on the artificial agent's first-person view observations with a generative adversarial network(GAN). The top-down view is useful as it provides a complete overview of the environment by building a map of the entire environment. It provides information about the objects' dimensions and shapes along with their relative positions with one another. Initially, when only a partial observation of the environment is visible to the agent, only a partial top-down view is generated. As the agent explores the environment through a set of actions, the generated top-down view becomes complete. This generated top-down view can assist the agent in deducing better policy decisions. The focus of the project is to learn the top-down view of an RL environment. It doesn't deal with any Reinforcement Learning task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12372v1-abstract-full').style.display = 'none'; document.getElementById('2410.12372v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06828">arXiv:2410.06828</a> <span> [<a href="https://arxiv.org/pdf/2410.06828">pdf</a>, <a href="https://arxiv.org/format/2410.06828">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"> Transfer Learning for a Class of Cascade Dynamical Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rabiei%2C+S">Shima Rabiei</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sandipan Mishra</a>, <a href="/search/cs?searchtype=author&query=Paternain%2C+S">Santiago Paternain</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="2410.06828v1-abstract-short" style="display: inline;"> This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training strategy is that running simulations in the full-state system may take excessive time if the dynamics are complex. While transfer learning alleviates the compu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06828v1-abstract-full').style.display = 'inline'; document.getElementById('2410.06828v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06828v1-abstract-full" style="display: none;"> This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training strategy is that running simulations in the full-state system may take excessive time if the dynamics are complex. While transfer learning alleviates the computational issue, the transfer guarantees depend on the discrepancy between the two systems. In this work, we consider a class of cascade dynamical systems, where the dynamics of a subset of the state-space influence the rest of the states but not vice-versa. The reinforcement learning policy learns in a model that ignores the dynamics of these states and treats them as commanded inputs. In the full-state system, these dynamics are handled using a classic controller (e.g., a PID). These systems have vast applications in the control literature and their structure allows us to provide transfer guarantees that depend on the stability of the inner loop controller. Numerical experiments on a quadrotor support the theoretical findings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06828v1-abstract-full').style.display = 'none'; document.getElementById('2410.06828v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">8 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.2.2, I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05435">arXiv:2410.05435</a> <span> [<a href="https://arxiv.org/pdf/2410.05435">pdf</a>, <a href="https://arxiv.org/format/2410.05435">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> Salient Store: Enabling Smart Storage for Continuous Learning Edge Servers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+C+S">Cyan Subhra Mishra</a>, <a href="/search/cs?searchtype=author&query=Chaudhary%2C+D">Deeksha Chaudhary</a>, <a href="/search/cs?searchtype=author&query=Sampson%2C+J">Jack Sampson</a>, <a href="/search/cs?searchtype=author&query=Knademir%2C+M+T">Mahmut Taylan Knademir</a>, <a href="/search/cs?searchtype=author&query=Das%2C+C">Chita Das</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="2410.05435v1-abstract-short" style="display: inline;"> As continuous learning based video analytics continue to evolve, the role of efficient edge servers in efficiently managing vast and dynamic datasets is becoming increasingly crucial. Unlike their compute architecture, storage and archival system for these edge servers has often been under-emphasized. This is unfortunate as they contribute significantly to the data management and data movement, es… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05435v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05435v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05435v1-abstract-full" style="display: none;"> As continuous learning based video analytics continue to evolve, the role of efficient edge servers in efficiently managing vast and dynamic datasets is becoming increasingly crucial. Unlike their compute architecture, storage and archival system for these edge servers has often been under-emphasized. This is unfortunate as they contribute significantly to the data management and data movement, especially in a emerging complute landscape where date storage and data protection has become one of the key concerns. To mitigate this, we propose Salient Store that specifically focuses on the integration of Computational Storage Devices (CSDs) into edge servers to enhance data processing and management, particularly in continuous learning scenarios, prevalent in fields such as autonomous driving and urban mobility. Our research, gos beyond the compute domain, and identifies the gaps in current storage system designs. We proposes a framework that aligns more closely with the growing data demands. We present a detailed analysis of data movement challenges within the archival workflows and demonstrate how the strategic integration of CSDs can significantly optimize data compression, encryption, as well as other data management tasks, to improve overall system performance. By leveraging the parallel processing capabilities of FPGAs and the high internal bandwidth of SSDs, Salient Store reduces the communication latency and data volume by ~6.2x and ~6.1x, respectively. This paper provides a comprehensive overview of the potential of CSDs to revolutionize storage, making them not just data repositories but active participants in the computational process. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05435v1-abstract-full').style.display = 'none'; document.getElementById('2410.05435v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05358">arXiv:2410.05358</a> <span> [<a href="https://arxiv.org/pdf/2410.05358">pdf</a>, <a href="https://arxiv.org/format/2410.05358">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"> A Predictive and Optimization Approach for Enhanced Urban Mobility Using Spatiotemporal Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shambhavi Mishra</a>, <a href="/search/cs?searchtype=author&query=Murthy%2C+T+S">T. Satyanarayana Murthy</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="2410.05358v1-abstract-short" style="display: inline;"> In modern urban centers, effective transportation management poses a significant challenge, with traffic jams and inconsistent travel durations greatly affecting commuters and logistics operations. This study introduces a novel method for enhancing urban mobility by combining machine learning algorithms with live traffic information. We developed predictive models for journey time and congestion a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05358v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05358v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05358v1-abstract-full" style="display: none;"> In modern urban centers, effective transportation management poses a significant challenge, with traffic jams and inconsistent travel durations greatly affecting commuters and logistics operations. This study introduces a novel method for enhancing urban mobility by combining machine learning algorithms with live traffic information. We developed predictive models for journey time and congestion analysis using data from New York City's yellow taxi trips. The research employed a spatiotemporal analysis framework to identify traffic trends and implemented real-time route optimization using the GraphHopper API. This system determines the most efficient paths based on current conditions, adapting to changes in traffic flow. The methodology utilizes Spark MLlib for predictive modeling and Spark Streaming for processing data in real-time. By integrating historical data analysis with current traffic inputs, our system shows notable enhancements in both travel time forecasts and route optimization, demonstrating its potential for widespread application in major urban areas. This research contributes to ongoing efforts aimed at reducing urban congestion and improving transportation efficiency through advanced data-driven methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05358v1-abstract-full').style.display = 'none'; document.getElementById('2410.05358v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03464">arXiv:2410.03464</a> <span> [<a href="https://arxiv.org/pdf/2410.03464">pdf</a>, <a href="https://arxiv.org/format/2410.03464">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="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Dynamical Systems">math.DS</span> </div> </div> <p class="title is-5 mathjax"> S7: Selective and Simplified State Space Layers for Sequence Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Soydan%2C+T">Taylan Soydan</a>, <a href="/search/cs?searchtype=author&query=Zubi%C4%87%2C+N">Nikola Zubi膰</a>, <a href="/search/cs?searchtype=author&query=Messikommer%2C+N">Nico Messikommer</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Siddhartha Mishra</a>, <a href="/search/cs?searchtype=author&query=Scaramuzza%2C+D">Davide Scaramuzza</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="2410.03464v1-abstract-short" style="display: inline;"> A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, they often lack input-dependent filtering or require substantial increases in model complexity to handle input variability. We address this gap by introducing S7, a simplified yet powerful SSM that can handle input depend… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03464v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03464v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03464v1-abstract-full" style="display: none;"> A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, they often lack input-dependent filtering or require substantial increases in model complexity to handle input variability. We address this gap by introducing S7, a simplified yet powerful SSM that can handle input dependence while incorporating stable reparameterization and specific design choices to dynamically adjust state transitions based on input content, maintaining efficiency and performance. We prove that this reparameterization ensures stability in long-sequence modeling by keeping state transitions well-behaved over time. Additionally, it controls the gradient norm, enabling efficient training and preventing issues like exploding or vanishing gradients. S7 significantly outperforms baselines across various sequence modeling tasks, including neuromorphic event-based datasets, Long Range Arena benchmarks, and various physical and biological time series. Overall, S7 offers a more straightforward approach to sequence modeling without relying on complex, domain-specific inductive biases, achieving significant improvements across key benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03464v1-abstract-full').style.display = 'none'; document.getElementById('2410.03464v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <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">23 pages, 3 figures, 11 tables. Equal contribution by Taylan Soydan and Nikola Zubi膰</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00181">arXiv:2410.00181</a> <span> [<a href="https://arxiv.org/pdf/2410.00181">pdf</a>, <a href="https://arxiv.org/format/2410.00181">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Analysis of human steering behavior differences in human-in-control and autonomy-in-control driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mai%2C+R">Rene Mai</a>, <a href="/search/cs?searchtype=author&query=Julius%2C+A">Agung Julius</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sandipan Mishra</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="2410.00181v1-abstract-short" style="display: inline;"> Steering models (such as the generalized two-point model) predict human steering behavior well when the human is in direct control of a vehicle. In vehicles under autonomous control, human control inputs are not used; rather, an autonomous controller applies steering and acceleration commands to the vehicle. For example, human steering input may be used for state estimation rather than direct cont… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00181v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00181v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00181v1-abstract-full" style="display: none;"> Steering models (such as the generalized two-point model) predict human steering behavior well when the human is in direct control of a vehicle. In vehicles under autonomous control, human control inputs are not used; rather, an autonomous controller applies steering and acceleration commands to the vehicle. For example, human steering input may be used for state estimation rather than direct control. We show that human steering behavior changes when the human no longer directly controls the vehicle and the two are instead working in a shared autonomy paradigm. Thus, when a vehicle is not under direct human control, steering models like the generalized two-point model do not predict human steering behavior. We also show that the error between predicted human steering behavior and actual human steering behavior reflects a fundamental difference when the human directly controls the vehicle compared to when the vehicle is autonomously controlled. Moreover, we show that a single distribution describes the error between predicted human steering behavior and actual human steering behavior when the human's steering inputs are used for state estimation and the vehicle is autonomously controlled, indicating there may be a underlying model for human steering behavior under this type of shared autonomous control. Future work includes determining this shared autonomous human steering model and demonstrating its performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00181v1-abstract-full').style.display = 'none'; document.getElementById('2410.00181v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> 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">6 pages, 10 figures, accepted for publication at the 5th IFAC at the 5th IFAC Workshop on Cyber-Physical Human Systems</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18359">arXiv:2409.18359</a> <span> [<a href="https://arxiv.org/pdf/2409.18359">pdf</a>, <a href="https://arxiv.org/format/2409.18359">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="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Fluid Dynamics">physics.flu-dyn</span> </div> </div> <p class="title is-5 mathjax"> Generative AI for fast and accurate statistical computation of fluids </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Molinaro%2C+R">Roberto Molinaro</a>, <a href="/search/cs?searchtype=author&query=Lanthaler%2C+S">Samuel Lanthaler</a>, <a href="/search/cs?searchtype=author&query=Raoni%C4%87%2C+B">Bogdan Raoni膰</a>, <a href="/search/cs?searchtype=author&query=Rohner%2C+T">Tobias Rohner</a>, <a href="/search/cs?searchtype=author&query=Armegioiu%2C+V">Victor Armegioiu</a>, <a href="/search/cs?searchtype=author&query=Simonis%2C+S">Stephan Simonis</a>, <a href="/search/cs?searchtype=author&query=Grund%2C+D">Dana Grund</a>, <a href="/search/cs?searchtype=author&query=Ramic%2C+Y">Yannick Ramic</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+Z+Y">Zhong Yi Wan</a>, <a href="/search/cs?searchtype=author&query=Sha%2C+F">Fei Sha</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Siddhartha Mishra</a>, <a href="/search/cs?searchtype=author&query=Zepeda-N%C3%BA%C3%B1ez%2C+L">Leonardo Zepeda-N煤帽ez</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="2409.18359v2-abstract-short" style="display: inline;"> We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on an end-to-end conditional score-based diffusion model. Through extensive numerical experimentation with a set of challenging fluid flows, we demonstrate that GenCFD provides an accurate a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18359v2-abstract-full').style.display = 'inline'; document.getElementById('2409.18359v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18359v2-abstract-full" style="display: none;"> We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on an end-to-end conditional score-based diffusion model. Through extensive numerical experimentation with a set of challenging fluid flows, we demonstrate that GenCFD provides an accurate approximation of relevant statistical quantities of interest while also efficiently generating high-quality realistic samples of turbulent fluid flows and ensuring excellent spectral resolution. In contrast, ensembles of deterministic ML algorithms, trained to minimize mean square errors, regress to the mean flow. We present rigorous theoretical results uncovering the surprising mechanisms through which diffusion models accurately generate fluid flows. These mechanisms are illustrated with solvable toy models that exhibit the mathematically relevant features of turbulent fluid flows while being amenable to explicit analytical formulae. Our codes are publicly available at https://github.com/camlab-ethz/GenCFD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18359v2-abstract-full').style.display = 'none'; document.getElementById('2409.18359v2-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">v1</span> submitted 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">120 pages, 33 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16799">arXiv:2409.16799</a> <span> [<a href="https://arxiv.org/pdf/2409.16799">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Large Language Model Predicts Above Normal All India Summer Monsoon Rainfall in 2024 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+U">Ujjawal Sharma</a>, <a href="/search/cs?searchtype=author&query=Biyani%2C+M">Madhav Biyani</a>, <a href="/search/cs?searchtype=author&query=Suresh%2C+A+D">Akhil Dev Suresh</a>, <a href="/search/cs?searchtype=author&query=Bhuyan%2C+D+P">Debi Prasad Bhuyan</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S+K">Saroj Kanta Mishra</a>, <a href="/search/cs?searchtype=author&query=Chakraborty%2C+T">Tanmoy Chakraborty</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="2409.16799v1-abstract-short" style="display: inline;"> Reliable prediction of the All India Summer Monsoon Rainfall (AISMR) is pivotal for informed policymaking for the country, impacting the lives of billions of people. However, accurate simulation of AISMR has been a persistent challenge due to the complex interplay of various muti-scale factors and the inherent variability of the monsoon system. This research focuses on adapting and fine-tuning the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16799v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16799v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16799v1-abstract-full" style="display: none;"> Reliable prediction of the All India Summer Monsoon Rainfall (AISMR) is pivotal for informed policymaking for the country, impacting the lives of billions of people. However, accurate simulation of AISMR has been a persistent challenge due to the complex interplay of various muti-scale factors and the inherent variability of the monsoon system. This research focuses on adapting and fine-tuning the latest LLM model, PatchTST, to accurately predict AISMR with a lead time of three months. The fine-tuned PatchTST model, trained with historical AISMR data, the Ni帽o3.4 index, and categorical Indian Ocean Dipole values, outperforms several popular neural network models and statistical models. This fine-tuned LLM model exhibits an exceptionally low RMSE percentage of 0.07% and a Spearman correlation of 0.976. This is particularly impressive, since it is nearly 80% more accurate than the best-performing NN models. The model predicts an above-normal monsoon for the year 2024, with an accumulated rainfall of 921.6 mm in the month of June-September for the entire country. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16799v1-abstract-full').style.display = 'none'; document.getElementById('2409.16799v1-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> <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">3 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/2409.08916">arXiv:2409.08916</a> <span> [<a href="https://arxiv.org/pdf/2409.08916">pdf</a>, <a href="https://arxiv.org/format/2409.08916">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+N">Namita Singh</a>, <a href="/search/cs?searchtype=author&query=Wang%27ombe%2C+J">Jacqueline Wang'ombe</a>, <a href="/search/cs?searchtype=author&query=Okanga%2C+N">Nereah Okanga</a>, <a href="/search/cs?searchtype=author&query=Zelenska%2C+T">Tetyana Zelenska</a>, <a href="/search/cs?searchtype=author&query=Repishti%2C+J">Jona Repishti</a>, <a href="/search/cs?searchtype=author&query=K%2C+J+G">Jayasankar G K</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sanjeev Mishra</a>, <a href="/search/cs?searchtype=author&query=Manokaran%2C+R">Rajsekar Manokaran</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+V">Vineet Singh</a>, <a href="/search/cs?searchtype=author&query=Rafiq%2C+M+I">Mohammed Irfan Rafiq</a>, <a href="/search/cs?searchtype=author&query=Gandhi%2C+R">Rikin Gandhi</a>, <a href="/search/cs?searchtype=author&query=Nambi%2C+A">Akshay Nambi</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="2409.08916v2-abstract-short" style="display: inline;"> Small and medium-sized agricultural holders face challenges like limited access to localized, timely information, impacting productivity and sustainability. Traditional extension services, which rely on in-person agents, struggle with scalability and timely delivery, especially in remote areas. We introduce FarmerChat, a generative AI-powered chatbot designed to address these issues. Leveraging Ge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08916v2-abstract-full').style.display = 'inline'; document.getElementById('2409.08916v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08916v2-abstract-full" style="display: none;"> Small and medium-sized agricultural holders face challenges like limited access to localized, timely information, impacting productivity and sustainability. Traditional extension services, which rely on in-person agents, struggle with scalability and timely delivery, especially in remote areas. We introduce FarmerChat, a generative AI-powered chatbot designed to address these issues. Leveraging Generative AI, FarmerChat offers personalized, reliable, and contextually relevant advice, overcoming limitations of previous chatbots in deterministic dialogue flows, language support, and unstructured data processing. Deployed in four countries, FarmerChat has engaged over 15,000 farmers and answered over 300,000 queries. This paper highlights how FarmerChat's innovative use of GenAI enhances agricultural service scalability and effectiveness. Our evaluation, combining quantitative analysis and qualitative insights, highlights FarmerChat's effectiveness in improving farming practices, enhancing trust, response quality, and user engagement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08916v2-abstract-full').style.display = 'none'; document.getElementById('2409.08916v2-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">v1</span> submitted 13 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">35 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.00801">arXiv:2409.00801</a> <span> [<a href="https://arxiv.org/pdf/2409.00801">pdf</a>, <a href="https://arxiv.org/format/2409.00801">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"> Container Data Item: An Abstract Datatype for Efficient Container-based Edge Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+R">Md Rezwanur Rahman</a>, <a href="/search/cs?searchtype=author&query=Annapareddy%2C+T">Tarun Annapareddy</a>, <a href="/search/cs?searchtype=author&query=Ebadi%2C+S">Shirin Ebadi</a>, <a href="/search/cs?searchtype=author&query=Natarajan%2C+V">Varsha Natarajan</a>, <a href="/search/cs?searchtype=author&query=Srinivasan%2C+A">Adarsh Srinivasan</a>, <a href="/search/cs?searchtype=author&query=Keller%2C+E">Eric Keller</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Shivakant Mishra</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="2409.00801v1-abstract-short" style="display: inline;"> We present Container Data Item (CDI), an abstract datatype that allows multiple containers to efficiently operate on a common data item while preserving their strong security and isolation semantics. Application developers can use CDIs to enable multiple containers to operate on the same data, synchronize execution among themselves, and control the ownership of the shared data item during runtime.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00801v1-abstract-full').style.display = 'inline'; document.getElementById('2409.00801v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00801v1-abstract-full" style="display: none;"> We present Container Data Item (CDI), an abstract datatype that allows multiple containers to efficiently operate on a common data item while preserving their strong security and isolation semantics. Application developers can use CDIs to enable multiple containers to operate on the same data, synchronize execution among themselves, and control the ownership of the shared data item during runtime. These containers may reside on the same server or different servers. CDI is designed to support microservice based applications comprised of a set of interconnected microservices, each implemented by a separate dedicated container. CDI preserves the important isolation semantics of containers by ensuring that exactly one container owns a CDI object at any instant and the ownership of a CDI object may be transferred from one container to another only by the current CDI object owner. We present three different implementations of CDI that allow different containers residing on the same server as well containers residing on different servers to use CDI for efficiently operating on a common data item. The paper provides an extensive performance evaluation of CDI along with two representative applications, an augmented reality application and a decentralized workflow orchestrator. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00801v1-abstract-full').style.display = 'none'; document.getElementById('2409.00801v1-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 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/2408.14379">arXiv:2408.14379</a> <span> [<a href="https://arxiv.org/pdf/2408.14379">pdf</a>, <a href="https://arxiv.org/format/2408.14379">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Synergistic and Efficient Edge-Host Communication for Energy Harvesting Wireless Sensor Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+C+S">Cyan Subhra Mishra</a>, <a href="/search/cs?searchtype=author&query=Sampson%2C+J">Jack Sampson</a>, <a href="/search/cs?searchtype=author&query=Kandmeir%2C+M+T">Mahmut Taylan Kandmeir</a>, <a href="/search/cs?searchtype=author&query=Narayanan%2C+V">Vijaykrishnan Narayanan</a>, <a href="/search/cs?searchtype=author&query=Das%2C+C+R">Chita R Das</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="2408.14379v1-abstract-short" style="display: inline;"> There is an increasing demand for intelligent processing on ultra-low-power internet of things (IoT) device. Recent works have shown substantial efficiency boosts by executing inferences directly on the IoT device (node) rather than transmitting data. However, the computation and power demands of Deep Neural Network (DNN)-based inference pose significant challenges in an energy-harvesting wireless… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14379v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14379v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14379v1-abstract-full" style="display: none;"> There is an increasing demand for intelligent processing on ultra-low-power internet of things (IoT) device. Recent works have shown substantial efficiency boosts by executing inferences directly on the IoT device (node) rather than transmitting data. However, the computation and power demands of Deep Neural Network (DNN)-based inference pose significant challenges in an energy-harvesting wireless sensor network (EH-WSN). Moreover, these tasks often require responses from multiple physically distributed EH sensor nodes, which impose crucial system optimization challenges in addition to per-node constraints. To address these challenges, we propose Seeker, a hardware-software co-design approach for increasing on-sensor computation, reducing communication volume, and maximizing inference completion, without violating the quality of service, in EH-WSNs coordinated by a mobile device. Seeker uses a store-and-execute approach to complete a subset of inferences on the EH sensor node, reducing communication with the mobile host. Further, for those inferences unfinished because of the harvested energy constraints, it leverages task-aware coreset construction to efficiently communicate compact features to the host device. We evaluate Seeker for human activity recognition, as well as predictive maintenance and show ~8.9x reduction in communication data volume with 86.8% accuracy, surpassing the 81.2% accuracy of the state-of-the-art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14379v1-abstract-full').style.display = 'none'; document.getElementById('2408.14379v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2204.13106</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13696">arXiv:2408.13696</a> <span> [<a href="https://arxiv.org/pdf/2408.13696">pdf</a>, <a href="https://arxiv.org/format/2408.13696">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"> Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mishra%2C+C+S">Cyan Subhra Mishra</a>, <a href="/search/cs?searchtype=author&query=Chaudhary%2C+D">Deeksha Chaudhary</a>, <a href="/search/cs?searchtype=author&query=Sampson%2C+J">Jack Sampson</a>, <a href="/search/cs?searchtype=author&query=Knademir%2C+M+T">Mahmut Taylan Knademir</a>, <a href="/search/cs?searchtype=author&query=Das%2C+C">Chita Das</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="2408.13696v2-abstract-short" style="display: inline;"> The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these challenges, this study introduces and evaluates a novel training methodology tailored for DNNs operating within such contexts. In particular, we propose a dynamic d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13696v2-abstract-full').style.display = 'inline'; document.getElementById('2408.13696v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13696v2-abstract-full" style="display: none;"> The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these challenges, this study introduces and evaluates a novel training methodology tailored for DNNs operating within such contexts. In particular, we propose a dynamic dropout technique that adapts to both the architecture of the device and the variability in energy availability inherent in energy harvesting scenarios. Our proposed approach leverages a device model that incorporates specific parameters of the network architecture and the energy harvesting profile to optimize dropout rates dynamically during the training phase. By modulating the network's training process based on predicted energy availability, our method not only conserves energy but also ensures sustained learning and inference capabilities under power constraints. Our preliminary results demonstrate that this strategy provides 6 to 22 percent accuracy improvements compared to the state of the art with less than 5 percent additional compute. This paper details the development of the device model, describes the integration of energy profiles with intermittency aware dropout and quantization algorithms, and presents a comprehensive evaluation of the proposed approach using real-world energy harvesting data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13696v2-abstract-full').style.display = 'none'; document.getElementById('2408.13696v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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/2408.12136">arXiv:2408.12136</a> <span> [<a href="https://arxiv.org/pdf/2408.12136">pdf</a>, <a href="https://arxiv.org/format/2408.12136">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"> Domain Adaptation for Offline Reinforcement Learning with Limited Samples </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weiqin Chen</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sandipan Mishra</a>, <a href="/search/cs?searchtype=author&query=Paternain%2C+S">Santiago Paternain</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="2408.12136v2-abstract-short" style="display: inline;"> Offline reinforcement learning (RL) learns effective policies from a static target dataset. Despite state-of-the-art (SOTA) offline RL algorithms being promising, they highly rely on the quality of the target dataset. The performance of SOTA algorithms can degrade in scenarios with limited samples in the target dataset, which is often the case in real-world applications. To address this issue, dom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12136v2-abstract-full').style.display = 'inline'; document.getElementById('2408.12136v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12136v2-abstract-full" style="display: none;"> Offline reinforcement learning (RL) learns effective policies from a static target dataset. Despite state-of-the-art (SOTA) offline RL algorithms being promising, they highly rely on the quality of the target dataset. The performance of SOTA algorithms can degrade in scenarios with limited samples in the target dataset, which is often the case in real-world applications. To address this issue, domain adaptation that leverages auxiliary samples from related source datasets (such as simulators) can be beneficial. In this context, determining the optimal way to trade off the source and target datasets remains a critical challenge in offline RL. To the best of our knowledge, this paper proposes the first framework that theoretically and experimentally explores how the weight assigned to each dataset affects the performance of offline RL. We establish the performance bounds and convergence neighborhood of our framework, both of which depend on the selection of the weight. Furthermore, we identify the existence of an optimal weight for balancing the two datasets. All theoretical guarantees and optimal weight depend on the quality of the source dataset and the size of the target dataset. Our empirical results on the well-known Procgen Benchmark substantiate our theoretical contributions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12136v2-abstract-full').style.display = 'none'; document.getElementById('2408.12136v2-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">v1</span> submitted 22 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/2408.11821">arXiv:2408.11821</a> <span> [<a href="https://arxiv.org/pdf/2408.11821">pdf</a>, <a href="https://arxiv.org/format/2408.11821">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 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.iot.2024.101075">10.1016/j.iot.2024.101075 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MIMA 2.0 -- Compact and Portable Multifunctional IoT integrated Menstrual Aid </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jyothish%2C+K+J">Kumar J. Jyothish</a>, <a href="/search/cs?searchtype=author&query=Shivangi%2C+S">Shreya Shivangi</a>, <a href="/search/cs?searchtype=author&query=Bibhu%2C+A">Amish Bibhu</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Subhankar Mishra</a>, <a href="/search/cs?searchtype=author&query=Saha%2C+S">Sulagna Saha</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="2408.11821v1-abstract-short" style="display: inline;"> The shredding intrauterine lining or the endometrium is known as Menstruation. It occurs every month and causes several issues like Menstrual Cramps and aches in the abdominal region, stains, menstrual malodor, rashes in intimate areas, and many more. In our research, almost all of the products available in the market do not cater to these problems single-handedly. There are few remedies available… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11821v1-abstract-full').style.display = 'inline'; document.getElementById('2408.11821v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11821v1-abstract-full" style="display: none;"> The shredding intrauterine lining or the endometrium is known as Menstruation. It occurs every month and causes several issues like Menstrual Cramps and aches in the abdominal region, stains, menstrual malodor, rashes in intimate areas, and many more. In our research, almost all of the products available in the market do not cater to these problems single-handedly. There are few remedies available to cater to the cramps, among which heat therapy is the most commonly used. Our methodology, involved surveys regarding problems and the solutions to these problems that are deemed optimal. This inclusive approach helped us infer about the gaps in available menstrual aids which has become our guide towards developing MIMA (Multifunctional IoT Integrated Menstrual Aid). In this paper, we have featured an IOT incorporated multifunctional smart intimate wear that aims to provide for the multiple necessities of women during menstruation like leakproof, antibacterial, anti-odor, rash-free experience along with an integrated Bluetooth-controlled intimate heat-pad for relieving abdominal cramps. The entire process of product development has been done in phases according to feedback from target users in each stage. This paper is an extension to our paper [1] which serves as the proof of concept for our approach. The development has led us towards MIMA 2.0 featuring a completely concealed and integrated design that includes a safe Bluetooth-controlled heating system for the intimate area. The product has received incredibly positive feedback from survey participants. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11821v1-abstract-full').style.display = 'none'; document.getElementById('2408.11821v1-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">Journal ref:</span> In Internet of Things (Vol. 25, p. 101075). Elsevier BV (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01729">arXiv:2408.01729</a> <span> [<a href="https://arxiv.org/pdf/2408.01729">pdf</a>, <a href="https://arxiv.org/format/2408.01729">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3648355">10.1145/3648355 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Survey on Robotic Prosthetics: Neuroprosthetics, Soft Actuators, and Control Strategies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jyothish%2C+K+J">Kumar J. Jyothish</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Subhankar Mishra</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="2408.01729v1-abstract-short" style="display: inline;"> The field of robotics is a quickly evolving feat of technology that accepts contributions from various genres of science. Neuroscience, Physiology, Chemistry, Material science, Computer science, and the wide umbrella of mechatronics have all simultaneously contributed to many innovations in the prosthetic applications of robotics. This review begins with a discussion of the scope of the term robot… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01729v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01729v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01729v1-abstract-full" style="display: none;"> The field of robotics is a quickly evolving feat of technology that accepts contributions from various genres of science. Neuroscience, Physiology, Chemistry, Material science, Computer science, and the wide umbrella of mechatronics have all simultaneously contributed to many innovations in the prosthetic applications of robotics. This review begins with a discussion of the scope of the term robotic prosthetics and discusses the evolving domain of Neuroprosthetics. The discussion is then constrained to focus on various actuation and control strategies for robotic prosthetic limbs. This review discusses various soft robotic actuators such as EAP, SMA, FFA, etc., and the merits of such actuators over conventional hard robotic actuators. Options in control strategies for robotic prosthetics, that are in various states of research and development, are reviewed. This paper concludes the discussion with an analysis regarding the prospective direction in which this field of robotic prosthetics is evolving in terms of actuation, control, and other features relevant to artificial limbs. This paper intends to review some of the emerging research and development trends in the field of robotic prosthetics and summarize many tangents that are represented under this broad domain in an approachable manner. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01729v1-abstract-full').style.display = 'none'; document.getElementById('2408.01729v1-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">Journal ref:</span> ACM Comput. Surv. 56, 8, Article 195 (August 2024), 44 pages </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.20782">arXiv:2407.20782</a> <span> [<a href="https://arxiv.org/pdf/2407.20782">pdf</a>, <a href="https://arxiv.org/format/2407.20782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Boundedness for Unions of Conjunctive Regular Path Queries over Simple Regular Expressions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Figueira%2C+D">Diego Figueira</a>, <a href="/search/cs?searchtype=author&query=Krishna%2C+S">S. Krishna</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+O+S">Om Swostik Mishra</a>, <a href="/search/cs?searchtype=author&query=Padmanabha%2C+A">Anantha Padmanabha</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="2407.20782v1-abstract-short" style="display: inline;"> The problem of checking whether a recursive query can be rewritten as query without recursion is a fundamental reasoning task, known as the boundedness problem. Here we study the boundedness problem for Unions of Conjunctive Regular Path Queries (UCRPQs), a navigational query language extensively used in ontology and graph database querying. The boundedness problem for UCRPQs is ExpSpace-complete.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.20782v1-abstract-full').style.display = 'inline'; document.getElementById('2407.20782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.20782v1-abstract-full" style="display: none;"> The problem of checking whether a recursive query can be rewritten as query without recursion is a fundamental reasoning task, known as the boundedness problem. Here we study the boundedness problem for Unions of Conjunctive Regular Path Queries (UCRPQs), a navigational query language extensively used in ontology and graph database querying. The boundedness problem for UCRPQs is ExpSpace-complete. Here we focus our analysis on UCRPQs using simple regular expressions, which are of high practical relevance and enjoy a lower reasoning complexity. We show that the complexity for the boundedness problem for this UCRPQs fragment is $螤^P_2$-complete, and that an equivalent bounded query can be produced in polynomial time whenever possible. When the query turns out to be unbounded, we also study the task of finding an equivalent maximally bounded query, which we show to be feasible in $螤^P_2$. As a side result of independent interest stemming from our developments, we study a notion of succinct finite automata and prove that its membership problem is in NP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.20782v1-abstract-full').style.display = 'none'; document.getElementById('2407.20782v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 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/2407.09855">arXiv:2407.09855</a> <span> [<a href="https://arxiv.org/pdf/2407.09855">pdf</a>, <a href="https://arxiv.org/format/2407.09855">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"> Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Parida%2C+S">Shantipriya Parida</a>, <a href="/search/cs?searchtype=author&query=Panwar%2C+S">Shakshi Panwar</a>, <a href="/search/cs?searchtype=author&query=Lata%2C+K">Kusum Lata</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Sanskruti Mishra</a>, <a href="/search/cs?searchtype=author&query=Sekhar%2C+S">Sambit Sekhar</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="2407.09855v1-abstract-short" style="display: inline;"> Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic languages, is the availability of high-quality data for building foundation LLMs. In this paper, we are proposing a large pre-train dataset in Hindi useful for the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09855v1-abstract-full').style.display = 'inline'; document.getElementById('2407.09855v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09855v1-abstract-full" style="display: none;"> Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic languages, is the availability of high-quality data for building foundation LLMs. In this paper, we are proposing a large pre-train dataset in Hindi useful for the Indic language Hindi. We have collected the data span across several domains including major dialects in Hindi. The dataset contains 1.28 billion Hindi tokens. We have explained our pipeline including data collection, pre-processing, and availability for LLM pre-training. The proposed approach can be easily extended to other Indic and low-resource languages and will be available freely for LLM pre-training and LLM research purposes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09855v1-abstract-full').style.display = 'none'; document.getElementById('2407.09855v1-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 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 as a book chapter in the book Title "APPLIED SPEECH AND TEXT PROCESSING FOR LOW RESOURCE LANGUAGES"</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08223">arXiv:2407.08223</a> <span> [<a href="https://arxiv.org/pdf/2407.08223">pdf</a>, <a href="https://arxiv.org/format/2407.08223">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"> Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zilong Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zifeng Wang</a>, <a href="/search/cs?searchtype=author&query=Le%2C+L">Long Le</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H+S">Huaixiu Steven Zheng</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swaroop Mishra</a>, <a href="/search/cs?searchtype=author&query=Perot%2C+V">Vincent Perot</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuwei Zhang</a>, <a href="/search/cs?searchtype=author&query=Mattapalli%2C+A">Anush Mattapalli</a>, <a href="/search/cs?searchtype=author&query=Taly%2C+A">Ankur Taly</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+J">Jingbo Shang</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+C">Chen-Yu Lee</a>, <a href="/search/cs?searchtype=author&query=Pfister%2C+T">Tomas Pfister</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="2407.08223v1-abstract-short" style="display: inline;"> Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval outcomes through iterative LLM refinement or self-critique capabilities acquired through additional instruction tuning of LLMs. In this work, we introduce Specul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08223v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08223v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08223v1-abstract-full" style="display: none;"> Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval outcomes through iterative LLM refinement or self-critique capabilities acquired through additional instruction tuning of LLMs. In this work, we introduce Speculative RAG - a framework that leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM. Each draft is generated from a distinct subset of retrieved documents, offering diverse perspectives on the evidence while reducing input token counts per draft. This approach enhances comprehension of each subset and mitigates potential position bias over long context. Our method accelerates RAG by delegating drafting to the smaller specialist LM, with the larger generalist LM performing a single verification pass over the drafts. Extensive experiments demonstrate that Speculative RAG achieves state-of-the-art performance with reduced latency on TriviaQA, MuSiQue, PubHealth, and ARC-Challenge benchmarks. It notably enhances accuracy by up to 12.97% while reducing latency by 51% compared to conventional RAG systems on PubHealth. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08223v1-abstract-full').style.display = 'none'; document.getElementById('2407.08223v1-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 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">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/2407.05986">arXiv:2407.05986</a> <span> [<a href="https://arxiv.org/pdf/2407.05986">pdf</a>, <a href="https://arxiv.org/format/2407.05986">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"> KidSat: satellite imagery to map childhood poverty dataset and benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+M">Makkunda Sharma</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/cs?searchtype=author&query=Vo%2C+D">Duy-Nhat Vo</a>, <a href="/search/cs?searchtype=author&query=Suel%2C+E">Esra Suel</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/cs?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/cs?searchtype=author&query=Fiala%2C+O">Oliver Fiala</a>, <a href="/search/cs?searchtype=author&query=Rudgard%2C+W">William Rudgard</a>, <a href="/search/cs?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2407.05986v1-abstract-short" style="display: inline;"> Satellite imagery has emerged as an important tool to analyse demographic, health, and development indicators. While various deep learning models have been built for these tasks, each is specific to a particular problem, with few standard benchmarks available. We propose a new dataset pairing satellite imagery and high-quality survey data on child poverty to benchmark satellite feature representat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05986v1-abstract-full').style.display = 'inline'; document.getElementById('2407.05986v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05986v1-abstract-full" style="display: none;"> Satellite imagery has emerged as an important tool to analyse demographic, health, and development indicators. While various deep learning models have been built for these tasks, each is specific to a particular problem, with few standard benchmarks available. We propose a new dataset pairing satellite imagery and high-quality survey data on child poverty to benchmark satellite feature representations. Our dataset consists of 33,608 images, each 10 km $\times$ 10 km, from 19 countries in Eastern and Southern Africa in the time period 1997-2022. As defined by UNICEF, multidimensional child poverty covers six dimensions and it can be calculated from the face-to-face Demographic and Health Surveys (DHS) Program . As part of the benchmark, we test spatial as well as temporal generalization, by testing on unseen locations, and on data after the training years. Using our dataset we benchmark multiple models, from low-level satellite imagery models such as MOSAIKS , to deep learning foundation models, which include both generic vision models such as Self-Distillation with no Labels (DINOv2) models and specific satellite imagery models such as SatMAE. We provide open source code for building the satellite dataset, obtaining ground truth data from DHS and running various models assessed in our work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05986v1-abstract-full').style.display = 'none'; document.getElementById('2407.05986v1-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">15 pages, 1 figure</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Mishra%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